RL for LLM Agents

RL: Reinforcement Learning · LLM: Large Language Model

Ask about this topic

Overview

This field studies how to train large language model agents to act over multiple steps in environments such as web browsers, coding tools, games, and simulated workplaces. Common approaches use policy-gradient methods such as PPO and GRPO, verifiable task rewards, and process-level credit assignment to connect outcomes to particular actions or turns. Other methods teach agents to plan hierarchically, manage memory and reusable skills, or coordinate multiple agents, often using simulators and environment-generated feedback. A central challenge is making learning stable and efficient when rewards are sparse and tasks are long, while ensuring gains transfer to new environments and do not come from exploiting flawed reward signals.

Latest papers

CardsList

616 papers134 papers in the last four weeks, up 139% on the four weeks before. 0.8% of all new papers.

May 18, 2026

Learning to Hand Off: Provably Convergent Workflow Learning under Interface Constraints

We study workflow learning in a setting where specialized agents hand off control through a shared artifact, each agent observes only a local function of that artifact and its own private state, and no centralized learner accesses joint trajectories -- the operating regime of multi-agent LLM pipelines that span organizational, vendor, or trust boundaries. We formalize this regime as an interface-constrained semi-Markov decision process (IC-SMDP), whose decision epochs occur at handoff times, and design IC-QQ, an asynchronous decentralized QQ-learning algorithm in which cross-agent coordination at every handoff is exactly one scalar. Our main result is a finite-sample bound for neural IC-QQ that decomposes into three independently controllable error sources: neural function-approximation error, interface representation gap, and a mixing-time residual, under the random option-duration discount. Establishing this bound requires lifting the approximate information state (AIS) framework from single-agent primitive-step MDPs to multi-agent SMDPs and controlling Markovian noise under random duration, neither of which has been done in prior work. To our knowledge this is the first finite-sample guarantee for neural QQ-learning under decentralized partial observability. Four experiments: a controlled synthetic IC-SMDP that validates the bound term-by-term, multi-LLM mathematical reasoning, multi-agent routing, and multi-agent CPU programming, show that IC-QQ matches a centralized oracle without any agent observing joint trajectories, with each of the three error sources scaling along its corresponding axis as the bound predicts.

Jiayu Li, Enpei Zhang, Dawei Zhou +2

Stern School of Business · New York University · Department of Computer Science +2

Sequential MARLSequential Decision MakingPartially Observable RLQ-LearningSemi-Markov Decision ProcessDecentralized MARL+3
AskPDF
May 18, 2026

PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization

A significant hurdle for current LLMs is the execution of complex, multi-stage tasks. Group Relative Policy Optimization (GRPO) has been emerging as a leading choice, but its reliance on sparse outcome rewards severely limits credit assignment across intermediate steps. Existing remedies such as running full rollouts to assign step-level advantages, calling external LLM judges at each step, or computing intrinsic rewards that require ground-truth answers at every evaluation introduce significant costs or practical constraints. We hypothesize that internal correctness probing over LLM hidden states can be repurposed as a step-level reward signal, potentially addressing all of these limitations at once. However, existing probing research assumes clean inputs, and we first show that this assumption breaks down in multi-step settings: hidden-state probes degrade severely under prefix contamination tracking coherence with the (possibly corrupted) prefix rather than grounded correctness, while attention-based features remain robust to contamination but underperform on clean prefixes. Building on this complementary relationship, we propose the Prefix-Aware Internal Reward (PAIR), a two-stage model with a frozen hidden-state probe estimating belief-consistency and a lightweight attention-based head correcting it toward grounded correctness. Experimental results show that PAIR achieves the highest AUROC on contaminated trajectories while operating at negligible inference cost, enabling dense step-level reward signals for GRPO training without external model calls, ground-truth dependencies, or full-trajectory rollouts.

Wonjoong Kim, Yeonjun In, Sangwu Park +2

KAIST · Yonsei University

Reward ModelingCredit Assignment in RLStep-Level Credit Assignment in RLStep-Level Credit AssignmentSparse-Reward RLHidden-State Probing+1
AskPDF
May 18, 2026

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents

Recently, vision-language model (VLM) agents have shown promising progress in open-world tasks, where successful task completion often requires multiple turns of visual perception and action execution. However, existing methods still rely primarily on Supervised Fine-Tuning (SFT) with expert demonstrations, while the advanced reinforcement learning (RL) algorithm, specifically Group Relative Policy Optimization (GRPO), has not been effectively employed for multi-turn RL in these tasks because standard GRPO requires full trajectories as training samples which leads to excessively long context and noise. To address this issue, we propose GROW, a RL framework for open-world VLM agents that decomposes collected trajectories into state-action samples, and computes advantages between these samples rather than treating a full trajectory as a single entity. We further provide a surrogate analysis indicating that, even though the grouped samples are conditioned on different local states rather than an identical prompt context, the objective can preserve the core relative policy optimization signal of GRPO under simplifying assumptions. Experiments on more than 800 Minecraft tasks show that our method achieves state-of-the-art (SOTA) performance, demonstrating the effectiveness of our proposed RL framework for open-world VLM agents.

Xiongbin Wu, Zhihao Luo, Shanzhe Lei +7

Shanghai Jiao Tong University · Shanghai Artificial Intelligence Laboratory · East China Normal University +2

Reinforcement LearningGroup Relative Policy OptimizationRL for VLMsRL for LLM AgentsVision-Language Agents
AskPDF
May 18, 2026

HydroAgent: Closing the Gap Between Frontier LLMs and Human Experts in Hydrologic Model Calibration via Simulator-Grounded RL

