Pith. sign in

REVIEW 2 major objections 2 minor 60 cited by

A methodology-centered taxonomy unifies how LLM agents are built, collaborate, and evolve.

Reviewed by Pith at T0; open to challenge. T0 means a machine referee read the full paper against a public rubric. the ladder, T0–T4 →

Challenge this review Download PDF Read on arXiv ↗

T0 review · grok-4.3

2026-05-22 21:48 UTC

load-bearing objection Standard survey that taxonomizes LLM agent work but gives no details on paper selection or coverage. the 2 major comments →

arxiv 2503.21460 v1 submitted 2025-03-27 cs.CL

Large Language Model Agent: A Survey on Methodology, Applications and Challenges

Junyu Luo , Weizhi Zhang , Ye Yuan , Yusheng Zhao , Junwei Yang , Yiyang Gu , Bohan Wu , Binqi Chen
show 18 more authors
Ziyue Qiao Qingqing Long Rongcheng Tu Xiao Luo Wei Ju Zhiping Xiao Yifan Wang Meng Xiao Chenwu Liu Jingyang Yuan Shichang Zhang Yiqiao Jin Fan Zhang Xian Wu Hanqing Zhao Dacheng Tao Philip S. Yu Ming Zhang
This is my paper
classification cs.CL
keywords LLM agentssurveytaxonomymethodologymulti-agent systemsagent evolutiontool useevaluation
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

The pith

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This survey organizes LLM agent research around a single taxonomy focused on methodology. It connects the basic building blocks of agent design to how multiple agents work together and how the systems change over time. The goal is to show hidden links between separate studies that otherwise look unrelated. By doing this, the survey also covers how to test these agents, what tools they use, and the main practical problems that remain. A reader who accepts the taxonomy gains a single map for an otherwise scattered collection of papers on goal-driven AI systems.

Core claim

The survey claims that LLM agent systems are best understood by grouping them according to the methods used to construct them, rather than by application or by model size. This grouping reveals direct connections between architectural choices, multi-agent cooperation rules, and the paths agents take as they improve or adapt. The taxonomy therefore turns a fragmented set of papers into one coherent picture that also includes evaluation methods, tool use, open challenges, and real-world domains.

What carries the argument

The methodology-centered taxonomy that groups agent systems by how they are constructed, how they collaborate, and how they change over time.

Load-bearing premise

One fixed taxonomy built around methodology can capture the main patterns in a fast-moving field without leaving out important new designs or forcing unrelated work into the same boxes.

What would settle it

Publication of multiple new LLM agent papers whose designs cannot be placed into any of the taxonomy's main categories without stretching the definitions.

Watch this falsifier — get emailed when new claim-graph text bears on it.

If this is right

  • Future papers can cite the taxonomy to position their contribution instead of starting from scratch.
  • Evaluation benchmarks can be organized by the same methodological categories used for design.
  • Tool-use and collaboration patterns become comparable across studies once they share the same taxonomy slots.
  • Application domains can be mapped to the architectural and evolutionary parts of the taxonomy to spot gaps.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • If the taxonomy holds, new agent designs could be generated by recombining existing categories rather than starting from scratch.
  • The same structure might later be applied to non-LLM agents to test whether the methodological patterns are general.
  • Rapid growth in the field will test whether the taxonomy needs frequent updates or whether its top-level categories remain stable.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit.

Referee Report

2 major / 2 minor

Summary. The paper is a survey on LLM agents that proposes a methodology-centered taxonomy linking architectural foundations, collaboration mechanisms, and evolutionary pathways. It claims to unify fragmented research threads, examines construction, collaboration, evolution, evaluation, tools, challenges, and applications, and provides a GitHub collection of papers.

Significance. If the taxonomy proves comprehensive and representative, the survey would supply a useful organizational framework for a rapidly evolving area, with the GitHub repository serving as a concrete, reusable resource that supports reproducibility of the literature collection.

major comments (2)
  1. [Abstract / §1] Abstract and §1: The central claim that the survey 'systematically deconstructs LLM agent systems through a methodology-centered taxonomy' and 'unifies fragmented research threads' is load-bearing, yet no details are supplied on literature search strategy, databases, date cutoffs, inclusion/exclusion rules, or total papers reviewed. This omission prevents verification that the taxonomy rests on a representative sample rather than selective or post-hoc groupings.
  2. [Taxonomy sections] Taxonomy sections (e.g., those presenting the methodology-centered categories): It is unclear how the three main axes (architectural foundations, collaboration mechanisms, evolutionary pathways) were derived from the literature and whether they reflect genuine cross-cutting connections or are imposed categorizations; explicit justification or derivation steps for the taxonomy structure are needed to support the unification assertion.
minor comments (2)
  1. Ensure the GitHub repository is kept up to date with all references cited in the final version and includes a README describing the collection process.
  2. Add a short dedicated subsection on survey methodology (search terms, screening process) to make the coverage claims verifiable.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback and the recommendation of minor revision. The comments identify opportunities to increase transparency in the survey methodology and taxonomy construction. We address each point below and will revise the manuscript to incorporate the suggested clarifications.

read point-by-point responses

  1. Referee: [Abstract / §1] Abstract and §1: The central claim that the survey 'systematically deconstructs LLM agent systems through a methodology-centered taxonomy' and 'unifies fragmented research threads' is load-bearing, yet no details are supplied on literature search strategy, databases, date cutoffs, inclusion/exclusion rules, or total papers reviewed. This omission prevents verification that the taxonomy rests on a representative sample rather than selective or post-hoc groupings.

    Authors: We agree that explicit documentation of the literature search process would strengthen verifiability. The revised manuscript will add a dedicated subsection (new §1.3) detailing the systematic review protocol: databases searched (arXiv, ACL Anthology, Google Scholar, NeurIPS/ICLR/ICML proceedings), primary keywords and Boolean combinations used, date range (January 2022–March 2025), inclusion criteria (papers that propose or analyze methodological components of LLM agents), exclusion criteria (purely application-focused works without architectural discussion, non-English papers), and the final count of papers retained. The existing GitHub repository will be annotated with the same protocol to enable independent verification. revision: yes

  2. Referee: [Taxonomy sections] Taxonomy sections (e.g., those presenting the methodology-centered categories): It is unclear how the three main axes (architectural foundations, collaboration mechanisms, evolutionary pathways) were derived from the literature and whether they reflect genuine cross-cutting connections or are imposed categorizations; explicit justification or derivation steps for the taxonomy structure are needed to support the unification assertion.

