Agentic RL

RL: Reinforcement Learning

Follow this topic Ask about this topic

Momentum

28 papers in the last four weeks, up 300% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 140

Jul 15, 2026cs.RO

Learning Robust Execution in Robotic Manipulation with Agentic Reinforcement Learning

Robotic manipulation poses fundamental challenges due to uncertainty, long-horizon execution, and compounding errors, which can easily destabilize execution and lead to task failure. Although recent vision-language-action (VLA) models exhibit strong generalization, they typically lack explicit mechanisms to assess execution stability and to recover when execution deviates from its nominal behavior. In this paper, we propose: (1) two complementary metrics to assess execution quality at runtime, and (2) an agentic reinforcement learning framework that learns to restore effective execution through high-level decision-making rather than directly learning low-level actions. In this framework, an agentic policy reasons over recent execution history and selects among a small set of execution modes to regulate the execution process. Under execution degradation, it triggers appropriate recovery mechanisms to restore the robot to previously visited nominal states, enabling the task to continue. We evaluate the proposed method on the LIBERO benchmark, achieving up to a 13.7% improvement in success rate under standard settings and up to a 39.2% improvement under disturbance settings, demonstrating substantially enhanced execution robustness.

Xiaopeng Zhang, Yueyang Weng, Qi Liu +2

School of Inteligence Science and Engineering, the Harbin Institute of Technology Shenzhen, 518055, China. · Faculty of Robot Science and Engineering, Northeastern University, Shenyang, 110819, China.

Agentic RL Robot Failure Recovery Robotic Manipulation Robust RL Robustness of VLA Models

Jul 10, 2026cs.LG

Mach-Mind-4-Flash Technical Report

We present Mach-Mind-4-Flash, a 35B-parameter Mixture-of-Experts (MoE) agentic model with 3B activated parameters. Through post-training optimization alone without scaling pre-training compute, the model achieves performance on par with or surpassing that of 100B-parameter-class models. By introducing scalable agentic interaction environments for large-scale reinforcement learning, the model attains significant performance gains on real-world application tasks. Our pipeline comprises three stages: (1) a unified RL/OPD training infrastructure with dynamic multi-teacher scheduling and operator-level acceleration, delivering 17% end-to-end training speedup; (2) multiple domain-specific RL experts trained in parallel across Reasoning, General, and Agent tracks, then fused into a single generalist via Multi-Teacher On-Policy Distillation (MOPD) -- a routed reverse-KL objective that eliminates the see-saw degradation of mixed-reward RL; (3) Hybrid Median-length Policy Optimization (HMPO), a single-stage token-efficiency method that compresses reasoning chains by 19--46% with

\le

0.7 percentage-point accuracy loss. Mach-Mind-4-Flash scores 92.70 on AIME'26, 82.82 on IFBench, 80.74 on Behavioral-SafetyBench, 75.80 on BFCL-v4, 72.31 on BrowseComp-zh, and 84.20 on ClawBench -- leading or matching models with 10--30

\times

its activated size at a fraction of the inference cost.

Foundation Model Team

Foundation Model, Li Auto Inc.

Agentic RL Token Efficiency LLM Agent Training On-Policy Distillation RL Post-Training Mixture-of-Experts Models

