pith. sign in

arxiv: 2601.02553 · v3 · pith:6W2BJYNYnew · submitted 2026-01-05 · 💻 cs.AI

SimpleMem: Efficient Lifelong Memory for LLM Agents

Jiaqi Liu , Yaofeng Su , Peng Xia , Siwei Han , Zeyu Zheng , Cihang Xie , Mingyu Ding , Huaxiu Yao This is my paper

Pith reviewed 2026-05-22 08:05 UTC · model grok-4.3

classification 💻 cs.AI
keywords LLM agentsmemory compressionsemantic synthesisintent-aware retrievallifelong memorytoken efficiencycontext management
0
0 comments X

The pith

SimpleMem compresses unstructured LLM agent interactions into compact multi-view memory units via a three-stage semantic pipeline, preserving critical details while cutting token costs.

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

The paper presents SimpleMem as a memory framework that replaces either full history retention or expensive iterative filtering with semantic lossless compression. Its pipeline first distills raw interactions into structured indexed units, then synthesizes related context on the fly to remove redundancy, and finally plans retrieval by inferring user intent to assemble only the needed context. If this holds, agents could sustain accurate performance across much longer sessions without the quadratic token blowup that currently limits complex environments. A sympathetic reader cares because lifelong memory is a bottleneck for any agent meant to operate over days or weeks rather than single turns.

Core claim

By distilling interactions through Semantic Structured Compression into compact multi-view indexed units, followed by intra-session Online Semantic Synthesis that merges related context into unified abstracts and Intent-Aware Retrieval Planning that infers search intent to set retrieval scope, the method produces memory representations that maintain task-critical information while dramatically lowering inference-time token use.

What carries the argument

The three-stage pipeline (Semantic Structured Compression into multi-view indexed units, Online Semantic Synthesis for intra-session abstraction, and Intent-Aware Retrieval Planning) that turns raw interaction histories into high-density, query-adaptive memory.

If this is right

  • Agents achieve an average 26.4% F1 gain on LoCoMo while consuming up to 30 times fewer tokens at inference time.
  • Memory size stays bounded even as interaction length grows, because redundancy is removed at synthesis time rather than stored.
  • Retrieval becomes more precise because intent inference dynamically limits scope instead of pulling broad context windows.
  • The same pipeline can be applied across sessions, turning episodic memory into a growing but compact lifelong store.

Where Pith is reading between the lines

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

  • The approach could be combined with external knowledge bases by treating retrieved documents as additional input to the synthesis stage.
  • If the compression remains lossless at scale, similar pipelines might reduce context length requirements for other long-horizon reasoning tasks such as multi-turn planning or code maintenance.
  • Real-world deployment would still need safeguards against drift if the intent inference model itself hallucinates the wrong retrieval scope.

Load-bearing premise

The compression steps preserve every task-critical detail from the original unstructured interactions without any information loss that would affect downstream agent decisions.

What would settle it

An experiment that replays the same long interaction trace through SimpleMem and a full-history baseline, then measures whether the agent produces identical answers on questions that depend on a single early detail omitted from the compressed memory.

read the original abstract

To support long-term interaction in complex environments, LLM agents require memory systems that manage historical experiences. Existing approaches either retain full interaction histories via passive context extension, leading to substantial redundancy, or rely on iterative reasoning to filter noise, incurring high token costs. To address this challenge, we introduce SimpleMem, an efficient memory framework based on semantic lossless compression. We propose a three-stage pipeline designed to maximize information density and token utilization: (1) Semantic Structured Compression, which distills unstructured interactions into compact, multi-view indexed memory units; (2) Online Semantic Synthesis, an intra-session process that instantly integrates related context into unified abstract representations to eliminate redundancy; and (3) Intent-Aware Retrieval Planning, which infers search intent to dynamically determine retrieval scope and construct precise context efficiently. Experiments on benchmark datasets show that our method consistently outperforms baseline approaches in accuracy, retrieval efficiency, and inference cost, achieving an average F1 improvement of 26.4% in LoCoMo while reducing inference-time token consumption by up to 30-fold, demonstrating a superior balance between performance and efficiency. Code is available at https://github.com/aiming-lab/SimpleMem.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The paper introduces SimpleMem, a memory framework for LLM agents that employs semantic lossless compression via a three-stage pipeline: (1) Semantic Structured Compression to distill interactions into compact multi-view indexed units, (2) Online Semantic Synthesis for intra-session redundancy elimination through unified abstract representations, and (3) Intent-Aware Retrieval Planning to dynamically scope retrieval based on inferred intent. Experiments on benchmark datasets are reported to show consistent outperformance over baselines, with an average 26.4% F1 gain on LoCoMo and up to 30-fold reduction in inference-time token consumption.