    Authors: The three axes emerged from iterative coding of recurring design patterns across the collected papers rather than from a single a-priori framework. In the revision we will insert an explicit derivation paragraph at the start of the taxonomy section that walks through the bottom-up process: (i) clustering of single-agent papers by core architectural choices, (ii) identification of interaction primitives that appear across multi-agent studies, and (iii) extraction of temporal adaptation mechanisms from long-horizon agent work. We will also add a short table showing representative papers that instantiate each axis and the intersections between them, thereby demonstrating that the taxonomy captures observed cross-cutting connections rather than imposing an external structure. revision: yes

Circularity Check

0 steps flagged

No circularity: survey organizes external literature without derivations or self-referential reductions

full rationale

This is a literature survey paper that proposes a methodology-centered taxonomy to organize existing LLM agent research from external sources. There are no equations, derivations, predictions, fitted parameters, or first-principles results that could reduce to the paper's own inputs by construction. The central claim of unifying threads is an organizational assertion based on reviewed literature, not a load-bearing derivation. No self-citation chains, uniqueness theorems, or ansatzes are invoked in any derivation step, as none exist. The GitHub collection is a supplementary resource for the surveyed papers and does not create circularity under the enumerated patterns. This matches the default expectation for honest non-findings in purely review works that remain self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

As a survey the paper introduces no free parameters, new axioms, or invented entities; it relies on standard assumptions about the value of taxonomies in organizing AI literature.

pith-pipeline@v0.9.0 · 5781 in / 954 out tokens · 20971 ms · 2026-05-22T21:48:59.165329+00:00 · methodology

0 comments
read the original abstract

The era of intelligent agents is upon us, driven by revolutionary advancements in large language models. Large Language Model (LLM) agents, with goal-driven behaviors and dynamic adaptation capabilities, potentially represent a critical pathway toward artificial general intelligence. This survey systematically deconstructs LLM agent systems through a methodology-centered taxonomy, linking architectural foundations, collaboration mechanisms, and evolutionary pathways. We unify fragmented research threads by revealing fundamental connections between agent design principles and their emergent behaviors in complex environments. Our work provides a unified architectural perspective, examining how agents are constructed, how they collaborate, and how they evolve over time, while also addressing evaluation methodologies, tool applications, practical challenges, and diverse application domains. By surveying the latest developments in this rapidly evolving field, we offer researchers a structured taxonomy for understanding LLM agents and identify promising directions for future research. The collection is available at https://github.com/luo-junyu/Awesome-Agent-Papers.

Figures

Figures reproduced from arXiv: 2503.21460 by Binqi Chen, Bohan Wu, Chenwu Liu, Dacheng Tao, Fan Zhang, Hanqing Zhao, Jingyang Yuan, Junwei Yang, Junyu Luo, Meng Xiao, Ming Zhang, Philip S. Yu, Qingqing Long, Rongcheng Tu, Shichang Zhang, Wei Ju, Weizhi Zhang, Xian Wu, Xiao Luo, Ye Yuan, Yifan Wang, Yiqiao Jin, Yiyang Gu, Yusheng Zhao, Zhiping Xiao, Ziyue Qiao.

Figure 1
Figure 1. Figure 1: An overview of the LLM agent ecosystem organized into four interconnected dimensions: [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: A taxonomy of large language model agent methodologies. [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: An overview of evaluation benchmarks and tools [PITH_FULL_IMAGE:figures/full_fig_p008_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: An overview of real-world issues in LLM agent [PITH_FULL_IMAGE:figures/full_fig_p010_4.png] view at source ↗

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 60 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Agent-ValueBench: A Comprehensive Benchmark for Evaluating Agent Values

    cs.AI 2026-05 unverdicted novelty 8.0

    Agent-ValueBench is the first dedicated benchmark for agent values, showing they diverge from LLM values, form a homogeneous 'Value Tide' across models, and bend under harnesses and skill steering.

  2. LLM-as-an-Investigator: Evidence-First Reasoning for Robust Interactive Problem Diagnosis

    cs.AI 2026-06 unverdicted novelty 7.0

    LLM-as-an-Investigator improves diagnostic accuracy over direct prompting by using an evidence-first protocol of hypothesis generation, clarification questions, and iterative probability updates in technical problem solving.

  3. TimeSage-MT: A Multi-Turn Benchmark for Evaluating Agentic Time Series Reasoning

    cs.CL 2026-05 unverdicted novelty 7.0

    TimeSage-MT introduces a multi-turn benchmark for agentic time series reasoning and shows frontier LLMs drop sharply on decision-oriented tasks due to memory and uncertainty failures.

  4. Skill or Skip? Learning Selective Skill Invocation in Agentic Tasks via Dual-Granularity Preference Learning

    cs.CL 2026-05 unverdicted novelty 7.0

    SelSkill applies dual-granularity preference learning to selective skill-or-skip decisions, improving task success by 10.9 points and execution precision by 29.1 points on ALFWorld with Qwen3-8B.

  5. Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems

    cs.AI 2026-05 unverdicted novelty 7.0

    AgingBench demonstrates multi-dimensional degradation in deployed AI agents through four aging mechanisms diagnosed by temporal graphs and counterfactual probes across hundreds of runs.

  6. A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE

    cs.CL 2026-05 unverdicted novelty 7.0

    PARAMΔ upcycles dense models to MoE for per-language experts and grafts post-training deltas to enable data-efficient language expansion while preserving original capabilities.

  7. Learning Agentic Policy from Action Guidance

    cs.CL 2026-05 unverdicted novelty 7.0

    ActGuide-RL uses human action data as plan-style guidance in mixed-policy RL to overcome exploration barriers in LLM agents, matching SFT+RL performance on search benchmarks without cold-start training.

  8. DRIP-R: A Benchmark for Decision-Making and Reasoning Under Real-World Policy Ambiguity in the Retail Domain

    cs.CL 2026-05 unverdicted novelty 7.0

    DRIP-R is a new benchmark showing that frontier LLMs systematically disagree on how to resolve identical ambiguous retail policy scenarios, highlighting ambiguity as a core challenge for agent decision-making.

  9. WaterAdmin: Orchestrating Community Water Distribution Optimization via AI Agents

    cs.LG 2026-04 unverdicted novelty 7.0

    WaterAdmin uses a bi-level design with LLM agents for dynamic context abstraction and optimization for real-time pump/valve control, achieving better pressure reliability and lower energy use than traditional methods ...

  10. Skill-Conditioned Visual Geolocation for Vision-Language Models

    cs.CV 2026-04 unverdicted novelty 7.0

    GeoSkill uses an evolving Skill-Graph initialized from expert trajectories and grown via autonomous analysis of successful and failed reasoning rollouts to boost geolocation accuracy, faithfulness, and generalization ...

  11. Skill-Conditioned Visual Geolocation for Vision-Language Models

    cs.CV 2026-04 unverdicted novelty 7.0

    GeoSkill lets vision-language models improve geolocation accuracy and reasoning by maintaining an evolving Skill-Graph that grows through autonomous analysis of successful and failed rollouts on web-scale image data.

  12. GenCellAgent: Generalizable, Training-Free Cellular Image Segmentation via Large Language Model Agents

    q-bio.QM 2025-10 unverdicted novelty 7.0

    GenCellAgent deploys a planner-executor-evaluator LLM agent loop to automatically select, adapt, and refine segmentation tools for diverse cellular microscopy images, matching or exceeding specialist performance on 4,...