Calibrating distributed hydrologic models is a critical bottleneck across operational water resources management - streamflow prediction, reservoir operation, drought monitoring, infrastructure design, and flood forecasting all depend on it. Each basin demands an expert to translate hydrograph signatures into adjustments of a high-dimensional parameter vector, and the resulting workflow does not transfer between watersheds. We ask: can frontier large language model (LLM) agents replace the human hydrologic modeler, and if not, what would it take? We benchmark nine frontier LLM agents - Claude Opus 4.6/4.7, Sonnet 4.6, GPT-5/5.4/5.4-pro, and Gemini 2.5-pro/3.1-pro/3-flash - on the operational CREST distributed hydrologic model used by the U.S. National Weather Service for flash-flood forecasting. Best-of-twenty-rounds Nash-Sutcliffe Efficiency (NSE) across four held-out gauges spanning 329-40,792 km2 ranges from -0.16 (GPT-5.4) to 0.75 (Sonnet 4.6); the ceiling reproduces across all three vendors and capability tiers, with the strongest models concentrating in the 0.65-0.75 band, and no model reaches the human-expert reference except Opus-4.7 on one gauge. We argue this gap is not a parameter-count problem but a domain-grounding problem. We then propose HYDROAGENT, fine-tuning open-weight Qwen3-4B with supervised fine-tuning on 2,576 expert calibration trajectories and Group-Relative Policy Optimization using NSE as a verifiable reward from online CREST simulations - reinforcement learning with simulation feedback (RLSF). For Earth system science, a small domain-tuned policy with simulator-in-the-loop RL is a more compute-efficient and physically faithful path than scaling generic frontier models, and the multi-modal richness of Earth data - remote sensing, in-situ time series, and forecaster narrative - makes domain agents a leveraged direction for AI in physical science.

Zhi Li, Songkun Yan, Jie Cao +4

Civil, Environmental, and Architectural Engineering, University of Colorado Boulder · Civil Engineering and Environmental Sciences, University of Oklahoma · Department of Computer Science, University of Oklahoma +3

Reinforcement LearningModel CalibrationHydrologyLLM Agent TrainingRL for LLM Agents
AskPDF
May 17, 2026

Agent Bazaar: Enabling Economic Alignment in Multi-Agent Marketplaces

The deployment of Large Language Models (LLMs) as autonomous economic agents introduces systemic risks that extend beyond individual capability failures. As agents transition to directly interacting with marketplaces, their collective behavior can amplify volatility and mask deception at scale. We introduce the Agent Bazaar, a multi-agent simulation framework for evaluating Economic Alignment, the capacity of agentic systems to preserve market stability and integrity. We identify two failure modes: (1) Algorithmic Instability in a B2C market ("The Crash"), where firms amplify price volatility until the market collapses, and (2) Sybil Deception in a C2C market ("The Lemon Market"), where a single deceptive agent controlling multiple coordinated seller identities floods the market with fraudulent listings, eroding trust and consumer welfare. We evaluate frontier and open-weight models across both scenarios and find that models largely fail to self-regulate, with failure severity varying by model rather than by size. We propose economically aligned harnesses, Stabilizing Firms and Skeptical Guardians, that improve outcomes but remain fragile under harder market conditions. To close this gap, we train agents with REINFORCE++ using an adaptive curriculum, producing a 9B model that outperforms all evaluated frontier and open-weight models. We propose the Economic Alignment Score (EAS), a 4-component scalar metric aggregating stability, integrity, welfare, and profitability, enabling direct cross-model comparison. Our results show that economic alignment is orthogonal to general capability and can be directly trained with targeted RL.

Seth Karten, Cameron Crow, Chi Jin

Princeton University

AI Agent BenchmarksMulti-Agent SystemsRL for LLM Agents
AskPDF
May 15, 2026

Look Before You Leap: Autonomous Exploration for LLM Agents

Large language model based agents often fail in unfamiliar environments due to premature exploitation: a tendency to act on prior knowledge before acquiring sufficient environment-specific information. We identify autonomous exploration as a critical yet underexplored capability for building adaptive agents. To formalize and quantify this capability, we introduce Exploration Checkpoint Coverage, a verifiable metric that measures how broadly an agent discovers key states, objects, and affordances. Our systematic evaluation reveals that agents trained with standard task-oriented reinforcement learning consistently exhibit narrow and repetitive behaviors that impede downstream performance. To address this limitation, we develop a training strategy that interleaves task-execution rollouts and exploration rollouts, with each type of rollout optimized by its corresponding verifiable reward. Building on this training strategy, we propose the Explore-then-Act paradigm, which decouples information-gathering from task execution: agents first utilize an interaction budget to acquire grounded environmental knowledge, then leverage it for task resolution. Our results demonstrate that learning to systematically explore is imperative for building generalizable and real-world-ready agents.

Ziang Ye, Wentao Shi, Yuxin Liu +6

University of Science and Technology of China · Meituan

RL ExplorationLLM AgentsLLM Agent TrainingRL for LLM Agents
AskPDF
May 15, 2026

ALSO: Adversarial Online Strategy Optimization for Social Agents

Social simulation provides a compelling testbed for studying social intelligence, where agents interact through multi-turn dialogues under evolving contexts and strategically adapting opponents. Such environments are inherently non-stationary, requiring agents to dynamically adjust their strategies over time. However, most Large Language Model (LLM) based social agents rely on static personas, while existing approaches for enhancing social intelligence, such as offline reinforcement learning or external planners, are ill-suited to these settings, typically assuming stationarity and incurring substantial training overhead. To bridge this gap, we propose ALSO (Adversarial onLine Strategy Optimization), the first framework for online strategy optimization in multi-agent social simulation. ALSO advances social adaptation through two key contributions. (1) ALSO formulates multi-turn interaction as an adversarial bandit problem, where combinations of static personas and dynamic strategy instructions are treated as arms, providing a principled solution to non-stationarity without relying on environmental stability assumptions. (2) To predict rewards and generalize sparse feedback in multi-turn dialogues, ALSO introduces a lightweight neural surrogate to predict rewards from interaction histories, enabling sample-efficient exploration and continuous online adaptation. Experiments on the Sotopia benchmark demonstrate that ALSO consistently outperforms static baselines and existing optimization methods in dynamic environments, validating the effectiveness of adversarial online strategy optimization for building robust social agents.

Xiang Li, Liping Yi, Mingze Kong +3

School of Artificial Intelligence, Tianjin University, Tianjin, China · The Chinese University of Hong Kong, Shenzhen, China · East China Normal University, Shanghai, China.