Significance. If the experimental claims hold under rigorous validation, the work could meaningfully advance efficient lifelong memory for LLM agents by balancing information density with reduced token costs during inference. The public code release at the cited GitHub repository supports reproducibility and is a clear strength.

major comments (2)
  1. [Experiments / Results] The central performance claims (26.4% F1 improvement on LoCoMo and 30-fold token reduction) rest on the three-stage pipeline producing memory units that preserve all task-critical details, yet no ablation, information-theoretic metric, or explicit verification of semantic lossless compression is supplied in the experimental section to rule out systematic omission of entities or relations.
  2. [Experiments] The abstract and results report specific quantitative gains without describing the baseline implementations, dataset characteristics, number of runs, statistical tests, or error analysis; this leaves the robustness of the accuracy, efficiency, and cost comparisons difficult to evaluate.
minor comments (2)
  1. [Introduction] The term 'semantic lossless compression' is used repeatedly but never formally defined or contrasted with lossy alternatives; a brief operational definition would improve clarity.
  2. [Figures and Tables] Figure captions and table headers should explicitly state the evaluation metrics (e.g., F1, token count) and the exact baselines being compared.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback on our manuscript. We address each major comment below and outline the revisions we will make to strengthen the experimental validation and reporting.

read point-by-point responses

  1. Referee: [Experiments / Results] The central performance claims (26.4% F1 improvement on LoCoMo and 30-fold token reduction) rest on the three-stage pipeline producing memory units that preserve all task-critical details, yet no ablation, information-theoretic metric, or explicit verification of semantic lossless compression is supplied in the experimental section to rule out systematic omission of entities or relations.

    Authors: We agree that explicit verification of information preservation would strengthen the claims. The Semantic Structured Compression stage is designed to retain task-critical details by extracting and indexing entities, relations, and temporal attributes into multi-view structures, while Online Semantic Synthesis unifies redundant intra-session content without discarding unique facts. However, we acknowledge the absence of dedicated ablations or metrics in the current experimental section. In the revised manuscript, we will add an ablation study isolating each pipeline stage and report an information-retention metric based on entity and relation overlap (via automated extraction) between original interactions and compressed memory units. This will directly address concerns about potential systematic omissions. revision: yes

  2. Referee: [Experiments] The abstract and results report specific quantitative gains without describing the baseline implementations, dataset characteristics, number of runs, statistical tests, or error analysis; this leaves the robustness of the accuracy, efficiency, and cost comparisons difficult to evaluate.

    Authors: We concur that greater transparency on experimental setup is required. The current manuscript provides high-level comparisons but lacks granular details on implementation and statistical rigor. In the revision, we will expand the Experiments section with: (i) precise descriptions of baseline adaptations (including prompt templates and memory management logic for methods such as MemGPT and full-context baselines), (ii) dataset statistics (e.g., number of sessions, average turns per session, and domain coverage for LoCoMo and other benchmarks), (iii) results averaged over multiple runs with standard deviations, (iv) statistical significance testing (paired t-tests with p-values), and (v) a categorized error analysis highlighting cases of retrieval failure versus compression-induced loss. These additions will improve evaluability without altering the core claims. revision: yes