  13. Mandol: An Agglomerative Agent Memory System for Long-Term Conversations

    cs.DB 2026-06 unverdicted novelty 6.0

    Mandol unifies memory storage and retrieval into an agglomerative semantic graph architecture with quantitative query mechanisms, reporting best accuracy on LoCoMo and LongMemEval plus 5.4x retrieval and 4.8x insertio...

  14. TriggerBench: Investigating Prospective Memory for Large Language Models

    cs.CL 2026-06 unverdicted novelty 6.0

    TriggerBench is a new benchmark showing prospective memory in LLMs is harder than retrospective memory, exhibits precision-recall trade-offs, and may indicate spare reasoning capacity.

  15. Managing Procedural Memory in LLM Agents: Control, Adaptation, and Evaluation

    cs.AI 2026-06 unverdicted novelty 6.0

    AFTER benchmark shows single refinement improves LLM agent performance by 3.7-6.7 points and multi-model procedural skills reach 73.1% cross-model accuracy on 382 tasks.

  16. Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning

    cs.LG 2026-06 unverdicted novelty 6.0

    G2PO transforms linear trajectories into graphs, aggregates identical states for lower-variance value estimates, and uses edge-centric TD standardization, reporting up to 22.2% gains over GRPO on WebShop, ALFWorld, an...

  17. When Lower Privileges Suffice: Investigating Over-Privileged Tool Selection in LLM Agents

    cs.SE 2026-06 unverdicted novelty 6.0

    LLM agents commonly select over-privileged tools across domains, a tendency worsened by transient failures and not fixed by standard safety alignment, but reducible by privilege-aware post-training.

  18. BioHarness: Substrate-Aware Evidence Assembly for Biomedical Question Answering across Literature, Knowledge Bases, and Biological Atlases

    q-bio.QM 2026-06 unverdicted novelty 6.0

    BioHarness improves pooled biomedical QA score from 65.9 to 71.0 on 19,302 items by using staged, substrate-aware evidence assembly that escalates only when needed.

  19. SkillJuror: Measuring How Agent Skill Organization Changes Runtime Behavior

    cs.AI 2026-06 unverdicted novelty 6.0

    Empirical study finds Progressive Disclosure raises distinct resources touched (1.18 to 3.85) and uptake events (1.33 to 3.92) per trajectory, adds 17 passing trials out of 410 (+4.1%), with gains task-dependent.

  20. Civil Court Simulation with Large Language Models

    cs.CL 2026-06 unverdicted novelty 6.0

    Multi-agent LLM framework simulates Chinese civil trials through five-stage procedures with memory and retrieval, producing judgments strong in liability allocation and multi-item decisions.

  21. Workflow-to-Skill: Skill Creation via Routing-Workflow-Semantics-Attachments Decomposition

    cs.AI 2026-06 unverdicted novelty 6.0

    W2S framework with RWSA decomposition converts heterogeneous traces into Skills and improves behavioral replay consistency by 10.5% over summarization baselines on 70 Skills.

  22. Beyond Alignment: Value Diversity as a Collective Property in Multicultural Agent Systems

    cs.CL 2026-06 unverdicted novelty 6.0

    Multicultural multi-agent LLM systems exhibit substantially lower value diversity than human societies on the World Values Survey, with diversity uncorrelated to per-agent alignment and further reduced by agent interactions.

  23. SeClaw: Spec-Driven Security Task Synthesis for Evaluating Autonomous Agents

    cs.CR 2026-06 unverdicted novelty 6.0

    SeClaw provides spec-driven synthesis of security tasks and an execution-based docker testbed for evaluating unsafe behaviors in autonomous LLM agents.

  24. A Unified Framework for the Evaluation of LLM Agentic Capabilities

    cs.AI 2026-05 unverdicted novelty 6.0

    A unified framework standardizes LLM agent benchmarks and demonstrates through 400K rollouts that scaffold and environment choices materially alter outcomes, enabling separation of intrinsic capabilities from artifacts.

  25. TrajAudit: Automated Failure Diagnosis for Agentic Coding Systems

    cs.SE 2026-05 unverdicted novelty 6.0

    TrajAudit diagnoses failures in repository-level agentic coding trajectories by filtering noise and injecting test-failure priors, achieving >24.4 pp higher localization accuracy and 18% lower token use on the new Roo...

  26. From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills

    cs.AI 2026-05 unverdicted novelty 6.0

    A systematic study across five domains finds model-generated skills yield average gains but non-uniform negative transfer, with a meta-skill improving extraction quality.

  27. OEP: Poisoning Self-Evolving LLM Agents via Locally Correct but Non-Transferable Experiences

    cs.CR 2026-05 unverdicted novelty 6.0

    OEP poisons self-evolving LLM agents by constructing clean edge-case experiences that appear locally valid yet cause harmful over-generalization during reflection, achieving over 50% attack success rate on GPT-4o agen...

  28. Dynamic Skill Lifecycle Management for Agentic Reinforcement Learning

    cs.LG 2026-05 unverdicted novelty 6.0

    SLIM dynamically optimizes active external skills in agentic RL via leave-one-skill-out marginal contribution estimates and three lifecycle operations, outperforming baselines by 7.1% on ALFWorld and SearchQA while sh...

  29. From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills

    cs.CL 2026-04 unverdicted novelty 6.0

    SSL representation disentangles skill scheduling, structure, and logic using an LLM normalizer, improving skill discovery MRR@50 from 0.649 to 0.729 and risk assessment macro F1 from 0.409 to 0.509 over text baselines.

  30. Learning to Evolve: A Self-Improving Framework for Multi-Agent Systems via Textual Parameter Graph Optimization

    cs.AI 2026-04 unverdicted novelty 6.0

    TPGO represents multi-agent systems as graphs of textual parameters and applies group relative optimization to enable self-improvement from execution history.

  31. SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models

    cs.AI 2026-04 unverdicted novelty 6.0

    SafetyALFRED shows multimodal LLMs recognize kitchen hazards accurately in QA tests but achieve low success rates when required to mitigate those hazards through embodied planning.

  32. ChemGraph-XANES: An Agentic Framework for XANES Simulation and Curation

    cond-mat.mtrl-sci 2026-04 unverdicted novelty 6.0

    An LLM-orchestrated framework automates the full XANES workflow from natural language to normalized spectra and curated data.

  33. Chain-of-Authorization: Embedding authorization into large language models

    cs.AI 2026-03 unverdicted novelty 6.0

    LLMs fine-tuned to output authorization trajectories as a prerequisite for responses achieve high rejection rates for unauthorized prompts while preserving utility in allowed scenarios.

  34. EcoGym: Evaluating LLMs for Long-Horizon Plan-and-Execute in Interactive Economies

    cs.CL 2026-02 conditional novelty 6.0

    EcoGym is a new open benchmark with three economic environments that reveals no leading LLM dominates at sustained plan-and-execute decision making across scenarios.

  35. SupChain-Bench: Benchmarking Large Language Models for Real-World Supply Chain Management

    cs.AI 2026-02 unverdicted novelty 6.0

    SupChain-Bench reveals substantial gaps in LLM reliability for long-horizon supply chain orchestration, while the proposed SupChain-ReAct framework improves tool-calling by autonomously synthesizing procedures.