Jul 8, 2026cs.LG

Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning

Reinforcement learning (RL) is becoming increasingly important for post-training large language models (LLMs). Previous RL pipelines for LLMs were mostly synchronous and batch-interleaved, which is inefficient for long-horizon agentic tasks. Recently, asynchronous RL has emerged as a more efficient alternative by updating the model as rollouts arrive. However, existing asynchronous RL systems often emphasize throughput, while leaving training stability and task effectiveness largely underexplored. For example, a key challenge is that group-wise sampling in the widely-used GRPO framework does not naturally fit asynchronous agentic training. In this paper, we present Single-rollout Asynchronous Optimization (SAO) to address the stability and off-policy challenges in asynchronous RL. To reduce off-policy effects and improve generalization, we replace group-wise sampling with single-rollout sampling, that is, using one rollout per prompt. We further improve this single-rollout strategy with practical value-model training designs. To improve optimization stability, we introduce a strict double-side token-level clipping strategy. SAO is able to train stably for one thousand steps and consistently outperform GRPO and its variants on agentic coding and reasoning benchmarks, such as SWE-Bench Verified, BeyondAIME, and IMOAnswerBench. We also demonstrate that single-rollout RL is particularly effective in a simulated online learning setting, where the model must adapt to changing evolving environments. To this end, SAO is successfully deployed in the agentic RL pipeline for training the open GLM-5.2 model (750B-A40B).

Zhenyu Hou, Yujiang Li, Jie Tang +1

Tsinghua University · Work done while ZH and YL interned at Z.AI.

Agentic RL Asynchronous RL Reinforcement Learning RL Post-Training Off-Policy RL

Jul 8, 2026cs.LG

RLVP: Penalize the Path, Reward the Outcome

Agents acting on our behalf in the real world (e.g. placing phone calls) must learn online from costly, often irreversible interactions rather than cheap simulator steps. Two things follow. First, deployability depends on the path, not only the outcome. An agent must respect outcome-neutral constraints such as not repeatedly calling an unresponsive user, respecting business hours, or completing required authentication constraints that outcome-based rewards cannot express, since violating them frequently improves apparent success. Second, because each interaction is expensive, the agent must learn efficiently from very few examples. Reinforcement learning from verifiable rewards (RLVR) is blind to both challenges: it optimizes solely on the outcome and wastes expensive rollouts on all-fail groups where group-relative advantage collapses to zero. Attempts to densify supervision by rewarding progress target the hard-to-verify direction. In contrast, real agentic environments can cheaply detect bad moves. Since group-relative advantage is equivalent to within-group variance, a dense signal helps only when it supplies variance the outcome lacks. A verifiable penalty on the path meets this condition reliably, while a progress potential helps only where partial progress is reachable. The resulting recipe "penalize the path, reward the outcome" achieves high task success with near-zero violations, where outcome-only training violates constraints on nearly every episode. We provide four design rules for effective penalties, including avoidance of the inaction trap that arises when a penalty is used in isolation.

Bojie Li, Noah Shi

Pine AI · University of Washington

Agentic RL Constrained RL Reinforcement Learning with Verifiable Rewards Reward Design for RL

Jul 8, 2026cs.LG

Entropy Pacing Policy Optimization for Multi-Task Agentic Reinforcement Learning

Recent breakthroughs of Reinforcement Learning (RL) have highlighted its potential for complex agentic Large Language Model (LLM) tasks. However, existing efforts largely focus on single-task settings, whereas real-world deployment necessitates a generalist agent capable of solving multiple tasks simultaneously. In this work, we identify a critical yet underexplored phenomenon in multi-task agentic RL: different tasks can exhibit exploration-exploitation pace mismatch. Specifically, easier tasks may converge early to low-entropy policies that hinder learning on harder tasks, while harder tasks can, in turn, push easier tasks back toward high-entropy exploration. This back-and-forth interaction creates inter-task entropy crossovers and frequent entropy spikes. Inspired by this observation, we introduce Entropy Pacing Policy Optimization (EPPO) for multi-task agentic LLMs, which coordinates entropy across tasks to stabilize multi-task optimization. At the core of EPPO is a task-wise dynamic clipping mechanism that replaces the fixed clipping threshold in Group Relative Policy Optimization (GRPO) with a task entropy-aware adaptive bound, tightening updates for over-confident tasks while relaxing them for under-explored ones. Experiments on the multi-task agentic benchmarks demonstrate that the proposed EPPO yields results superior to its counterparts.