Circularity Check

0 steps flagged

No significant circularity identified

full rationale

The paper introduces SimpleMem as an empirical three-stage pipeline (Semantic Structured Compression, Online Semantic Synthesis, Intent-Aware Retrieval Planning) for lifelong memory in LLM agents and supports its claims through benchmark experiments reporting F1 gains and token reductions. No load-bearing mathematical derivations, equations, fitted parameters renamed as predictions, or self-citation chains appear in the provided text; the central claims rest on external experimental outcomes rather than any reduction of results to inputs by construction. The approach is therefore self-contained.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claims rest on the domain assumption that semantic compression of dialogues can be performed losslessly for downstream agent tasks; no free parameters or invented entities are visible in the abstract.

axioms (1)
  • domain assumption Semantic structured compression preserves all task-critical information from unstructured interactions
    Invoked in the description of the first pipeline stage as the basis for compact memory units.

pith-pipeline@v0.9.0 · 5753 in / 1147 out tokens · 44616 ms · 2026-05-22T08:05:48.249230+00:00 · methodology

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. MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare

    cs.AI 2026-05 conditional novelty 8.0

    MedMemoryBench supplies a 2,000-session synthetic medical trajectory dataset and an evaluate-while-constructing streaming protocol to expose memory saturation and reasoning failures in current agent architectures for ...

  2. MemTrace: Probing What Final Accuracy Misses in Long-Term Memory

    cs.AI 2026-06 unverdicted novelty 7.0

    MemTrace shows that evidence utilization, not retrieval, is the dominant failure mode in LLM long-term memory systems across tested configurations.

  3. Co-Evolving Skill Generation and Policy Optimization

    cs.CL 2026-06 unverdicted novelty 7.0

    Framework estimates context-dependent marginal utility of candidate skills via reward gaps in matched base vs. skill-augmented rollouts to filter skills and co-train policy as generator.

  4. Agent Memory: Characterization and System Implications of Stateful Long-Horizon Workloads

    cs.AI 2026-06 unverdicted novelty 7.0

    The paper delivers the first systems characterization of agent memory, with a four-axis taxonomy, phase-aware profiler, evaluation of ten systems on two benchmarks, and ten design recommendations.

  5. 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.

  6. Personal Visual Memory from Explicit and Implicit Evidence

    cs.CV 2026-05 unverdicted novelty 7.0

    VisualMem augments text memory with a visual module that resolves identity and durable user facts from images, outperforming prior systems on a new benchmark for explicit and implicit personal visual evidence.

  7. MemFail: Stress-Testing Failure Modes of LLM Memory Systems

    cs.AI 2026-05 unverdicted novelty 7.0

    MemFail introduces diagnostic datasets that isolate failure modes in LLM memory systems by testing summarization, storage, and retrieval operations separately.

  8. Memory-Induced Tool-Drift in LLM Agents

    cs.CR 2026-05 unverdicted novelty 7.0

    Biased long-term memories in LLM agents cause measurable deviations in tool parameters across 105 scenarios, seven models, and 608 real tools, persisting under standard memory architectures.

  9. MemGym: a Long-Horizon Memory Environment for LLM Agents

    cs.CL 2026-05 unverdicted novelty 7.0

    MemGym unifies agent gyms into a memory benchmark with isolated scoring across tool-use, research, coding, and computer-use regimes plus a lightweight reward model for tractable coding evaluation.

  10. ClawForge: Generating Executable Interactive Benchmarks for Command-Line Agents

    cs.AI 2026-05 unverdicted novelty 7.0

    ClawForge is a generator framework that creates reproducible executable benchmarks for command-line agents under state conflict, with ClawForge-Bench showing frontier models reach at most 45.3% strict accuracy and tha...

  11. ClawForge: Generating Executable Interactive Benchmarks for Command-Line Agents

    cs.AI 2026-05 conditional novelty 7.0

    ClawForge supplies a generator that turns scenario templates into reproducible command-line tasks testing state conflict handling, where the strongest frontier model scores only 45.3 percent strict accuracy.