  36. WorldCup Sampling for Multi-bit LLM Watermarking

    cs.CL 2026-02 unverdicted novelty 6.0

    WorldCup is a new multi-bit LLM watermarking framework that models token sampling as a communication channel and uses hierarchical competition with entropy-aware modulation for robust message embedding and recovery.

  37. SciHorizon-GENE: Benchmarking LLM for Life Sciences Inference from Gene Knowledge to Functional Understanding

    q-bio.GN 2026-01 unverdicted novelty 6.0

    SciHorizon-GENE is a large-scale benchmark evaluating LLMs on gene-to-function inference across four perspectives, revealing heterogeneity and challenges in faithful, complete, literature-grounded outputs.

  38. EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle

    cs.CL 2025-10 unverdicted novelty 6.0

    EvolveR enables LLM agents to self-evolve via a closed loop of distilling interaction trajectories into strategic principles offline and retrieving them to guide online decisions with policy reinforcement, yielding be...

  39. The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

    cs.AI 2025-09 accept novelty 6.0

    Survey that defines agentic RL for LLMs via POMDPs, introduces a taxonomy of planning/tool-use/memory/reasoning capabilities and domains, and compiles open environments from over 500 papers.

  40. RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources

    cs.SE 2026-06 unverdicted novelty 5.0

    RESOURCE2SKILL converts multimodal human resources into a hierarchical Skill Wiki of executable agent skills, reporting +11.9 percentage point average gains over no-skill baselines across seven authoring domains.

  41. RubricsTree: Scalable and Evolving Open-Ended Evaluation of Personal Health Agents across Health Memory and Medical Skills

    cs.CL 2026-06 unverdicted novelty 5.0

    RubricsTree is a scalable, evolving rubric-based evaluation system with adaptive routing that improves physician alignment for health AI responses and enables performance gains when used as feedback or rewards.

  42. EnvRL: Learn from Environment Dynamics in Agentic Reinforcement Learning

    cs.LG 2026-06 unverdicted novelty 5.0

    EnvRL incorporates environment dynamics learning via state prediction and inverse dynamics auxiliary objectives into agentic RL, reporting higher success rates than RL-only baselines on ALFWorld and WebShop.

  43. A Unified Framework for the Evaluation of LLM Agentic Capabilities

    cs.AI 2026-05 unverdicted novelty 5.0

    A unified framework integrates 7 benchmarks across 24 domains using standardized formats, fixed ReAct execution, and offline snapshots to disentangle intrinsic LLM agent capabilities from scaffold and environment arti...

  44. Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs

    cs.CL 2026-05 unverdicted novelty 5.0

    Mix-Quant quantizes prefilling to NVFP4 and keeps BF16 for decoding in agentic LLMs, achieving up to 3x prefilling speedup while largely preserving task performance on long-context and agentic benchmarks.

  45. Dynamic Skill Lifecycle Management for Agentic Reinforcement Learning

    cs.LG 2026-05 unverdicted novelty 5.0

    SLIM dynamically optimizes the active external skill set in agentic RL via leave-one-skill-out marginal contribution estimates and lifecycle operations, delivering a 7.1% average gain over baselines on ALFWorld and Se...

  46. Heterogeneous Scientific Foundation Model Collaboration

    cs.AI 2026-04 unverdicted novelty 5.0

    Eywa enables language-based agentic AI systems to collaborate with specialized scientific foundation models for improved performance on structured data tasks.

  47. Test-time Scaling over Perception: Resolving the Grounding Paradox in Thinking with Images

    cs.CV 2026-04 unverdicted novelty 5.0

    TTSP resolves the Grounding Paradox by treating perception as a scalable test-time process that generates, filters, and iteratively refines multiple visual exploration traces, outperforming baselines on high-resolutio...

  48. Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering

    cs.SE 2026-04 accept novelty 5.0

    LLM agent progress depends on externalizing cognitive functions into memory, skills, protocols, and harness engineering that coordinates them reliably.

  49. Security Threat Modeling for Emerging AI-Agent Protocols: A Comparative Analysis of MCP, A2A, Agora, and ANP

    cs.CR 2026-02 unverdicted novelty 5.0

    The paper identifies twelve protocol-level security risks across MCP, A2A, Agora, and ANP and quantifies wrong-provider tool execution risk in MCP via a measurement-driven case study on multi-server composition.

  50. MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning

    cs.AI 2026-01 unverdicted novelty 5.0

    MemOCR renders structured memory as images with adaptive visual density to improve long-horizon reasoning under tight context budgets.

  51. EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle

    cs.CL 2025-10 unverdicted novelty 5.0

    EvolveR proposes a closed-loop self-evolution system for LLM agents that distills experiences into principles offline and applies reinforcement during online task interactions to achieve better performance on multi-ho...

  52. Small Language Models are the Future of Agentic AI

    cs.AI 2025-06 unverdicted novelty 5.0

    Small language models are sufficiently capable, more suitable, and far more economical than large models for the repetitive tasks that dominate agentic AI systems.

  53. OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning

    cs.CL 2026-06 unverdicted novelty 4.0

    OPID distills episode- and step-level skills from completed on-policy trajectories, routes them via critical-first mechanism, and combines the resulting log-probability shift advantage with outcome advantage for polic...

  54. From Question Answering to Task Completion: A Survey on Agent System and Harness Design

    cs.AI 2026-06 unverdicted novelty 4.0

    Survey framing LLM agents as model-plus-harness systems, decomposing harness responsibilities, mapping them to tasks, and highlighting open challenges in evaluation, safety, and co-evolution.

  55. A Robust Agentic Framework for Expert-Level Automation of Atomistic Simulations

    cond-mat.mtrl-sci 2026-06 unverdicted novelty 4.0

    Paimon is an agentic framework that automates atomistic simulations and improves reliability by suppressing silent errors in agent workflows, demonstrated on liquid electrolyte cases and literature reproduction.

  56. Post-AGI Economies: Superposition and the Second Fundamental Theorem of Welfare Economics

    cs.GT 2026-06 unverdicted novelty 4.0

    An autonomy-qualified Second Welfare Theorem is stated for post-AGI economies under the joint conditions of convexity, stable moral status, non-fungible rights, welfare selection, non-manipulation, governed self-modif...

  57. Scaling Behavior of Single LLM-Driven Multi-Agent Systems

    cs.MA 2026-05 unverdicted novelty 4.0

    LLM multi-agent systems exhibit diminishing returns with more agents due to coordination overhead rather than monotonic scaling.

  58. CogEvolution: A Human-like Generative Educational Agent to Simulate Student's Cognitive Evolution

    cs.AI 2026-04 unverdicted novelty 4.0

    CogEvolution combines ICAP cognitive taxonomy, IRT memory retrieval, and evolutionary algorithms into a generative agent that simulates dynamic student cognitive evolution and outperforms baselines in fidelity and lea...