Non-Stationary RLLarge Language Model-Based Social SimulationRL for LLM Agents
AskPDF
May 15, 2026

Response-Conditioned Parallel-to-Sequential Orchestration for Multi-Agent Systems

Multi-agent systems can solve complex tasks through collaboration between multiple Large Language Model agents. Existing collaboration frameworks typically operate in either a parallel or a sequential mode. In the parallel mode, agents respond independently to queries followed by aggregation of responses. In contrast, sequential systems allow agents to communicate via a directed topology and refine one another step by step. However, both modes are inadequate for achieving the desired objectives of minimizing communication and latency while simultaneously maximizing the accuracy of the final response. In this work, we introduce a hybrid paradigm called Nexa, a trainable response-conditioned policy that bridges the gap between the two modes. Nexa begins with a parallel execution stage, embeds the resulting responses into a shared semantic space, and then predicts a sparse directed acyclic communication graph. If the graph is empty, the system remains purely parallel; if it is non-empty, the system performs one sequential message propagation. The policy is a lightweight transformer model, and the method avoids the need for external LLM judges or reward models, as well as hand-crafted test-time topology search. We formalize this hybrid execution problem, show that the resulting graph is acyclic by construction, and that the framework strictly subsumes pure parallel execution, and present a training procedure based on policy-gradient optimization. Results demonstrate that the response-conditioned policy learned by Nexa under one setting can be reused when the number of agents, the task, or the underlying agent changes, thus emphasizing the generalizability of the learned communication policy.

Nurbek Tastan, Alex Iacob, Lorenzo Sani +4

1MBZUAI, UAE · University of Cambridge, UK · 3Flower Labs, UK +1

Multi-Agent System OptimizationMulti-Agent OrchestrationMulti-Agent Communication TopologyMulti-Agent CommunicationRL for LLM Agents
AskPDF
May 14, 2026

Self-Distilled Agentic Reinforcement Learning

Reinforcement learning (RL) has emerged as a central paradigm for post-training LLM agents, yet its trajectory-level reward signal provides only coarse supervision for long-horizon interaction. On-Policy Self-Distillation (OPSD) complements RL by introducing dense token-level guidance from a teacher branch augmented with privileged context. However, transferring OPSD to multi-turn agents proves problematic: compounding multi-turn instability destabilizes supervision, while skill-conditioned privileged guidance requires asymmetric treatment for negative teacher rejections may arise from imperfect skills retrieval or utilization. We introduce SDAR (Self-Distilled Agentic Reinforcement Learning), which treats OPSD as a gated auxiliary objective while keeping RL as the primary optimization backbone. SDAR maps detached token-level signals into a sigmoid gate, strengthening distillation on teacher-endorsed positive-gap tokens and softly attenuating negative teacher rejections. Across the Qwen2.5 and Qwen3 families on ALFWorld, WebShop, and Search-QA, SDAR substantially improves over GRPO (+9.4% on ALFWorld, +7.0% on Search-QA, +10.2% on WebShop-Acc), avoids the instability of naive GRPO+OPSD, and consistently outperforms hybrid RL--OPSD baselines across model scales.

Zhengxi Lu, Zhiyuan Yao, Zhuowen Han +8

Zhejiang University · Meituan · Tsinghua University

Agentic RLSelf-DistillationOn-Policy DistillationRL for LLM Agents
AskPDF
May 14, 2026

COLLATOR: Compositional Multi-Agent Orchestration with Counterfactual Reinforcement Learning

Large language models (LLMs) provide a flexible foundation for multi-agent systems, but their effectiveness and computational cost depend critically on orchestration design. Across different tasks, role design, capacity assignment, and dependency construction jointly affect both solution quality and execution efficiency. Existing approaches automate parts of this design process, yet they often optimize these decisions partially or sequentially, and rely on execution-level feedback that provides limited credit assignment for local orchestration decisions. We propose LEMON (Learning Executable Multi-Agent Orchestration via Counterfactual Reinforcement Learning), an LLM-based orchestrator that learns to design efficient multi-agent orchestration. Given a task, LEMON designs a unified orchestration specification that composes customized agent duties, capacity levels, and dependency relations. To train the orchestrator, we augment the orchestration-level Group Relative Policy Optimization (GRPO) objective with a localized counterfactual credit signal that edits role, capacity, or dependency fields and applies the resulting reward contrast only to the edited spans. Experiments on six reasoning and coding benchmarks, including MMLU, GSM8K, AQuA, MultiArith, SVAMP, and HumanEval, show that LEMON achieves the best average performance among evaluated multi-agent orchestration methods while improving the accuracy-token trade-off.

Xudong Chen, Yixin Liu, Hua Wei +1

Multi-Agent System OptimizationMulti-Agent OrchestrationReinforcement LearningLLM Agent OrchestrationLLM Agent Workflow OptimizationCounterfactual Learning+1
AskPDF
May 13, 2026

SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestration

In recent years, a variety of powerful LLM-based agentic systems have been applied to automate complex tasks through task orchestration. However, existing orchestration methods still face key challenges, including strategy collapse under reward maximization, high gradient variance with opaque credit assignment, and unguided skill evolution whose decisions are typically made by directly prompting an LLM to judge rather than derived from principled training signals. To address these challenges, we propose SkillFlow, a flow-based framework that takes a trainable Supervisor as the agent and a structured environment with dynamic skill library and frozen executor, automating task orchestration through multi-turn interaction. SkillFlow employs Tempered Trajectory Balance (TTB), a regression-based flow-matching loss that samples trajectories proportional to reward, preserving diverse orchestration strategies rather than collapsing to a single mode. The same flow objective yields a jointly learned backward policy that provides transparent per-step credit assignment at zero additional inference cost. Building on these flow diagnostics, a recursive skill evolution mechanism determines when to evolve, what skills to create or prune, and where decision gaps lie -- closing the loop from training signal to autonomous capability growth. Experimental results on 14 datasets show that SkillFlow significantly outperforms baselines across question answering, mathematical reasoning, code generation, and real-world interactive decision making tasks. Our code is available at https://github.com/beita6969/SkillFlow.