  12. EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents

    cs.LG 2026-05 unverdicted novelty 7.0

    EvolveMem enables autonomous self-evolution of LLM memory retrieval configurations via LLM diagnosis and safeguards, delivering 25.7% gains over strong baselines on LoCoMo and 18.9% on MemBench with positive cross-ben...

  13. RewardHarness: Self-Evolving Agentic Post-Training

    cs.AI 2026-05 unverdicted novelty 7.0

    RewardHarness self-evolves a tool-and-skill library from 100 preference examples to reach 47.4% accuracy on image-edit evaluation, beating GPT-5, and yields stronger RL-tuned models.

  14. Latent Preference Modeling for Cross-Session Personalized Tool Calling

    cs.CL 2026-04 unverdicted novelty 7.0

    Introduces MPT benchmark and PRefine method that models user preferences as evolving hypotheses to improve personalized tool calling accuracy with 1.24% of full-history token cost.

  15. SensorPersona: An LLM-Empowered System for Continual Persona Extraction from Longitudinal Mobile Sensor Streams

    cs.CL 2026-03 unverdicted novelty 7.0

    SensorPersona uses LLMs for hierarchical reasoning on longitudinal mobile sensor streams to continually extract stable personas, showing up to 31.4% higher recall and 85.7% win rate over baselines on a 20-user dataset.

  16. What Memory Do GUI Agents Really Need? From Passive Records to Active Task-Driving States

    cs.CV 2026-06 unverdicted novelty 6.0

    Introduces Active Task Driving Memory (ATMem) and STR-GRPO to move GUI agents from passive record storage to actively maintained task states, tested on a new mobile benchmark with progress and scope-aware metrics.

  17. Are We Ready For An Agent-Native Memory System?

    cs.CL 2026-06 unverdicted novelty 6.0

    A four-module framework is used to benchmark 12 agent memory systems, showing no architecture dominates and that workload alignment plus localized maintenance drive performance and cost.

  18. EvoEmbedding: Evolvable Representations for Long-Context Retrieval and Agentic Memory

    cs.CL 2026-06 unverdicted novelty 6.0

    EvoEmbedding generates evolvable embeddings via a latent memory updated during sequential processing, outperforming larger models on long-context retrieval and generalizing to 10x longer contexts in downstream tasks.

  19. MemRefine: LLM-Guided Compression for Long-Term Agent Memory

    cs.CL 2026-06 unverdicted novelty 6.0

    MemRefine uses LLM factual judgments to iteratively compress agent memory to target budgets while preserving downstream task performance better than rule-based baselines.

  20. MemPro: Agentic Memory Systems as Evolvable Programs

    cs.CL 2026-05 unverdicted novelty 6.0

    MemPro evolves the entire MCR pipeline as runnable programs via failure-guided refinement on a version tree and outperforms static baselines on LongMemEval, LoCoMo, HotpotQA, and NarrativeQA.

  21. Learning to Retrieve: Dual-Level Long-Term Memory for Text-to-SQL Agents

    cs.CL 2026-05 unverdicted novelty 6.0

    MERIT maintains episode-level and turn-level memories with RL-optimized retrieval and a process reward model, outperforming baselines on BIRD-Interact with positive transfer to Spider2-Snow.

  22. MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems

    cs.CL 2026-05 unverdicted novelty 6.0

    MemTrace turns LLM memory operations into executable evolution graphs for error tracing, builds a benchmark across systems like RAG and Mem0, and uses attribution to optimize prompts, improving task performance by up ...

  23. From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents

    cs.CL 2026-05 unverdicted novelty 6.0

    RoleMemo dataset and DualMem dual-memory framework let role-playing agents interpret facts through personas, with a 4B model beating larger zero-shot systems on fidelity.