  59. Red Skills or Blue Skills? A Dive Into Skills Published on ClawHub

    cs.CL 2026-03 unverdicted novelty 4.0

    Analysis of ClawHub shows language-based functional divides in agent skills, with over 30% flagged suspicious and submission-time documentation enabling 73% accurate risk prediction.

  60. Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward

    cs.MA 2026-02 unverdicted novelty 4.0

    The paper surveys agent skills for LLMs across architecture, acquisition, deployment, and security, proposing a four-tier Skill Trust and Lifecycle Governance Framework to address vulnerabilities in community skills.

Reference graph

Works this paper leans on

300 extracted references · 300 canonical work pages · cited by 61 Pith papers · 28 internal anchors

  1. [1]

    The rise and potential of large language model based agents: A survey,

    Z. Xi, W. Chen, X. Guo, W. He, Y. Ding, B. Hong, M. Zhang, J. Wang, S. Jin, E. Zhou et al. , “The rise and potential of large language model based agents: A survey,” Science China Information Sciences, vol. 68, no. 2, p. 121101, 2025

    work page 2025

  2. [2]

    Intelligent agents: Theory and practice,

    M. Wooldridge and N. R. Jennings, “Intelligent agents: Theory and practice,” The knowledge engineering review, vol. 10, no. 2, pp. 115–152, 1995

    work page 1995

  3. [3]

    Large language models as reliable knowledge bases?

    D. Zheng, M. Lapata, and J. Z. Pan, “Large language models as reliable knowledge bases?” arXiv preprint arXiv:2407.13578, 2024

    work page arXiv 2024

  4. [4]

    Lotfi, M

    S. Lotfi, M. Finzi, Y. Kuang, T. G. Rudner, M. Goldblum, and A. G. Wilson, “Non-vacuous generalization bounds for large language models,” arXiv preprint arXiv:2312.17173, 2023

    work page arXiv 2023

  5. [5]

    From multimodal llm to human-level ai: Modality, instruction, reasoning, efficiency and beyond,

    H. Fei, Y. Yao, Z. Zhang, F. Liu, A. Zhang, and T.-S. Chua, “From multimodal llm to human-level ai: Modality, instruction, reasoning, efficiency and beyond,” in COLING, 2024, pp. 1–8

    work page 2024

  6. [6]

    Towards Reasoning in Large Language Models: A Survey

    J. Huang and K. C.-C. Chang, “Towards reasoning in large language models: A survey,” arXiv preprint arXiv:2212.10403, 2022

    work page internal anchor Pith review Pith/arXiv arXiv 2022

  7. [7]

    Tool-lmm: A large multi-modal model for tool agent learning,

    C. Wang, W. Luo, Q. Chen, H. Mai, J. Guo, S. Dong, Z. Li, L. Ma, S. Gao et al., “Tool-lmm: A large multi-modal model for tool agent learning,” arXiv e-prints, pp. arXiv–2401, 2024

    work page 2024

  8. [8]

    A Survey on the Memory Mechanism of Large Language Model based Agents

    Z. Zhang, X. Bo, C. Ma, R. Li, X. Chen, Q. Dai, J. Zhu, Z. Dong, and J.-R. Wen, “A survey on the memory mechanism of large language model based agents,” arXiv preprint arXiv:2404.13501 , 2024

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  9. [9]

    arXiv preprint arXiv:2309.14365 , year=

    P . Zhao, Z. Jin, and N. Cheng, “An in-depth survey of large language model-based artificial intelligence agents,” arXiv preprint arXiv:2309.14365, 2023

    work page arXiv 2023

  10. [10]

    Cognitive architectures for language agents,

    T. Sumers, S. Yao, K. Narasimhan, and T. Griffiths, “Cognitive architectures for language agents,” TMLR, 2023

    work page 2023

  11. [11]

    A Survey on Large Language Model-Based Game Agents

    S. Hu, T. Huang, F. Ilhan, S. Tekin, G. Liu, R. Kompella, and L. Liu, “A survey on large language model-based game agents,” arXiv preprint arXiv:2404.02039, 2024

    work page internal anchor Pith review arXiv 2024

  12. [12]

    A survey on game playing agents and large models: Methods, applications, and challenges,

    X. Xu, Y. Wang, C. Xu, Z. Ding, J. Jiang, Z. Ding, and B. F. Karlsson, “A survey on game playing agents and large models: Methods, applications, and challenges,” arXiv preprint arXiv:2403.10249 , 2024

    work page arXiv 2024

  13. [13]

    Unleashing the power of edge-cloud generative ai in mobile networks: A survey of aigc services,

    M. Xu, H. Du, D. Niyato, J. Kang, Z. Xiong, S. Mao, Z. Han, A. Jamalipour, D. I. Kim, X. Shen et al., “Unleashing the power of edge-cloud generative ai in mobile networks: A survey of aigc services,” IEEE Communications Surveys & Tutorials, vol. 26, no. 2, pp. 1127–1170, 2024

    work page 2024

  14. [14]

    Mobile edge intelligence for large language models: A contemporary survey,

    G. Qu, Q. Chen, W. Wei, Z. Lin, X. Chen, and K. Huang, “Mobile edge intelligence for large language models: A contemporary survey,” IEEE Communications Surveys & Tutorials, 2025

    work page 2025

  15. [15]

    Agent AI: Surveying the Horizons of Multimodal Interaction

    Z. Durante, Q. Huang, N. Wake, R. Gong, J. S. Park, B. Sarkar, R. Taori, Y. Noda, D. Terzopoulos, Y. Choi et al. , “Agent ai: Surveying the horizons of multimodal interaction,” arXiv preprint arXiv:2401.03568, 2024

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  16. [16]

    Luan and Jiawen Kang and Dusit Niyato , year=

    Y. Wang, Y. Pan, Q. Zhao, Y. Deng, Z. Su, L. Du, and T. H. Luan, “Large model agents: State-of-the-art, cooperation paradigms, security and privacy, and future trends,” arXiv preprint arXiv:2409.14457, 2024

    work page arXiv 2024

  17. [17]

    A survey on large language model based autonomous agents,

    L. Wang, C. Ma, X. Feng, Z. Zhang, H. Yang, J. Zhang, Z. Chen, J. Tang, X. Chen, Y. Lin et al., “A survey on large language model based autonomous agents,” Frontiers of Computer Science, vol. 18, no. 6, p. 186345, 2024

    work page 2024

  18. [18]

    A survey on llm-based multi-agent systems: workflow, infrastructure, and challenges,

    X. Li, S. Wang, S. Zeng, Y. Wu, and Y. Yang, “A survey on llm-based multi-agent systems: workflow, infrastructure, and challenges,” Vicinagearth, vol. 1, no. 1, p. 9, 2024

    work page 2024

  19. [19]

    A review of prominent paradigms for llm-based agents: Tool use (including rag), planning, and feedback learning,

    X. Li, “A review of prominent paradigms for llm-based agents: Tool use (including rag), planning, and feedback learning,” arXiv preprint arXiv:2406.05804, 2024

    work page arXiv 2024

  20. [20]

    arXiv preprint arXiv:2503.13415 , year=

    W. Jin, H. Du, B. Zhao, X. Tian, B. Shi, and G. Yang, “A com- prehensive survey on multi-agent cooperative decision-making: Scenarios, approaches, challenges and perspectives,”arXiv preprint arXiv:2503.13415, 2025

    work page arXiv 2025

  21. [21]