Zetian Hu, Shunyu Liu, Junjie Zhang +4

Generative AI Lab, College of Computing and Data Science, Nanyang Technological University, Singapore 639798 · Tongyi Lab, Alibaba Group

Agentic RL Group Relative Policy Optimization Maximum Entropy RL Multi-Task RL RL for LLM Agents

Jul 7, 2026cs.AI

Beyond Static Evaluation: Building Simulation Environments for Scalable Agentic Reinforcement Learning

As Large Language Models (LLMs) evolve into autonomous agents, traditional static evaluation fails to capture multi-step decision-making. We introduce AgenticAI-Supervisor, an API and UI-driven RL Gym environment that decouples environment creation from scalable execution. By moving to verifiable execution outcomes, the platform generates high-fidelity traces and applies multi-dimensional reward shaping. Critically, our framework mitigates reward hacking through rigorous internal state validation and testing. This work provides a first look at our platform's core capabilities through a Customer Support Agent case study demonstrating a consistent closed-loop feedback for model optimization. Future work will focus on advanced features such as Computer Use, Tool Use, automated "stumping", and edge-case generation.

Akshay Arora, Ishan Nigam, Ashutosh Aggarwal +6

Uber AI Solutions San Francisco, CA, USA

Agentic RL AI Agent Evaluation Reinforcement Learning with Verifiable Rewards

Jul 5, 2026cs.AI

Progress- and Reliability-Oriented Group Policy Optimization for Agentic Reinforcement Learning

Group-based reinforcement learning (RL) has become an effective paradigm for improving large language model agents on long-horizon interactive tasks. To obtain finer-grained policy updates than trajectory-level optimization, recent work has moved toward step-level group-based RL, where intermediate steps are grouped and compared within a rollout batch. However, step-level advantage estimation is sensitive to how groups are formed: grouping by broad state keys improves coverage but may compare actions taken under different histories, while enforcing historical consistency yields fairer comparisons at the cost of fragmented groups and missing peer-comparison signal. In this paper, we propose ProGPO (Progress- and Reliability-Oriented Group Policy Optimization), a learned-critic-free method for context-consistent step-level learning. ProGPO keeps exact-prefix action comparison, and complements sparse peer comparisons with transition credit derived from rollout-based state potentials. To estimate these potentials reliably, ProGPO combines semantic expansion with inverse-variance fusion across history depths. We evaluate ProGPO on two challenging agentic tasks, ALFWorld and WebShop, with Qwen2.5-1.5B-Instruct. Results show that ProGPO improves over matched agentic RL baselines under comparable computational overhead, and additional Qwen2.5-3B-Instruct experiments further test the scalability of the proposed method.

Mingxuan Fan, Peiyang Liu

Baidu Inc., China · Peking University, China

Agentic RL Group Relative Policy Optimization Policy Optimization

Jul 4, 2026cs.AI

Harness-Aware Self-Evolving: Co-Evolving Model Weights, Harness, and Task Solutions

Self-evolving frameworks usually optimize task solutions while treating the surrounding harness as fixed. We introduce Harness-Aware Self-Evolving (HASE), an agentic reinforcement-learning framework in which a single model can generate task solutions or edit selected harness components in a multi-turn action space. HASE enables a single Qwen3-8B model to match the text-classification performance of a GPT-OSS-120B model that uses Claude Code as the harness proposer. In alpha factor mining, HASE outperforms the reported GPT-OSS-120B baseline. HASE also repairs imperfect evaluation components and converges to state-of-the-art performance in circle-packing algorithm discovery. These results show that HASE improves the harness and the solution through one unified agentic process.