Mingda Zhang, Tiesunlong Shen, Haoran Luo +4

The Chinese University of Hong Kong, Shenzhen · National University of Singapore · Nanyang Technological University +1

LLM Agent OrchestrationLLM Agent Self-ImprovementLLM Agent Skill LearningGenerative Flow NetworksRL for LLM Agents
AskPDF
May 13, 2026

Scaling Retrieval-Augmented Reasoning with Parallel Search and Explicit Merging

Deep search agents have proven effective in enhancing LLMs by retrieving external knowledge during multi-step reasoning. However, existing methods often generate a single query for retrieval at each reasoning step, limiting information coverage and introducing high noise. This may result in low signal-to-noise ratios (SNR) during search, degrading reasoning accuracy and leading to unnecessary reasoning steps. In this paper, we introduce MultiSearch, an RL-based framework that addresses these limitations through multi-query retrieval and explicit merging of retrieved information. At each reasoning step, MultiSearch generates queries from multiple perspectives and retrieves external information in parallel, expanding the scope of relevant information and mitigating the reliance on any single retrieval result. Then, the agent consolidates and refines retrieved information at the merging process, improving the SNR and ensuring more accurate reasoning. Additionally, we propose a reinforcement learning framework with a multi-process reward design to optimize agents for both multi-query retrieval and information consolidation. Extensive experiments on seven benchmarks demonstrate that MultiSearch outperforms baseline methods, enhancing the SNR of retrieval and improving reasoning performance in question-answering tasks.

Jiabei Liu, Wenyu Mao, Junfei Tan +4

University of Science and Technology of China · WeChat Technical Architecture Department, Tecent Inc.

Multi-Hop QAAgentic RAGInformation RetrievalRL for LLM Agents
AskPDF
May 13, 2026

GAGPO: Generalized Advantage Grouped Policy Optimization

Reinforcement learning has become a powerful paradigm for post-training large language model agents, yet credit assignment in multi-turn environments remains a challenge. Agents often receive sparse, trajectory-level rewards only at the end of an episode, making it difficult to determine which intermediate actions contributed to success or failure. As a result, propagating delayed outcomes back to individual decision steps without relying on costly auxiliary value models remains an open problem. We propose Generalized Advantage Grouped Policy Optimization (GAGPO), a critic-free reinforcement learning method for precise, step-aligned temporal credit assignment. GAGPO constructs a non-parametric grouped value proxy from sampled rollouts and uses it to compute TD/GAE-style temporal advantages, recursively propagating outcome supervision backward through time. Combined with group-wise advantage normalization and an action-level importance ratio, GAGPO extracts stable, localized optimization signals directly from multi-turn trajectories. Experiments on ALFWorld and WebShop show that GAGPO outperforms strong reinforcement learning baselines. Further analyses demonstrate faster early-stage learning, improved interaction efficiency, and smoother optimization dynamics, suggesting that GAGPO offers a simple yet effective framework for multi-turn agentic reinforcement learning.

Siyuan Zhu, Chao Yu, Rongxin Yang +4

School of Computer Science and Engineering, Sun Yat-sen University · Meituan

Reinforcement LearningGroup Relative Policy OptimizationCredit Assignment in RLStep-Level Credit Assignment in RLCritic-Free RLMulti-Turn RL+2
AskPDF
May 13, 2026

ICRL: Learning to Internalize Self-Critique with Reinforcement Learning

Large language model-based agents make mistakes, yet critique can often guide the same model toward correct behavior. However, when critique is removed, the model may fail again on the same query, indicating that it has not internalized the critique's guidance into its underlying capability. Meanwhile, a frozen critic cannot improve its feedback quality over time, limiting the potential for iterative self-improvement. To address this, we propose learning to internalize self-critique with reinforcement learning(ICRL), a novel framework that jointly trains a solver and a critic from a shared backbone to convert critique-induced success into unassisted solver ability. The critic is rewarded based on the solver's subsequent performance gain, incentivizing actionable feedback. To address the distribution shift between critique-conditioned and critique-free behavior, ICRL introduces a distribution-calibration re-weighting ratio that selectively transfers critique-guided improvements compatible with the solver's own prompt distribution. Additionally, a role-wise group advantage estimation stabilizes joint optimization across the two roles. Together, these mechanisms ensure that the solver learns to improve itself without external critique, rather than becoming dependent on critique-conditioned behavior. We evaluate ICRL on diverse benchmarks spanning agentic and mathematical reasoning tasks, using Qwen3-4B and Qwen3-8B as backbones. Results show consistent improvements, with average gains of 6.4 points over GRPO on agentic tasks, and 7.0 points on mathematical reasoning. Notably, the learned 8B critic is comparable to 32B critics while using substantially fewer tokens. The code is available at https://github.com/brick-pid/ICRL.

Jianbo Lin, Xiaomin Yu, Yi Xin +7

Hong Kong University of Science and Technology (Guangzhou) · Nanjing University · Sun Yat-sen University +3

RL for Language ModelsLLM Self-RefinementLanguage Model Self-ImprovementRL for LLM Agents
AskPDF
May 13, 2026

Reinforced Collaboration in Multi-Agent Flow Networks

Multi-agent systems provide a powerful way to extend large language models (LLMs) by decomposing a complex task into specialized subtasks handled by different agents. However, their performance is often hindered by error propagation, arising from suboptimal workflow design or inaccurate agent outputs, which can propagate through the agent collaboration process and degrade final results. To address the challenges, we present MANGO (Multi-Agent Network Gradient Optimization), a data-driven framework that organizes and refines agent collaboration via a flow network constructed from past successful workflows. MANGO integrates reinforcement learning and textual gradients to jointly optimize workflow paths and agent behaviors, while a skipping mechanism prevents redundant updates to well-optimized agents for improving efficiency. Extensive experiments on seven benchmarks show that MANGO achieves up to 12.8% performance improvement over state-of-the-art baselines, enhances efficiency by 47.4%, and generalizes effectively to unseen domains. Our code and datasets are publicly available at https://github.com/openJiuwen-ai/agent-store/tree/main/community/mango.