    A Survey on Vision-Language-Action Models for Embodied AI

    Y. Ma, Z. Song, Y. Zhuang, J. Hao, and I. King, “A survey on vision-language-action models for embodied ai,” arXiv preprint arXiv:2405.14093, 2024

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  22. [22]

    Large Language Model based Multi-Agents: A Survey of Progress and Challenges

    T. Guo, X. Chen, Y. Wang, R. Chang, S. Pei, N. V . Chawla, O. Wiest, and X. Zhang, “Large language model based multi- agents: A survey of progress and challenges,” arXiv preprint arXiv:2402.01680, 2024

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  23. [23]

    The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey

    T. Masterman, S. Besen, M. Sawtell, and A. Chao, “The landscape of emerging ai agent architectures for reasoning, planning, and tool calling: A survey,” arXiv preprint arXiv:2404.11584, 2024. 20

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  24. [24]

    arXiv preprint arXiv:2401.03428

    Y. Cheng, C. Zhang, Z. Zhang, X. Meng, S. Hong, W. Li, Z. Wang, Z. Wang, F. Yin, J. Zhao et al., “Exploring large language model based intelligent agents: Definitions, methods, and prospects,” arXiv preprint arXiv:2401.03428, 2024

    work page arXiv 2024

  25. [25]

    Camel: Communicative agents for

    G. Li, H. A. A. K. Hammoud, H. Itani, D. Khizbullin, and B. Ghanem, “Camel: Communicative agents for ”mind” explo- ration of large language model society,” in NeurIPS, 2023

    work page 2023

  26. [26]

    Autogen: Enabling next-gen llm applications via multi- agent conversation,

    Q. Wu, G. Bansal, J. Zhang, Y. Wu, B. Li, E. Zhu, L. Jiang, X. Zhang, S. Zhang, J. Liu, A. H. Awadallah, R. W. White, D. Burger, and C. Wang, “Autogen: Enabling next-gen llm applications via multi- agent conversation,” 2023

    work page 2023

  27. [27]

    Metagpt: Meta programming for a multi-agent collaborative framework,

    S. Hong, X. Zheng, J. Chen, Y. Cheng, J. Wang, C. Zhang, Z. Wang, S. K. S. Yau, Z. Lin, L. Zhou et al., “Metagpt: Meta programming for a multi-agent collaborative framework,” in ICLR, 2024

    work page 2024

  28. [28]

    Chatdev: Communicative agents for software development,

    C. Qian, W. Liu, H. Liu, N. Chen, Y. Dang, J. Li, C. Yang, W. Chen, Y. Su, X. Conget al., “Chatdev: Communicative agents for software development,” in ACL, 2024, pp. 15 174–15 186

    work page 2024

  29. [29]

    AFlow: Automating agentic workflow generation,

    J. Zhang, J. Xiang, Z. Yu, F. Teng, X.-H. Chen, J. Chen, M. Zhuge, X. Cheng, S. Hong, J. Wang, B. Liu, Y. Luo, and C. Wu, “AFlow: Automating agentic workflow generation,” in ICLR, 2025

    work page 2025

  30. [30]

    Generative agents: Interactive simulacra of human behavior,

    J. S. Park, J. O’Brien, C. J. Cai, M. R. Morris, P . Liang, and M. S. Bernstein, “Generative agents: Interactive simulacra of human behavior,” in UIST, 2023, pp. 1–22

    work page 2023

  31. [31]

    User behavior simulation with large language model-based agents,

    L. Wang, J. Zhang, H. Yang, Z.-Y. Chen, J. Tang, Z. Zhang, X. Chen, Y. Lin, H. Sun, R. Song et al., “User behavior simulation with large language model-based agents,” ACM Transactions on Information Systems, vol. 43, no. 2, pp. 1–37, 2025

    work page 2025

  32. [32]

    Dspy: Compiling declarative language model calls into self-improving pipelines,

    O. Khattab, A. Singhvi, P . Maheshwari, Z. Zhang, K. Santhanam, S. Vardhamanan, S. Haq, A. Sharma, T. T. Joshi, H. Moazam, H. Miller, M. Zaharia, and C. Potts, “Dspy: Compiling declarative language model calls into self-improving pipelines,” in ICLR, 2024

    work page 2024

  33. [33]

    React: Synergizing reasoning and acting in language models,

    S. Yao, J. Zhao, D. Yu, N. Du, I. Shafran, K. Narasimhan, and Y. Cao, “React: Synergizing reasoning and acting in language models,” in ICLR, 2023

    work page 2023

  34. [34]

    Graph of thoughts: Solving elaborate problems with large language models,

    M. Besta, N. Blach, A. Kubicek, R. Gerstenberger, M. Podstawski, L. Gianinazzi, J. Gajda, T. Lehmann, H. Niewiadomski, P . Nyczyk et al., “Graph of thoughts: Solving elaborate problems with large language models,” in AAAI, vol. 38, no. 16, 2024, pp. 17 682–17 690

    work page 2024

  35. [35]

    Voyager: An open-ended embodied agent with large language models,

    G. Wang, Y. Xie, Y. Jiang, A. Mandlekar, C. Xiao, Y. Zhu, L. Fan, and A. Anandkumar, “Voyager: An open-ended embodied agent with large language models,” TMLR, 2023

    work page 2023

  36. [36]

    Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory

    X. Zhu, Y. Chen, H. Tian, C. Tao, W. Su, C. Yang, G. Huang, B. Li, L. Lu, X. Wang et al., “Ghost in the minecraft: Generally capable agents for open-world environments via large language models with text-based knowledge and memory,” arXiv preprint arXiv:2305.17144, 2023

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  37. [37]

    Expel: Llm agents are experiential learners,

    A. Zhao, D. Huang, Q. Xu, M. Lin, Y.-J. Liu, and G. Huang, “Expel: Llm agents are experiential learners,” in AAAI, 2024, pp. 19 632– 19 642

    work page 2024

  38. [38]

    Reflexion: Language agents with verbal reinforcement learning,

    N. Shinn, F. Cassano, A. Gopinath, K. Narasimhan, and S. Yao, “Reflexion: Language agents with verbal reinforcement learning,” NeurIPS, vol. 36, pp. 8634–8652, 2023

    work page 2023

  39. [39]

    Tptu: Task planning and tool usage of large language model-based ai agents,

    J. Ruan, Y. Chen, B. Zhang, Z. Xu, T. Bao, H. Mao, Z. Li, X. Zeng, R. Zhao et al. , “Tptu: Task planning and tool usage of large language model-based ai agents,” in NeurIPS, 2023

    work page 2023

  40. [40]