Haochen Luo, Yi Huang, Sichun Luo +5

School of Computing and Data Science, The University of Hong Kong · Grace Investment Machine · Jiutian Research, China Mobile

Agentic RL Agent Harness Optimization LLM Agent Harnesses Self-Evolving Agents

Jun 30, 2026cs.LG

TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning

Agentic reinforcement learning requires assigning credit to environment-facing actions such as searches, clicks, edits, navigation commands, and object interactions. Standard GRPO uses the final verifier outcome as a uniform advantage over all action tokens. This outcome signal is useful but structurally incomplete: it punishes useful exploration in failed rollouts and reinforces redundant or regressive actions in successful rollouts. We propose TRIAGE, a role-typed credit assignment framework that adds a semantic role axis to outcome credit. A structured judge classifies each segment as decisive progress, useful exploration, no-progress infrastructure, or regression, and a fixed role-conditioned rule maps these labels to bounded segment-level process rewards. This keeps verifier outcomes as the source of optimization direction while correcting the two main blind spots of outcome-only credit. We further show that role-conditioned credit is the optimal segment-level correction expressible from role labels alone -- a projection of the per-segment advantage residual onto the role variable -- so that the fixed role constants reduce advantage estimation error whenever the judge is reliable, and we connect this to lower-variance policy gradients. Across ALFWorld, Search-QA, and WebShop, TRIAGE improves success rates over GRPO for two policy models and outperforms both a scalar judge-derived process reward and an outcome-supervised shared-backbone value baseline. Ablations show that the gain comes from role typing rather than merely adding dense rewards: reliable detection of regression inside successful trajectories is the dominant contributor, while exploration credit provides a consistent secondary gain; on completed ALFWorld and WebShop rollouts, TRIAGE also reduces environment-facing turns by an additional

10.4\%

and

14.8\%

relative to GRPO.

Yuanda Xu, Zhengze Zhou, Hejian Sang +6

1LinkedIn Corporation · 2Harvard University · 3Johns Hopkins University +1

Agentic RL Step-Level Credit Assignment in RL Credit Assignment Policy Learning Reward Design for RL Fine-Grained Credit Assignment+1

Jun 30, 2026cs.LG

ECHO: Prune To Act, Trace To Learn With Selective Turn Memory In Agentic RL

Long-horizon language agents must repeatedly interact with tools, accumulate evidence, and make decisions under bounded context windows. Context-management methods make such rollouts feasible by simplifying past interactions through deletion, folding, or memory editing. However, when useful history is collapsed into compressed states, the reconstructed context may no longer reveal which earlier observations support a successful final answer. This creates a mismatch between bounded-context acting and outcome-based reinforcement learning: the policy acts on reconstructed context, while the learner lacks source-level provenance for assigning credit to the evidence that mattered. We propose ECHO, a selective turn-memory framework for traceable context reconstruction in Agentic RL. ECHO compresses each completed environment turn into a compact source-indexed memory record, reconstructs bounded policy contexts by selecting useful records, and reuses the selected source indices to route positive outcome credit to the final trajectory segment, reused evidence turns, memory findings, and memory-selection actions. On BrowseComp-Plus, ECHO reaches 43.4% held-out accuracy, outperforming GRPO at 28.9% and the rolling-summary baseline SUPO at 36.1%, while using fewer turns and lower trajectory volume than SUPO. The trained policy also improves zero-shot generalization across multi-objective QA, code generation, and deep information-seeking benchmarks on both dense and MoE backbones.

Zijun Xie, Binbin Zheng, Enlei Gong +7

School of Mathematical Sciences, Peking University · Baidu Inc. · University of Science and Technology of China

Agentic RL Credit Assignment in RL Long-Horizon LLM Agents LLM Context Management Memory-Augmented Language Model Agents

Jun 28, 2026cs.LG

CRAFT: Counterfactual Credit Assignment from Free Sibling Rollouts for Self-Distilled Agentic Reinforcement Learning