Zheng Wang, Yuang Liu, Yangkai Ding

Huawei Technologies Co., Ltd.

Multi-Agent LLM SystemsMulti-Agent CollaborationMulti-Agent SystemsRL for LLM Agents
AskPDF
May 12, 2026

Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction

Asynchronous reinforcement learning improves rollout throughput for large language model agents by decoupling sample generation from policy optimization, but it also introduces a critical failure mode for PPO-style off-policy correction. In heterogeneous training systems, the total importance ratio should ideally be decomposed into two semantically distinct factors: a training--inference discrepancy term that aligns inference-side and training-side distributions at the same behavior-policy version, and a policy-staleness term that constrains the update from the historical policy to the current policy. We show that practical asynchronous pipelines with delayed updates and partial rollouts often lose the required historical training-side logits, or old logits. This missing-old-logit problem entangles discrepancy repair with staleness correction, breaks the intended semantics of decoupled correction, and makes clipping and masking thresholds interact undesirably. To address this issue, we study both exact and approximate correction routes. We propose three exact old-logit acquisition strategies: snapshot-based version tracking, a dedicated old-logit model, and synchronization via partial rollout interruption, and compare their system trade-offs. From the perspective of approximate correction, we focus on preserving the benefits of decoupled correction through a more appropriate approximate policy when exact old logits cannot be recovered at low cost, without incurring extra system overhead. Following this analysis, we adopt a revised PPO-EWMA method, which achieves significant gains in both training speed and optimization performance.

Zhong Guan, Yongjian Guo, Haoran Sun +5

Tianjin University · Tsinghua University · JDT AI Infra +1

Asynchronous RLReinforcement LearningProximal Policy OptimizationOff-Policy RLRL for LLM Agents
AskPDF
May 12, 2026

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

Skill libraries enable large language model agents to reuse experience from past interactions, but most existing libraries store skills as isolated entries and retrieve them only by semantic similarity. This leads to two key challenges for compositional tasks. Firstly, an agent must identify not only relevant skills but also how they depend on and build upon each other. Secondly, it also makes library maintenance difficult, since the system lacks structural cues for deciding when skills should be merged, split, or removed. We propose SKILLGRAPH, a framework that represents reusable skills as nodes in a directed graph, with typed edges encoding prerequisite, enhancement, and co-occurrence relations. Given a new task, SKILLGRAPH retrieves not just individual skills, but an ordered skill subgraph that can guide multi-step decision making. The graph is continuously updated from agent trajectories and reinforcement learning feedback, allowing both the skill library and the agent policy to improve together. Experiments on ALFWorld, WebShop, and seven search-augmented QA tasks show that SKILLGRAPH achieves state-of-the-art performance against memory-augmented RL methods, with especially large gains on complex tasks that require composing multiple skills.

Xiaoyuan Li, Moxin Li, Keqin Bao +4

University of Science and Technology of China · National University of Singapore · Alibaba Group

LLM Agent Skill LearningLLM Agent Skill RetrievalGraph-Based Agent MemoryAgent Skill LearningRL for LLM AgentsMemory-Augmented Language Model Agents
AskPDF
May 12, 2026

GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation

Reinforcement learning has become a widely used post-training approach for LLM agents, where training commonly relies on outcome-level rewards that provide only coarse supervision. While finer-grained credit assignment is promising for effective policy updates, obtaining reliable local credit and assigning it to the right parts of the long-horizon trajectory remains an open challenge. In this paper, we propose Granularity-adaptivE Advantage Reweighting (GEAR), an adaptive-granularity credit assignment framework that reshapes the trajectory-level GRPO advantage using token- and segment-level signals derived from self-distillation. GEAR compares an on-policy student with a ground-truth-conditioned teacher to obtain a reference-guided divergence signal for identifying adaptive segment boundaries and modulating local advantage weights. This divergence often spikes at the onset of a semantic deviation, while later tokens in the same autoregressive continuation may return to low divergence. GEAR therefore treats such spikes as anchors for adaptive credit regions: where the student remains aligned with the teacher, token-level resolution is preserved; where it departs, GEAR groups the corresponding continuation into an adaptive segment and uses the divergence at the departure point to modulate the segment' s advantage. Experiments across eight mathematical reasoning and agentic tool-use benchmarks with Qwen3 4B and 8B models show that GEAR consistently outperforms standard GRPO, self-distillation-only baselines, and token- or turn-level credit-assignment methods. The gains are especially strong on benchmarks with lower GRPO baseline accuracy, reaching up to around 20% over GRPO, suggesting that the proposed adaptive reweighting scheme is especially useful in more challenging long-horizon settings.

Sijia Li, Yuchen Huang, Zifan Liu +7

Hong Kong University of Science and Technology · Microsoft Research Asia

RL for Language Model ReasoningCredit Assignment in RLPolicy LearningReward Design for RLRL for LLM AgentsRL for Tool Use
AskPDF
May 12, 2026

Agent-BRACE: Decoupling Beliefs from Actions in Long-Horizon Tasks via Verbalized State Uncertainty

Large language models (LLMs) are increasingly deployed on long-horizon tasks in partially observable environments, where they must act while inferring and tracking a complex environment state over many steps. This leads to two challenges: partial observability requires maintaining uncertainty over unobserved world attributes, and long interaction history causes context to grow without bound, diluting task-relevant information. A principled solution to both challenges is a belief state: a posterior distribution over environment states given past observations and actions, which compactly encodes history for decision making regardless of episode length. In LLM agents, however, the open-ended nature of text makes it unclear how to represent such a distribution. Therefore, we introduce Agent-BRACE: Agent Belief state Representation via Abstraction and Confidence Estimation, a method that decouples an LLM agent into a belief state model and a policy model, jointly optimized via reinforcement learning. The belief state model produces a structured approximation of the belief distribution: a set of atomic natural language claims about the environment, each annotated with an ordinal verbalized certainty label ranging from certain to unknown. The policy model conditions on this compact, structured approximate belief rather than the full history, learning to select actions under explicit uncertainty. Across long-horizon, partially observable embodied language environments, Agent-BRACE achieves an average absolute improvement of +14.5% (Qwen2.5-3B-Instruct) and +5.3% (Qwen3-4B-Instruct), outperforming strong RL baselines while maintaining a near-constant context window independent of episode length. Further analysis shows that the learned belief becomes increasingly calibrated over the course of an episode as evidence accumulates.