  24. From Correctness to Preference: A Framework for Personalized Agentic Reinforcement Learning

    cs.CL 2026-05 unverdicted novelty 6.0

    Proposes PARPO for reward decoupling with user anchors and PSGM for preference-aligned skill memory in personalized agentic RL, reporting outperformance on ETAPP benchmarks.

  25. Self-Evolving Multi-Agent Systems via Decentralized Memory

    cs.MA 2026-05 unverdicted novelty 6.0

    DecentMem is a decentralized dual-pool memory framework for self-evolving multi-agent systems that provides O(log T) regret guarantees and yields up to 23.8% accuracy gains over centralized baselines.

  26. EvoIR-Agent: Self-Evolving Image Restoration Agentic System via Experience-Driven Learning

    cs.CV 2026-05 unverdicted novelty 6.0

    EvoIR-Agent formulates experience components into a hierarchical pool with a self-evolving update mechanism to improve performance and efficiency of training-free MLLM image restoration agents over prior paradigms.

  27. Auto-Dreamer: Learning Offline Memory Consolidation for Language Agents

    cs.CL 2026-05 unverdicted novelty 6.0

    Auto-Dreamer trains an offline memory consolidator via GRPO on agent performance to abstract cross-session patterns, outperforming baselines by 7 points on ScienceWorld with 12x smaller memory and generalizing to ALFW...

  28. MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agents

    cs.CV 2026-05 conditional novelty 6.0

    MementoGUI introduces a modular memory-control framework with working and episodic memory operators that improves long-horizon GUI agent performance over history-replay and text-only baselines.

  29. DimMem: Dimensional Structuring for Efficient Long-Term Agent Memory

    cs.CL 2026-05 unverdicted novelty 6.0

    DimMem introduces a dimensional memory framework that structures memories as typed atomic units to improve retrieval efficiency and accuracy for long-term LLM agent tasks.

  30. PRISM: Pareto-Efficient Retrieval over Intent-Aware Structured Memory for Long-Horizon Agents

    cs.CL 2026-05 unverdicted novelty 6.0

    PRISM is a new inference-time retrieval system that achieves higher accuracy than baselines on long-horizon agent tasks while using an order of magnitude less context by combining hierarchical graph search, intent-bas...

  31. PRISM: Pareto-Efficient Retrieval over Intent-Aware Structured Memory for Long-Horizon Agents

    cs.CL 2026-05 unverdicted novelty 6.0

    PRISM achieves higher accuracy than baselines on long-horizon agent tasks at an order-of-magnitude smaller context budget by combining hierarchical bundle search, query-sensitive costing, evidence compression, and ada...

  32. SkillGraph: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill Graphs

    cs.CL 2026-05 unverdicted novelty 6.0

    SkillGraph represents skills as nodes in an evolving directed graph with typed dependency edges and updates the graph from RL trajectories to boost compositional task performance.

  33. 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...

  34. SkillMaster: Toward Autonomous Skill Mastery in LLM Agents

    cs.AI 2026-05 unverdicted novelty 6.0

    SkillMaster is a training framework that lets LLM agents autonomously propose, update, and apply skills, yielding 8.8% and 9.3% higher success rates on ALFWorld and WebShop than prior methods.

  35. SkillMaster: Toward Autonomous Skill Mastery in LLM Agents

    cs.AI 2026-05 unverdicted novelty 6.0

    SkillMaster enables LLM agents to autonomously develop skills via trajectory review, counterfactual evaluation, and DualAdv-GRPO training, boosting success rates by 8.8% on ALFWorld and 9.3% on WebShop.

  36. Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning

    cs.AI 2026-05 unverdicted novelty 6.0

    Skill1 trains one policy to jointly evolve skill query generation, re-ranking, task solving, and distillation from a single task-success signal, with low-frequency trends crediting selection and high-frequency variati...

  37. MEMTIER: Tiered Memory Architecture and Retrieval Bottleneck Analysis for Long-Running Autonomous AI Agents

    cs.AI 2026-05 unverdicted novelty 6.0

    MEMTIER delivers 38% accuracy on the 500-question LongMemEval-S benchmark with a 7B model on 6GB GPU, a 33-point gain over full-context baselines, via structured episodic memory, five-signal retrieval, and semantic co...