    Liu, Yiheng Xu, Hongjin Su, Dongchan Shin, Caiming Xiong, and Tao Yu

    T. Xie, F. Zhou, Z. Cheng, P . Shi, L. Weng, Y. Liu, T. J. Hua, J. Zhao, Q. Liu, C. Liu et al., “Openagents: An open platform for language agents in the wild,” arXiv preprint arXiv:2310.10634, 2023

    work page arXiv 2023

  41. [41]

    Lego-prover: Neural theorem proving with growing libraries,

    H. Wang, H. Xin, C. Zheng, Z. Liu, Q. Cao, Y. Huang, J. Xiong, H. Shi, E. Xie, J. Yin et al., “Lego-prover: Neural theorem proving with growing libraries,” in ICLR, 2024

    work page 2024

  42. [42]

    Memgpt: Towards llms as operating systems,

    C. Packer, V . Fang, S. G. Patil, K. Lin, S. Wooders, and J. E. Gonzalez, “Memgpt: Towards llms as operating systems,” CoRR, 2023

    work page 2023

  43. [43]

    Retrieval- augmented generation for knowledge-intensive nlp tasks,

    P . Lewis, E. Perez, A. Piktus, F. Petroni, V . Karpukhin, N. Goyal, H. K ¨uttler, M. Lewis, W.-t. Yih, T. Rockt ¨aschel et al., “Retrieval- augmented generation for knowledge-intensive nlp tasks,” NeurIPS, vol. 33, pp. 9459–9474, 2020

    work page 2020

  44. [44]

    From Local to Global: A Graph RAG Approach to Query-Focused Summarization

    D. Edge, H. Trinh, N. Cheng, J. Bradley, A. Chao, A. Mody, S. Truitt, D. Metropolitansky, R. O. Ness, and J. Larson, “From local to global: A graph rag approach to query-focused summarization,” arXiv preprint arXiv:2404.16130, 2024

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  45. [45]

    Chain of agents: Large language models collaborating on long-context tasks,

    Y. Zhang, R. Sun, Y. Chen, T. Pfister, R. Zhang, and S. Arik, “Chain of agents: Large language models collaborating on long-context tasks,” Advances in Neural Information Processing Systems, vol. 37, pp. 132 208–132 237, 2024

    work page 2024

  46. [46]

    Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions

    H. Trivedi, N. Balasubramanian, T. Khot, and A. Sabharwal, “Inter- leaving retrieval with chain-of-thought reasoning for knowledge- intensive multi-step questions,” arXiv preprint arXiv:2212.10509, 2022

    work page internal anchor Pith review Pith/arXiv arXiv 2022

  47. [47]

    Llatrieval: Llm- verified retrieval for verifiable generation,

    X. Li, C. Zhu, L. Li, Z. Yin, T. Sun, and X. Qiu, “Llatrieval: Llm- verified retrieval for verifiable generation,” in NAACL, 2024, pp. 5453–5471

    work page 2024

  48. [48]

    Graph-augmented reasoning: Evolving step-by-step knowledge graph retrieval for llm reasoning,

    W. Wu, Y. Jing, Y. Wang, W. Hu, and D. Tao, “Graph-augmented reasoning: Evolving step-by-step knowledge graph retrieval for llm reasoning,” 2025

    work page 2025

  49. [49]

    Deeprag: Thinking to retrieval step by step for large language models

    X. Guan, J. Zeng, F. Meng, C. Xin, Y. Lu, H. Lin, X. Han, L. Sun, and J. Zhou, “Deeprag: Thinking to retrieval step by step for large language models,” arXiv preprint arXiv:2502.01142, 2025

    work page arXiv 2025

  50. [50]

    Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models

    L. Wang, W. Xu, Y. Lan, Z. Hu, Y. Lan, R. K.-W. Lee, and E.- P . Lim, “Plan-and-solve prompting: Improving zero-shot chain- of-thought reasoning by large language models,” arXiv preprint arXiv:2305.04091, 2023

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  51. [51]

    Distributed problem solving and planning,

    E. H. Durfee, “Distributed problem solving and planning,” in ECCAI Advanced Course on Artificial Intelligence. Springer, 2001, pp. 118–149

    work page 2001

  52. [52]

    Chain-of-discussion: A multi- model framework for complex evidence-based question answer- ing,

    M. Tao, D. Zhao, and Y. Feng, “Chain-of-discussion: A multi- model framework for complex evidence-based question answer- ing,” arXiv preprint arXiv:2402.16313, 2024

    work page arXiv 2024

  53. [53]

    Tree-planner: Efficient close- loop task planning with large language models,

    M. Hu, Y. Mu, X. Yu, M. Ding, S. Wu, W. Shao, Q. Chen, B. Wang, Y. Qiao, and P . Luo, “Tree-planner: Efficient close- loop task planning with large language models,” arXiv preprint arXiv:2310.08582, 2023

    work page arXiv 2023

  54. [54]

    Reactree: Hierarchical task planning with dynamic tree expansion using llm agent nodes,

    J.-W. Choi, H. Kim, H. Ong, Y. Yoon, M. Jang, J. Kim et al. , “Reactree: Hierarchical task planning with dynamic tree expansion using llm agent nodes,” 2025

    work page 2025

  55. [55]

    Large language model guided tree-of-thought,

    J. Long, “Large language model guided tree-of-thought,” arXiv preprint arXiv:2305.08291, 2023

    work page arXiv 2023

  56. [56]

    Rest- mcts*: Llm self-training via process reward guided tree search,

    D. Zhang, S. Zhoubian, Z. Hu, Y. Yue, Y. Dong, and J. Tang, “Rest- mcts*: Llm self-training via process reward guided tree search,” NeurIPS, vol. 37, pp. 64 735–64 772, 2024

    work page 2024

  57. [57]

    LLM- MARS: Large Language Model for Behavior Tree Generation and NLP-enhanced Dia- logue in Multi-Agent Robot Systems

    A. Lykov, M. Dronova, N. Naglov, M. Litvinov, S. Satsevich, A. Bazhenov, V . Berman, A. Shcherbak, and D. Tsetserukou, “Llm- mars: Large language model for behavior tree generation and nlp- enhanced dialogue in multi-agent robot systems,” arXiv preprint arXiv:2312.09348, 2023

    work page arXiv 2023

  58. [58]

    Llm as bt- planner: Leveraging llms for behavior tree generation in robot task planning,

    J. Ao, F. Wu, Y. Wu, A. Swikir, and S. Haddadin, “Llm as bt- planner: Leveraging llms for behavior tree generation in robot task planning,” arXiv preprint arXiv:2409.10444, 2024

    work page arXiv 2024

  59. [59]

    Concepta- gent: Llm-driven precondition grounding and tree search for ro- bust task planning and execution,

    C. Rivera, G. Byrd, W. Paul, T. Feldman, M. Booker, E. Holmes, D. Handelman, B. Kemp, A. Badger, A. Schmidt et al., “Concepta- gent: Llm-driven precondition grounding and tree search for ro- bust task planning and execution,” arXiv preprint arXiv:2410.06108, 2024

    work page arXiv 2024

  60. [60]

    Grounding llms for robot task planning using closed-loop state feedback.arXiv preprint arXiv:2402.08546, 2024