Joykirat Singh, Zaid Khan, Archiki Prasad +5

UNC Chapel Hill · Microsoft Research · The University of Texas at Austin

Partially Observable RLBayesian InferenceLLM Uncertainty EstimationLong-Horizon LLM AgentsRL for LLM Agents
AskPDF
May 11, 2026

RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards

Deep research agents plan, search, evaluate evidence, and synthesize long-form reports. Training these agents with reinforcement learning (RL) is challenging because they operate over long horizons and their outputs lack exact answer verifiers. To this end, we introduce RubricEM, a unified RL framework for deep research that combines stagewise credit assignment with reflection-based meta-RL for experience reuse. Rubrics unify the framework by providing a shared interface for policy execution, judge feedback, and experience reuse. RubricEM first instills a rubric-guided scaffold through supervised fine-tuning, teaching the agent to plan with rubrics and organize its trajectory into semantic stages. Building on this structural prior, we optimize the task policy with Stage-Structured GRPO, using stagewise judge feedback for finer-grained credit assignment. In parallel, we asynchronously train a shared-backbone reflection meta-policy (with meta-RL) to distill completed trajectories into reusable guidance, contributing through both shared-parameter updates and textual memory. The resulting RubricEM-8B model achieves strong performance across four long-form research benchmarks, outperforming existing open models of larger sizes and approaching proprietary deep-research systems. Beyond final performance, we perform thorough controlled analyses to understand the key ingredients of RubricEM.

Gaotang Li, Bhavana Dalvi Mishra, Zifeng Wang +9

University of Illinois Urbana-Champaign · Google Cloud AI Research

Reinforcement LearningRubric-Based RLMeta-Reinforcement LearningRubric-Based EvaluationRL Post-TrainingRubric-Guided Generation+1
AskPDF
May 11, 2026

Evolving-RL: End-to-End Optimization of Experience-Driven Self-Evolving Capability within Agents

Experience-driven self-evolving agents aim to overcome the static nature of large language models by distilling reusable experience from past interactions, thus enabling adaptation to novel tasks at deployment time. This process places substantial demands on the foundation model's capacities for abstraction, generalization, and in-context learning. However, most existing studies focus primarily on system-level design choices, such as how experience is represented and managed, neglecting the inherent capabilities of the underlying model. While some recent works have started to optimize the experience utilization stage via reinforcement learning, they still fail to treat self-evolution as a unified process to be jointly optimized. To this end, we propose Evolving-RL, an efficient algorithmic framework that jointly improves the experience extraction and utilization capabilities required for self-evolution. Specifically, we center the learning process on experience extraction and evaluation, using the two supervisory signals derived from evaluation to optimize the extractor and solver separately and thus enable their coordinated co-evolution. Experiments on ALFWorld and Mind2Web show that Evolving-RL effectively enhances LLMs' ability to extract and reuse experience, leading to strong performance gains on out-of-distribution tasks (up to 98.7% relative improvement over the GRPO baseline on ALFWorld unseen tasks and 35.8% on Mind2Web), and these gains are fully unlocked only through the coordinated co-evolution of experience extraction and utilization. Furthermore, Evolving-RL inherently functions as an experience-augmented RL algorithm. By internalizing reusable experience patterns directly into model parameters, it achieves remarkable performance gains over standard baselines on both seen and unseen tasks, even in the absence of test-time experience accumulation.

Zhiyuan Fan, Wenwei Jin, Feng Zhang +4

1Xiaohongshu Inc. · School of Computer Science, Peking University

Reinforcement LearningLanguage Model Self-ImprovementRL for LLM AgentsSelf-Evolving Agents
AskPDF
May 11, 2026

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning

Agent-compiled knowledge bases provide persistent external knowledge for large language model (LLM) agents in open-ended, knowledge-intensive downstream tasks. Yet their quality is systematically limited by incompleteness, incorrectness, and redundancy, manifested as missing evidence or cross-document links, low-confidence or imprecise claims, and ambiguous or coreference resolution issues. Such defects compound under iterative use, degrading retrieval fidelity and downstream task performance. We present DeepRefine, a general LLM-based reasoning model for agent-compiled knowledge refinement that improves the quality of any pre-constructed knowledge bases with user queries to make it more suitable for the downstream tasks. DeepRefine performs multi-turn interactions with the knowledge base and conducts abductive diagnosis over interaction history, localizes likely defects, and executes targeted refinement actions for incremental knowledge base updates. To optimize refinement policies of DeepRefine without gold references, we introduce a Gain-Beyond-Draft (GBD) reward and train the reasoning process end-to-end via reinforcement learning. Extensive experiments demonstrate consistent downstream gains over strong baselines.

Haoyu Huang, Jiaxin Bai, Shujie Liu +6

1HKUST · 2HKBU · 3Microsoft Research Asia

Knowledge EditingKnowledge Augmentation for Language ModelsLLM Agent TrainingRL for LLM Agents
AskPDF
May 11, 2026

Verifiable Process Rewards for Agentic Reasoning

Reinforcement learning from verifiable rewards (RLVR) has improved the reasoning capabilities of large language models (LLMs), yet existing approaches predominantly rely on sparse outcome-level feedback, posing a substantial credit-assignment challenge in long-horizon agentic tasks. In this work, we study structured agentic reasoning problems that admit symbolic or algorithmic task-solving oracles. We propose Verifiable Process Rewards (VPR), a training framework that repurposes such task oracles as action-level process verifiers, providing dense rewards for intermediate actions and enabling fine-grained credit assignment. We instantiate VPR in three distinct settings: a search-based oracle for Sokoban, a constraint-based oracle for Sudoku, and a posterior-based oracle for Minesweeper. To optimize policies with these rewards, we introduce oracle-guided state-group rollout and locally normalized optimization. Empirically, VPR-trained Qwen3-4B outperforms outcome-reward GRPO and VinePPO across all three training environments. When jointly trained on math data and all three game environments, VPR achieves the highest average general-reasoning performance and strongest agentic results among the compared training configurations. To further assess its applicability to more general agentic tool-use settings, we apply VPR-style action-level supervision to τ2τ^2-bench using an expert LLM as a reference policy and observe improved performance over outcome-reward GRPO on held-out tasks. Together, these results position VPR as a promising approach for leveraging reliable task oracles to improve agentic reasoning, while highlighting its dependence on the availability and reliability of task oracles and the challenge of extending intermediate verification to less structured, open-ended environments.

