KernelPro combines LLM code generation, roofline-guided tool orchestration, and domain-adapted MCTS to produce GPU kernels that outperform prior automated and some hand-tuned baselines on KernelBench and VeOmni workloads.
Bandit Based Monte- Carlo Planning
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
representative citing papers
Introduces OPT* tasks and two training regimes (solver-guided online policy optimization with rank-based reward shaping and search-based offline RL) plus a theoretical link between search success and information extraction per budget unit, showing empirical gains in optimization-like reasoning.
MCTS discovers superior data encoding circuits for QCCNNs that outperform standard encodings on medical datasets, with effective rank of feature maps serving as a performance predictor.
Bandit algorithms can be adapted to Tree MDPs by treating policies as arms with shared-data confidence bounds, achieving polynomial memory and instance-dependent bounds on sample complexity and regret that depend on terminal-state gaps rather than all policies.
Inverse-RPO derives two variance-aware prior-based UCT policies from UCB-V that outperform PUCT on benchmarks with no extra cost.
BERT stores relational knowledge extractable via cloze queries without fine-tuning and matches supervised baselines on open-domain QA tasks.
COMAP co-evolves textual world models and agent policies for LLMs through on-policy self-distillation, yielding up to 16.75% relative gains on embodied planning, web navigation, and tool-use tasks.
Improved upper bound α_3 ≤ 0.2953 for Witsenhausen's problem in dimension 3 via harmonic analysis, geometric fractional chromatic number, and a computer-searched 33-point set.
A protocol-coded audit of 77 LLM trading agent studies shows that only 2 of 19 primary empirical papers report time-consistent data splits and none reach high reproducibility standards.
citing papers explorer
-
Optimizing CUDA like a Human: Micro-Profiling Tools as Expert Surrogates for LLM-Based GPU Kernel Optimization
KernelPro combines LLM code generation, roofline-guided tool orchestration, and domain-adapted MCTS to produce GPU kernels that outperform prior automated and some hand-tuned baselines on KernelBench and VeOmni workloads.
-
Step-by-Step Optimization-like Reasoning in LLMs over Expanding Search Spaces
Introduces OPT* tasks and two training regimes (solver-guided online policy optimization with rank-based reward shaping and search-based offline RL) plus a theoretical link between search success and information extraction per budget unit, showing empirical gains in optimization-like reasoning.
-
Discovering Data Encoding Strategies for Quantum-Classical Neural Networks Using Monte Carlo Tree Search
MCTS discovers superior data encoding circuits for QCCNNs that outperform standard encodings on medical datasets, with effective rank of feature maps serving as a performance predictor.
-
On-line Learning in Tree MDPs by Treating Policies as Bandit Arms
Bandit algorithms can be adapted to Tree MDPs by treating policies as arms with shared-data confidence bounds, achieving polynomial memory and instance-dependent bounds on sample complexity and regret that depend on terminal-state gaps rather than all policies.
-
Variance-Aware Prior-Based Tree Policies for Monte Carlo Tree Search
Inverse-RPO derives two variance-aware prior-based UCT policies from UCB-V that outperform PUCT on benchmarks with no extra cost.
-
Language Models as Knowledge Bases?
BERT stores relational knowledge extractable via cloze queries without fine-tuning and matches supervised baselines on open-domain QA tasks.
-
COMAP: Co-Evolving World Models and Agent Policies for LLM Agents
COMAP co-evolves textual world models and agent policies for LLMs through on-policy self-distillation, yielding up to 16.75% relative gains on embodied planning, web navigation, and tool-use tasks.
-
Improved bounds for the double cap conjecture
Improved upper bound α_3 ≤ 0.2953 for Witsenhausen's problem in dimension 3 via harmonic analysis, geometric fractional chromatic number, and a computer-searched 33-point set.
-
Agentic Trading: When LLM Agents Meet Financial Markets
A protocol-coded audit of 77 LLM trading agent studies shows that only 2 of 19 primary empirical papers report time-consistent data splits and none reach high reproducibility standards.