  38. FileGram: Grounding Agent Personalization in File-System Behavioral Traces

    cs.CV 2026-04 unverdicted novelty 6.0

    FileGram grounds AI agent personalization in file-system behavioral traces via a data simulation engine, a diagnostic benchmark, and a bottom-up memory architecture.

  39. Cognis: Context-Aware Memory for Conversational AI Agents

    cs.CL 2026-03 unverdicted novelty 6.0

    Cognis is a unified memory system for LLM agents that combines BM25 keyword matching with vector search, context-aware ingestion for version tracking, and reranking to achieve state-of-the-art results on LoCoMo and Lo...

  40. HyMem: Hybrid Memory Architecture with Dynamic Retrieval Scheduling

    cs.AI 2026-02 unverdicted novelty 6.0

    HyMem introduces dual-granular memory storage with a lightweight summary module for fast responses and selective activation of a deep LLM module for complex queries, outperforming full-context baselines by 92.6% lower...

  41. What Memory Do GUI Agents Really Need? From Passive Records to Active Task-Driving States

    cs.CV 2026-06 unverdicted novelty 5.0

    Proposes ATMem as active task-driving state memory and STR-GRPO RL to improve GUI agent reliability on long-horizon mobile tasks over passive record storage.

  42. When Does Overlap Help? OSU-Mem and a Cell-Conditional Analysis of Trajectory Memory for LLM Agents

    cs.IR 2026-06 unverdicted novelty 5.0

    OSU-Mem shows overlapping memory helps retrieval when evidence shares tools or entities but hurts when steps are heterogeneous, with benefits on synthetic benchmarks vanishing on mixed real ones due to query mixing.

  43. Personalization Meets Safety:Mechanisms,Risks,and Mitigations in Personalized LLMs

    cs.AI 2026-06 unverdicted novelty 5.0

    A survey that maps safety risks in personalized LLMs, introduces a unified taxonomy, and highlights three structural inadequacies in existing research on user-invariant safety, isolated techniques, and short-term evaluations.

  44. ConMem: Structured Memory-Guided Adaptation in Training-Free Multi-Agent Systems

    cs.AI 2026-06 unverdicted novelty 5.0

    ConMem distills agent trajectories into structured memory cards organized in a relation-aware graph to enable training-free, relation-coordinated adaptation in LLM-based multi-agent systems.

  45. Exploring Cross-Scenario Generality of Agentic Memory Systems: Diagnostics and a Strong Baseline

    cs.AI 2026-06 unverdicted novelty 5.0

    An agentic harness letting the LLM self-manage flat text-file storage via tool calls outperforms eight prior memory systems on cross-scenario generality across QA, chat, trajectory, stress-test, and long-horizon tasks.

  46. SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training

    cs.AI 2026-06 unverdicted novelty 5.0

    SIRI trains LLM agents to discover, validate, and internalize reusable skills from their own rollouts without external generators or inference-time skill banks, yielding gains on ALFWorld and WebShop.

  47. Learning User-Aware Recall: Personalized Retrieval in Long-Term Conversational Memory

    cs.IR 2026-05 unverdicted novelty 5.0

    PPRO improves user-aware memory retrieval in conversational agents by using derived user profiles for ranking and training a query rewriter via Group Relative Policy Optimization, with reported gains on LoCoMo and Lon...

  48. Learning User-Aware Recall: Personalized Retrieval in Long-Term Conversational Memory

    cs.IR 2026-05 unverdicted novelty 5.0

    PPRO adds user-profile-guided ranking and retrieval-oriented query rewriting to memory-augmented LLMs, yielding gains on LoCoMo and LongMemEval-S over prior memory systems.