Huining Yuan, Zelai Xu, Huaijie Wang +6

Tsinghua University

Process Reward ModelsCredit Assignment in RLStep-Level Credit Assignment in RLReinforcement Learning with Verifiable RewardsRL for LLM Agents
AskPDF
May 10, 2026

Skill-R1: Agent Skill Evolution via Reinforcement Learning

Agentic large language models often rely on skills, reusable natural language procedures that guide planning, action, and tool use. In practice, skills are typically improved through prompt engineering or by aligning the task LLM itself, which is costly, model-specific, and often infeasible for closed-source models. Skill optimization is not a one-step problem but a recurrent process with two coupled levels of credit assignment: a useful skill must improve rollout quality under current conditioning, while a useful revision must turn observed outcomes into a better skill for the next round. We propose Skill-R1, a reinforcement learning framework for instance-level recurrent skill optimization from verifiable rewards. Rather than updating the task LLM, Skill-R1 trains a lightweight skill generator that conditions on the task context, prior rollouts, and their verified outcomes to produce skills that steer a frozen task LLM. This preserves black-box compatibility with both open- and closed-source models while making adaptation substantially cheaper than model-level updates. Skill-R1 proceeds over multiple generations: at each step, the current skill induces rollouts whose verified outcomes are fed back to produce the next revision. To optimize this recurrent process, we introduce a bi-level group-relative policy optimization objective combining intra-generation and inter-generation advantages. The intra-generation term compares rollouts under shared skill conditioning, while the inter-generation term rewards revisions that improve behavior across successive generations. Together, these provide a principled objective for directional skill evolution rather than one-shot self-refinement. Empirically, Skill-R1 achieves consistent gains over no-skill baselines and standard GRPO across benchmarks with verifiable rewards, with particularly strong improvements on complex, multi-step tasks.

Yash Vishe, Rohan Surana, Xunyi Jiang +8

UC San Diego · Adobe Research

Agent Skill LearningRL for LLM Agents
AskPDF
May 10, 2026

PiCA: Pivot-Based Credit Assignment for Search Agentic Reinforcement Learning

Large Language Model (LLM)-based search agents trained with reinforcement learning (RL) have significantly improved the performance of knowledge-intensive tasks. However, existing methods encounter critical challenges in long-horizon credit assignment: (i) Reward Sparsity, where models receive only outcome feedback without step-level guidance to differentiate action quality; (ii) Isolated Credit, where credit is assigned to steps independently, failing to capture sequential dependencies; and (iii) Distributional Shift, where rewards are estimated on templates that deviate from the model's natural generative distribution. To address these issues, we propose Pivot-Based Credit Assignment (PiCA), a novel step reward mechanism that reformulates the search trajectory as a sequential process of cumulative search progress. Unlike prior isolated step rewards, PiCA defines process rewards as success probabilities dependent on the historical context based on Potential-Based Reward Shaping (PBRS). This approach identifies pivot steps, which comprise target golden sub-queries and sub-answers derived from historical trajectories, as information peaks that significantly boost the likelihood of a correct final answer. By anchoring these step rewards to the final task objective, PiCA provides dense, pivot-aware and trajectory-dependent guidance while maintaining distributional consistency. Extensive experiments show that PiCA outperforms existing strong baselines across seven knowledge-intensive QA benchmarks, achieving 15.2% and 4.4% improvements for 3B and 7B models. The consistent performance gains across various models show PiCA's robust generalization. The code is available at https://github.com/novdream/PiCA.

Dongyi Liu, Yifan Niu, Qinwen Wang +2

The Hong Kong University of Science and Technology (Guangzhou) · The Hong Kong University of Science and Technology

Reinforcement LearningReward ShapingCredit Assignment in RLStep-Level Credit Assignment in RLStep-Level Credit AssignmentSparse-Reward RL+1
AskPDF
May 9, 2026

Learning to Explore: Scaling Agentic Reasoning via Exploration-Aware Policy Optimization

Recent advancements in agentic test-time scaling allow models to gather environmental feedback before committing to final actions. A key limitation of existing methods is that they typically employ undifferentiated exploration strategies, lacking the ability to adaptively distinguish when exploration is truly required. In this paper, we propose an exploration-aware reinforcement learning framework that enables LLM agents to adaptively explore only when uncertainty is high. Our method introduces a fine-grained reward function via variational inference that explicitly evaluates exploratory actions by estimating their potential to improve future decision-making, together with an exploration-aware grouping mechanism that separates exploratory actions from task-completion actions during optimization. By targeting informational gaps, this design allows agents to explore selectively and transition to execution as soon as the task context is clear. Empirically, we demonstrate that our approach achieves consistent improvements across a range of challenging text-based and GUI-based agent benchmarks. Code is available at https://github.com/HansenHua/EAPO-ICML26 and models are available at https://huggingface.co/hansenhua/EAPO-ICML26.