    V . Bhat, A. U. Kaypak, P . Krishnamurthy, R. Karri, and F. Khorrami, “Grounding llms for robot task planning using closed-loop state feedback,” arXiv preprint arXiv:2402.08546, 2024

    work page arXiv 2024

  61. [61]

    Traineragent: Customizable and efficient model training through llm-powered multi-agent system,

    H. Li, H. Jiang, T. Zhang, Z. Yu, A. Yin, H. Cheng, S. Fu, Y. Zhang, and W. He, “Traineragent: Customizable and efficient model training through llm-powered multi-agent system,” arXiv preprint arXiv:2311.06622, 2023

    work page arXiv 2023

  62. [62]

    Dynamic self-consistency: Leveraging reasoning paths for efficient llm sampling,

    G. Wan, Y. Wu, J. Chen, and S. Li, “Dynamic self-consistency: Leveraging reasoning paths for efficient llm sampling,” arXiv preprint arXiv:2408.17017, 2024

    work page arXiv 2024

  63. [63]

    Llm-based cooperative agents using information relevance and plan validation,

    S. Seo, J. Lee, S. Noh, and H. Kang, “Llm-based cooperative agents using information relevance and plan validation,” arXiv preprint arXiv:2405.16751, 2024

    work page arXiv 2024

  64. [64]

    Adaplan- ner: Adaptive planning from feedback with language models,

    H. Sun, Y. Zhuang, L. Kong, B. Dai, and C. Zhang, “Adaplan- ner: Adaptive planning from feedback with language models,” NeurIPS, vol. 36, pp. 58 202–58 245, 2023

    work page 2023

  65. [65]

    Adaptive iterative feedback prompting for obstacle-aware path planning via llms,

    M. Jafaripour, S. Golestan, S. Miwa, Y. Mitsuka, and O. Zaiane, “Adaptive iterative feedback prompting for obstacle-aware path planning via llms,” in AAAI Workshop, 2025

    work page 2025

  66. [66]

    Making language models better tool learners with execution feedback,

    S. Qiao, H. Gui, C. Lv, Q. Jia, H. Chen, and N. Zhang, “Making language models better tool learners with execution feedback,” arXiv preprint arXiv:2305.13068, 2023

    work page arXiv 2023

  67. [67]

    Gpt4tools: Teaching large language model to use tools via self- instruction,

    R. Yang, L. Song, Y. Li, S. Zhao, Y. Ge, X. Li, and Y. Shan, “Gpt4tools: Teaching large language model to use tools via self- instruction,” NeurIPS, vol. 36, pp. 71 995–72 007, 2023

    work page 2023

  68. [68]

    Easytool: Enhancing llm-based agents with concise tool instruction,

    S. Yuan, K. Song, J. Chen, X. Tan, Y. Shen, R. Kan, D. Li, and D. Yang, “Easytool: Enhancing llm-based agents with concise tool instruction,” arXiv preprint arXiv:2401.06201, 2024. 21

    work page arXiv 2024

  69. [69]

    Avatar: Optimizing llm agents for tool usage via contrastive reasoning,

    S. Wu, S. Zhao, Q. Huang, K. Huang, M. Yasunaga, K. Cao, V . Ioannidis, K. Subbian, J. Leskovec, and J. Y. Zou, “Avatar: Optimizing llm agents for tool usage via contrastive reasoning,” NeurIPS, vol. 37, pp. 25 981–26 010, 2025

    work page 2025

  70. [70]

    Drivlme: Enhancing llm-based autonomous driving agents with embodied and social experiences,

    Y. Huang, J. Sansom, Z. Ma, F. Gervits, and J. Chai, “Drivlme: Enhancing llm-based autonomous driving agents with embodied and social experiences,” in IROS. IEEE, 2024, pp. 3153–3160

    work page 2024

  71. [71]

    arXiv preprint arXiv:2405.14314 , year=

    Y. Zhang, S. Yang, C. Bai, F. Wu, X. Li, Z. Wang, and X. Li, “Towards efficient llm grounding for embodied multi-agent collab- oration,” arXiv preprint arXiv:2405.14314, 2024

    work page arXiv 2024

  72. [72]

    Improving embodied llm agents capabilities through collaboration,

    B. Colle, “Improving embodied llm agents capabilities through collaboration,” 2024

    work page 2024

  73. [73]

    Autonomous chemical research with large language models,

    D. A. Boiko, R. MacKnight, B. Kline, and G. Gomes, “Autonomous chemical research with large language models,” Nature, vol. 624, no. 7992, pp. 570–578, 2023

    work page 2023

  74. [74]

    Llmlingua: Compressing prompts for accelerated inference of large language models,

    H. Jiang, Q. Wu, C.-Y. Lin, Y. Yang, and L. Qiu, “Llmlingua: Compressing prompts for accelerated inference of large language models,” in EMNLP, 2023, pp. 13 358–13 376

    work page 2023

  75. [75]

    Autoact: Automatic agent learning from scratch for qa via self-planning,

    S. Qiao, N. Zhang, R. Fang, Y. Luo, W. Zhou, Y. E. Jiang, C. Lv, and H. Chen, “Autoact: Automatic agent learning from scratch for qa via self-planning,” arXiv preprint arXiv:2401.05268, 2024

    work page arXiv 2024

  76. [76]

    arXiv preprint arXiv:2401.12954 , year=

    M. Suzgun and A. T. Kalai, “Meta-prompting: Enhancing lan- guage models with task-agnostic scaffolding,” arXiv preprint arXiv:2401.12954, 2024

    work page arXiv 2024

  77. [77]

    arXiv preprint arXiv:2402.06782 , year=

    A. Khan, J. Hughes, D. Valentine, L. Ruis, K. Sachan, A. Rad- hakrishnan, E. Grefenstette, S. R. Bowman, T. Rockt ¨aschel, and E. Perez, “Debating with more persuasive llms leads to more truthful answers,” arXiv preprint arXiv:2402.06782, 2024

    work page arXiv 2024

  78. [78]

    arXiv preprint arXiv:2311.10537 , year=

    X. Tang, A. Zou, Z. Zhang, Z. Li, Y. Zhao, X. Zhang, A. Cohan, and M. Gerstein, “Medagents: Large language models as collaborators for zero-shot medical reasoning,” arXiv preprint arXiv:2311.10537, 2023

    work page arXiv 2023

  79. [79]

    arXiv preprint arXiv:2309.13007 , year=

    J. C.-Y. Chen, S. Saha, and M. Bansal, “Reconcile: Round-table conference improves reasoning via consensus among diverse llms,” arXiv preprint arXiv:2309.13007, 2023

    work page arXiv 2023

  80. [80]

    Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate

    T. Liang, Z. He, W. Jiao, X. Wang, Y. Wang, R. Wang, Y. Yang, S. Shi, and Z. Tu, “Encouraging divergent thinking in large language models through multi-agent debate,” arXiv preprint arXiv:2305.19118, 2023

    work page internal anchor Pith review Pith/arXiv arXiv 2023

Showing first 80 references.