InfoTree casts intermediate state selection in tree search as monotone submodular maximization under fixed rollout budgets, yielding closed-form UUCB terms and lifting mixed-outcome ratios while outperforming flat GRPO and prior tree variants on nine benchmarks.
hub
Tree search for llm agent reinforcement learning
23 Pith papers cite this work. Polarity classification is still indexing.
23
Pith papers citing it
hub tools
citation-role summary
background 3
baseline 1
citation-polarity summary
representative citing papers
Crab bridges the agent-OS semantic gap with an eBPF inspector, turn-aligned coordinator, and host engine to deliver 100% recovery correctness while cutting checkpoint traffic up to 87% and adding under 2% overhead.
This survey introduces the Generate-Filter-Control-Replay (GFCR) taxonomy to structure rollout pipelines for RL-based post-training of reasoning LLMs.
IGRPO allocates multi-turn LLM agent rollout budget proportional to intermediate-state information gain, inducing an exponentially tilted teacher distribution for policy optimization.
Mastermind's dual-loop planner learns transferable strategies via SFT and milestone GRPO, raising GPT-5.5 executor pass rate on 200 held-out CyberGym tasks from 60% to 84.5%.
ReSum's contrastive RL branching on self-summarization points improves LLM math reasoning accuracy by about 4% and shortens rollouts by about 18.6% across tested backbones.
TRACE is a rollout budget allocation framework that models ReAct turns as tree nodes and uses a predictor to allocate samples to informative prefixes, yielding a 2.8-point accuracy gain on Multi-Hop QA at equal cost.
PBSD reweights RL trajectory advantages with Bayesian evidence scores from privileged answer-conditioned likelihoods, improving credit assignment in long-horizon search agents.
ECPO improves GiGPO by shrinking low-count action advantages and suppressing noisy anchor states, yielding +5.2/+7.3 success gains on ALFWorld/WebShop with Qwen2.5-1.5B models at negligible extra cost.
GDCR assigns step-level rewards via distance to the answer node in a training-time ER graph and SAPO combines these with trajectory advantages for credit assignment in agentic search.
A two-stage probe (hidden-state estimate plus attention-based correction) yields per-step GRPO rewards that survive prefix contamination and beat external-judge and tree-search rewards in the reported benchmarks.
Shepherd provides a reversible execution trace substrate for LLM agents that enables meta-agents to inspect and transform runs, yielding reported gains on coding and terminal benchmarks via supervision, counterfactual repair, and RL credit assignment.
A²TGPO improves RL policy optimization for multi-turn agentic LLMs by normalizing information gain within same-depth turn groups, rescaling cumulative advantages by sqrt of term count, and modulating clipping ranges per turn's normalized IG.
A learned orchestration policy for LLM agents that jointly optimizes task decomposition and selective routing to (model, primitive) pairs, delivering 77% macro pass@1 at 10x lower cost than strong baselines across 13 benchmarks.
TreeMem assigns credit to agents in multi-agent memory systems by expanding outputs into a tree and using Monte Carlo averaging of final rewards to optimize each agent's policy.
Tree Training serializes tree trajectories via DFS and uses redundancy-free partitioning to compute weighted per-token losses exactly once per token, achieving up to 6.2x training speedup on dense and MoE models.
APPO improves LLM agent training by branching at tokens selected for both uncertainty and future impact, then scaling credit for consequential reasoning procedures.
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.
Centralized-critic actor-critic training (CoLLM-CC) improves sample efficiency and stability over Monte-Carlo multi-agent RL for training decentralized LLM collaboration.
A survey compiling RL methods, challenges, data resources, and applications for enhancing reasoning in large language models and large reasoning models since DeepSeek-R1.
citing papers explorer
-
Maximizing Rollout Informativeness under a Fixed Budget: A Submodular View of Tree Search for Tool-Use Agentic Reinforcement Learning
InfoTree casts intermediate state selection in tree search as monotone submodular maximization under fixed rollout budgets, yielding closed-form UUCB terms and lifting mixed-outcome ratios while outperforming flat GRPO and prior tree variants on nine benchmarks.
-
Crab: A Semantics-Aware Checkpoint/Restore Runtime for Agent Sandboxes
Crab bridges the agent-OS semantic gap with an eBPF inspector, turn-aligned coordinator, and host engine to deliver 100% recovery correctness while cutting checkpoint traffic up to 87% and adding under 2% overhead.