Xingyuan Hua, Sheng Yue, Ju Ren

Department of Computer Science and Technology, Tsinghua University, Beijing, China · State Key Laboratory of Internet Architecture, Tsinghua University, Beijing, China · School of Cyber Science and Technology, Sun Yat-sen University Shenzhen Campus, Shenzhen, China

RL for Language Model ReasoningTest-Time ScalingRL ExplorationRL for LLM Agents
AskPDF
May 9, 2026

EvoMAS: Learning Execution-Time Workflows for Multi-Agent Systems

Large language model (LLM)-based multi-agent systems have shown strong potential on complex tasks through agent specialization, tool use, and collaborative reasoning. However, most automated multi-agent system design methods still follow a one-shot paradigm: a workflow is optimized or selected before execution and then reused unchanged throughout the task. This static coordination strategy is ill-suited for long-horizon tasks whose subgoals, intermediate evidence, and information needs evolve over multiple execution stages. We propose EvoMAS, a framework for execution-time multi-agent workflow construction. EvoMAS formulates workflow construction as a meta-level sequential decision problem along a single task trajectory. At each stage, it constructs an explicit task state through a Planner-Evaluator-Updater pipeline and uses a learned Workflow Adapter to instantiate a stage-specific layered workflow from a fixed pool of candidate agents. The adapter is trained with policy gradients using sparse, verifiable terminal task success as the main supervision signal, while evaluator-based process reward is analyzed separately under very-hard sparse-reward settings. Experiments on GAIA, HLE, and DeepResearcher show that EvoMAS outperforms single-agent baselines and recent automated multi-agent workflow design methods. Our analyses further show that explicit task-state construction and learned workflow adaptation provide complementary benefits. Additional results indicate that process reward is most useful when terminal success is extremely sparse, and qualitative case studies illustrate that EvoMAS adapts agent coordination as the task state evolves.

Chengdong Xu, Kaiqiang Ke, Ziheng Liu +4

Sun Yat-Sen University · ShanghaiTech University · Zhejiang University +1

Multi-Agent LLM SystemsMulti-Agent System OptimizationMulti-Agent OrchestrationLLM Agent Workflow OptimizationLong-Horizon LLM AgentsRL for LLM Agents
AskPDF
May 9, 2026

SkillMaster: Toward Autonomous Skill Mastery in LLM Agents

Skills provide an effective mechanism for improving LLM agents on complex tasks, yet in existing agent frameworks, their creation, refinement, and selection are typically governed by external teachers, hand-designed rules, or auxiliary modules. As a result, skills remain external resources to be invoked, rather than capabilities that agents can develop, adapt, and internalize through experience. To endow LLM agents with autonomous skill mastery, we propose SkillMaster, a training framework that teaches agents to create new skills, refine existing skills, and select accumulated skills during task solving. This capability is achieved through three key designs. First, we train agents through trajectory-informed skill review, teaching agents to propose, update, or retain skills based on evidence from completed episodes. Second, each candidate skill edit is designed to be evaluated by its counterfactual utility on related probe tasks, providing a direct learning signal for training skill-editing decisions. Third, we introduce DualAdv-GRPO, which separately estimates advantages for task-solving actions and skill-editing decisions, stabilizing joint training across task solving and skill management. Experiments on ALFWorld and WebShop show that SkillMaster improves the overall success rate over state-of-the-art baselines by 8.8% and 9.3%, respectively, achieving the best performance among all compared methods. Further analysis reveals a marked shift in agent capability: agents trained with SkillMaster can identify skill failures, refine procedural knowledge from trajectory evidence, and transfer improvements to future tasks with limited skill-bank edits. Overall, SkillMaster moves LLM agents beyond mere skill use toward self-improving agents capable of developing, adapting, and applying their own skill repertoires.

Min Yang, Jinghua Piao, Xu Xia +4

Shandong University · Zhongguancun Academy · Tsinghua University +2

LLM Agent Self-ImprovementLLM Agent Skill LearningRL for LLM Agents
AskPDF
May 9, 2026

Iterative Critique-and-Routing Controller for Multi-Agent Systems with Heterogeneous LLMs

Multi-agent large language model (LLM) systems often rely on a controller to coordinate a pool of heterogeneous models, yet existing controllers are typically limited to one-shot routing: they select a model once and return its output directly. Such routing-only designs provide no mechanism to critique intermediate drafts or support iterative refinement. To address this limitation, we propose a critique-and-routing controller that casts multi-agent coordination as a sequential decision problem. At each turn, the controller evaluates the current draft, decides whether to stop or continue, and, if needed, selects the next agent for further refinement. We formulate this process as a finite-horizon Markov Decision Process (MDP) with explicit agent-utilization constraints, design a composite reward for controller decisions across turns, and optimize the controller via policy gradients under a Lagrangian-relaxed objective. Extensive experiments across multiple heterogeneous multi-agent systems and seven reasoning benchmarks show that our method consistently outperforms state-of-the-art baselines and substantially narrows the gap to the strongest agent, while using it for fewer than 25% of total calls.

Wenzhi Fang, Liangqi Yuan, Guangchen Lan +2

Purdue University · Yonsei University

Multi-Agent LLM SystemsMulti-Agent CoordinationLLM RoutingMulti-Agent ReasoningRL for LLM Agents
AskPDF
May 8, 2026

Towards Autonomous Business Intelligence via Data-to-Insight Discovery Agent

Transforming fragmented enterprise data into actionable insights remains a significant challenge for LLMs, constrained by complex database schemas, limitations in dynamic SQL generation, and the need for deep multi-dimensional analysis.In this paper, we propose AIDA(Autonomous Insight Discovery Agent), the first end-to-end framework designed for autonomous exploration in complex business environments. We establish a highly flexible instant retail environment encompassing 200+ metrics and 100+ dimensions, and integrates a proprietary Domain-Specific Language (DSL) that bridges semantic reasoning with precise SQL execution. Our reinforcement learning system subsequently formulates business analysis as a Pareto Principle-guided cumulative reasoning process. Experimental results demonstrate that AIDA significantly outperforms workflow-based agents, and extensive evaluations further reveal that AIDA achieves superior environmental perception and more in-depth analysis from diverse perspectives. Our work ultimately establishes the transformative potential of autonomous intelligence for industrial-scale business intelligence systems.

Dongming Wu, Junwen Li, Ming Lu +2

1Rajax Network Technology(Taobao Shangou of Alibaba)

AI-Assisted Decision MakingRL for LLM Agents
AskPDF