  49. Mitigating Provenance-Role Collapse in Long-Term Agents via Typed Memory Representation

    cs.CL 2026-05 unverdicted novelty 5.0

    MemIR is a typed memory representation for LLM agents that structures memory into atoms separating evidence, cues, and claims, leading to better performance on source tracking tasks in experiments on LoCoMo and BEAM-100K.

  50. EvoIR-Agent: Self-Evolving Image Restoration Agentic System via Experience-Driven Learning

    cs.CV 2026-05 unverdicted novelty 5.0

    EvoIR-Agent introduces a hierarchical experience pool and self-evolving mechanism to improve training-free image restoration agents, claiming significant metric leads and better performance-efficiency balance.

  51. DimMem: Dimensional Structuring for Efficient Long-Term Agent Memory

    cs.CL 2026-05 unverdicted novelty 5.0

    DimMem introduces typed dimensional memory units that improve accuracy to 81.43% and 78.20% on two long-term agent benchmarks while cutting token cost by 24% and enabling small models to match larger extractors.

  52. MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory

    cs.CV 2026-05 unverdicted novelty 5.0

    MemEye benchmark evaluates multimodal memory on visual granularity and evidence synthesis, finding that 13 methods across 4 VLMs struggle with fine details and temporal state changes.

  53. 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...

  54. Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning

    cs.AI 2026-05 unverdicted novelty 5.0

    Skill1 trains a single RL policy to co-evolve skill selection, utilization, and distillation in language model agents from one task-outcome reward, using low-frequency trends to credit selection and high-frequency var...

  55. Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning

    cs.AI 2026-05 unverdicted novelty 5.0

    Skill1 co-evolves skill selection, utilization, and distillation inside a single policy using only task-outcome reward, with low-frequency trends crediting selection and high-frequency variation crediting distillation...

  56. MEMTIER: Tiered Memory Architecture and Retrieval Bottleneck Analysis for Long-Running Autonomous AI Agents

    cs.AI 2026-05 unverdicted novelty 5.0

    MEMTIER is a tripartite memory system for autonomous agents that raises accuracy on the LongMemEval-S benchmark from 5% to 38% via episodic JSONL storage, five-signal retrieval, and PPO-adapted weights.

  57. Hierarchical Long-Term Semantic Memory for LinkedIn's Hiring Agent

    cs.IR 2026-04 unverdicted novelty 5.0

    HLTM structures textual data into a schema-aligned memory tree for scalable ingestion and low-latency retrieval in LinkedIn's Hiring Assistant, reporting over 5% higher answer correctness, over 10% higher retrieval F1...

  58. Scaling Teams or Scaling Time? Memory Enabled Lifelong Learning in LLM Multi-Agent Systems

    cs.MA 2026-03 unverdicted novelty 5.0

    LLMA-Mem improves long-horizon performance in LLM multi-agent systems over baselines while reducing cost and shows non-monotonic scaling where memory-enabled smaller teams can beat larger ones.

  59. MEMTIER: Tiered Memory Architecture and Retrieval Bottleneck Analysis for Long-Running Autonomous AI Agents

    cs.AI 2026-05 reject novelty 4.0

    MEMTIER reports 0.382 accuracy and 0.412 F1 on the 500-question LongMemEval-S benchmark, a 33pp gain over full-context baseline using tiered memory and retrieval components on 6GB GPU hardware.

  60. Hierarchical Long-Term Semantic Memory for LinkedIn's Hiring Agent

    cs.IR 2026-04 unverdicted novelty 4.0

    HLTM builds a hierarchical memory tree from longitudinal data to enable scalable, private, low-latency retrieval, delivering over 10% gains in answer correctness and retrieval F1 for LinkedIn's Hiring Assistant while ...