-
Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning
This survey introduces the Generate-Filter-Control-Replay (GFCR) taxonomy to structure rollout pipelines for RL-based post-training of reasoning LLMs.
-
Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn LLM Agents
IGRPO allocates multi-turn LLM agent rollout budget proportional to intermediate-state information gain, inducing an exponentially tilted teacher distribution for policy optimization.
-
Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction
Mastermind's dual-loop planner learns transferable strategies via SFT and milestone GRPO, raising GPT-5.5 executor pass rate on 200 held-out CyberGym tasks from 60% to 84.5%.
-
ReSum: Synergizing LLM Reasoning and Summarization with Reinforcement Learning
ReSum's contrastive RL branching on self-summarization points improves LLM math reasoning accuracy by about 4% and shortens rollouts by about 18.6% across tested backbones.
-
TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning
TRACE is a rollout budget allocation framework that models ReAct turns as tree nodes and uses a predictor to allocate samples to informative prefixes, yielding a 2.8-point accuracy gain on Multi-Hop QA at equal cost.
-
PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit Assignment
PBSD reweights RL trajectory advantages with Bayesian evidence scores from privileged answer-conditioned likelihoods, improving credit assignment in long-horizon search agents.
-
When Denser Credit Is Not Enough: Evidence-Calibrated Policy Optimization for Long-Horizon LLM Agent Training
ECPO improves GiGPO by shrinking low-count action advantages and suppressing noisy anchor states, yielding +5.2/+7.3 success gains on ALFWorld/WebShop with Qwen2.5-1.5B models at negligible extra cost.
-
Beyond Trajectory Rewards: Step-level Credit Assignment for Agentic Search via Graph Modeling
GDCR assigns step-level rewards via distance to the answer node in a training-time ER graph and SAPO combines these with trajectory advantages for credit assignment in agentic search.
-
PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization
A two-stage probe (hidden-state estimate plus attention-based correction) yields per-step GRPO rewards that survive prefix contamination and beat external-judge and tree-search rewards in the reported benchmarks.
-
Shepherd: Enabling Programmable Meta-Agents via Reversible Agentic Execution Traces
Shepherd provides a reversible execution trace substrate for LLM agents that enables meta-agents to inspect and transform runs, yielding reported gains on coding and terminal benchmarks via supervision, counterfactual repair, and RL credit assignment.
-
A$^2$TGPO: Agentic Turn-Group Policy Optimization with Adaptive Turn-level Clipping
A²TGPO improves RL policy optimization for multi-turn agentic LLMs by normalizing information gain within same-depth turn groups, rescaling cumulative advantages by sqrt of term count, and modulating clipping ranges per turn's normalized IG.
-
Uno-Orchestra: Parsimonious Agent Routing via Selective Delegation
A learned orchestration policy for LLM agents that jointly optimizes task decomposition and selective routing to (model, primitive) pairs, delivering 77% macro pass@1 at 10x lower cost than strong baselines across 13 benchmarks.
-
Tree-based Credit Assignment for Multi-Agent Memory System
TreeMem assigns credit to agents in multi-agent memory systems by expanding outputs into a tree and using Monte Carlo averaging of final rewards to optimize each agent's policy.
-
Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse
Tree Training serializes tree trajectories via DFS and uses redundancy-free partitioning to compute weighted per-token losses exactly once per token, achieving up to 6.2x training speedup on dense and MoE models.
-
APPO: Agentic Procedural Policy Optimization
APPO improves LLM agent training by branching at tokens selected for both uncertainty and future impact, then scaling credit for consequential reasoning procedures.
-
SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training
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.
-
Learning Decentralized LLM Collaboration with Multi-Agent Actor Critic
Centralized-critic actor-critic training (CoLLM-CC) improves sample efficiency and stability over Monte-Carlo multi-agent RL for training decentralized LLM collaboration.
-
A Survey of Reinforcement Learning for Large Reasoning Models
A survey compiling RL methods, challenges, data resources, and applications for enhancing reasoning in large language models and large reasoning models since DeepSeek-R1.
- Optimizing CUDA like a Human: Micro-Profiling Tools as Expert Surrogates for LLM-Based GPU Kernel Optimization
- RICE-PO: Turning Retrieval Interactions into Credit Signals for Reasoning Agents
- CAPO: Critic-Guided Action-Aligned Policy Optimization for Advancing LLM Agent Capabilities