Reference graph

Works this paper leans on

12 extracted references · 12 canonical work pages · cited by 47 Pith papers

  1. [1]

    Agent0-vl: Exploring self-evolving agent for tool-integrated vision-language reasoning

    URL https://api.semanticscholar. org/CorpusID:278960153. Liskavetsky, A. et al. Compressor: Context-aware prompt compression for enhanced llm inference.arXiv preprint, 2025. Liu, J., Xiong, K., Xia, P., Zhou, Y ., Ji, H., Feng, L., Han, S., Ding, M., and Yao, H. Agent0-vl: Exploring self- evolving agent for tool-integrated vision-language reason- ing.arXi...

    work page arXiv 2025

  2. [2]

    arXiv preprint arXiv:2505.20286 , year=

    URL https://api.semanticscholar. org/CorpusID:263909014. Qiu, J., Qi, X., Zhang, T., Juan, X., Guo, J., Lu, Y ., Wang, Y ., Yao, Z., Ren, Q., Jiang, X., et al. Alita: Generalist agent enabling scalable agentic reasoning with minimal predefinition and maximal self-evolution.arXiv preprint arXiv:2505.20286, 2025. Rasmussen, P., Paliychuk, P., Beauvais, T., ...

    work page arXiv 2025

  3. [3]

    - Discard redundant confirmations unless they modify or finalize a decision

    Information Filtering: - Discard social filler, acknowledgements, and conversational routines that introduce no new factual or semantic information. - Discard redundant confirmations unless they modify or finalize a decision. - If no informative content is present, output an empty list

    work page

  4. [4]

    - Ensure each memory unit is interpretable without access to prior dialogue

    Context Normalization: - Resolve all pronouns and implicit references into explicit entity names. - Ensure each memory unit is interpretable without access to prior dialogue

    work page

  5. [5]

    tomorrow

    Temporal Normalization: - Convert relative temporal expressions (e.g., "tomorrow", "last week") into absolute ISO 8601 timestamps using the window start time

    work page

  6. [6]

    memory_units

    Memory Unit Extraction: - Decompose complex utterances into minimal, indivisible factual statements. INPUT DIALOGUE: {dialogue_window} OUTPUT FORMAT (JSON): { "memory_units": [ { "content": "Alice agreed to meet Bob at the Starbucks on 5th Avenue on 2025-11-20T14 :00:00.", "entities": ["Alice", "Bob", "Starbucks", "5th Avenue"], "topic": "Meeting Planning...

    work page 2025

  7. [7]

    LOW" if the query can be answered via direct fact lookup or a single memory unit. - Assign

    Query Complexity Estimation: - Assign "LOW" if the query can be answered via direct fact lookup or a single memory unit. - Assign "HIGH" if the query requires aggregation across multiple events, temporal comparison, or synthesis of patterns

    work page

  8. [8]

    complexity

    Retrieval Signals: - Lexical layer: extract exact keywords or entity names. - Temporal layer: infer absolute time ranges if relevant. - Semantic layer: rewrite the query into a declarative form suitable for semantic matching. OUTPUT FORMAT (JSON): { "complexity": "HIGH", "retrieval_rationale": "The query requires reasoning over multiple temporally separat...

    work page 2025

  9. [9]

    - Use detailed memory units to ground the response with specific facts

    Hierarchical Reasoning: - Use abstract representations to capture recurring patterns or general user preferences. - Use detailed memory units to ground the response with specific facts

    work page

  10. [10]

    - Optionally reference abstract patterns when relevant

    Conflict Handling: - If inconsistencies arise, prioritize the most recent memory unit. - Optionally reference abstract patterns when relevant

    work page

  11. [11]

    12 SimpleMem: Efficient Lifelong Memory for LLM Agents

    Temporal Consistency: - Ensure all statements respect the timestamps provided in memory. 12 SimpleMem: Efficient Lifelong Memory for LLM Agents

    work page

  12. [12]

    I do not have enough information in my memory

    Faithfulness: - Base the answer strictly on the retrieved memory. - If required information is missing, respond with: "I do not have enough information in my memory." FINAL ANSWER: A.4. LongMemEval Evaluation Prompt For the LongMemEval benchmark, we employed gpt-4.1-mini as the judge to evaluate the correctness of the agent’s responses. The prompt strictl...

    work page 2024