Self-distilled agentic reinforcement learning augments trajectory-level reward with a token-level distillation loss, using as its teacher the same policy conditioned on privileged context. The prevailing recipe gates this loss by a single scalar, the teacher-student log-probability gap. This signal is doubly limited: it is retrospective, scoring only the realised rollout and never the counterfactual ones, and it is sign-blind, never signalling when a teacher-preferred action would have harmed the trajectory. We introduce CRAFT, a three-pillar credit-assignment scheme that addresses both limitations. Pillar 1, Counterfactual Token Importance, reuses the G-1 sibling rollouts that GRPO already samples and importance-weights them by the log-probability gap to form a self-normalised estimate of the group-level counterfactual change in advantage from up-weighting teacher-preferred actions at each step; this yields a signed per-token credit at near-zero extra compute. Pillar 2 is an asymmetric controller that raises the distillation weight as it lowers the reference-KL weight along an exponential moving average of gate activity, and conversely. Pillar 3 polarises the KL penalty token by token, switching between a mode-seeking and a mode-covering update according to the sign of the credit. Each pillar has an independent switch that, when disabled, renders the loss and gradient byte-identical to the baseline in IEEE-754 arithmetic, so any measured gain is attributable to algorithmic change rather than implementation drift. We prove the estimator's consistency and a variance bound, give structural and bit-exact reproducibility guarantees, and evaluate CRAFT across three agentic environments, four model scales, and five end-to-end methods, plus two tabulated prior-work baselines. Among these is Adaptive-CRINGE, a comparator sharing Pillar 2 with CRAFT, isolating the counterfactual contribution.

Zibin Meng, Kani Chen

The Hong Kong University of Science and Technology

Agentic RL KL-Regularized RL Credit Assignment in RL Step-Level Credit Assignment in RL On-Policy Distillation Counterfactual Credit Assignment

Jun 26, 2026cs.AI

ATOD: Annealed Turn-aware On-policy Distillation for Multi-turn Autonomous Agents

Training small language-model agents for long-horizon interactive tasks requires both fast imitation and reward-driven improvement. On-policy distillation (OPD) provides dense teacher guidance and typically improves rapidly in the early stage, but its gains saturate once the student approaches the teacher, limiting the final performance ceiling. Reinforcement learning (RL) directly optimizes environment rewards and encourages exploratory improvement toward a higher reward-defined ceiling, but sparse and delayed feedback makes early-stage learning much less efficient than OPD. In this paper, we propose ATOD (Annealed Turn-aware On-policy Distillation), a hybrid online distillation algorithm that explicitly exploits this complementarity. (1) ATOD uses an annealed OPD-RL schedule: OPD dominates early training to approach teacher-level behavior, while RL is gradually strengthened to drive reward-based exploration. (2) ATOD introduces Turn-level Disagreement-Uncertainty Reweighting (T-DUR), which softly amplifies high-utility turns and improves dense supervision in long trajectories. Experiments on ALFWorld, WebShop, and Search-QA show that ATOD consistently outperforms competing post-training baselines: across the three student sizes, ATOD improves average success rate by 3.03 points over OPD and 23.62 points over GRPO, while surpassing the corresponding teacher models by 2.16 points.

Qitai Tan, Zefang Zong, Yang Li +1

Tencent Inc. · Tsinghua University

Agentic RL On-Policy Distillation RL Post-Training RL for LLM Agents

Jun 25, 2026cs.CL

OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning

Outcome-based reinforcement learning provides a stable optimization backbone for language agents, but its sparse trajectory-level rewards provide little guidance on which intermediate decisions should be reinforced or suppressed. On-policy self-distillation offers dense token-level supervision, yet existing skill-conditioned variants often rely on external skill memories or retrieved privileged context, which are costly to maintain and can be mismatched with the state distribution induced by the current policy in multi-turn interaction. We propose \textbf{OPID} (\textbf{O}n-\textbf{P}olicy Sk\textbf{i}ll \textbf{D}istillation), a framework that extracts skill supervision directly from completed on-policy trajectories. OPID represents trajectory hindsight as hierarchical skills: episode-level skills capture global workflows or failure-avoidance rules, while step-level skills capture local decision knowledge at critical timesteps. A critical-first routing mechanism uses step-level skills when critical decisions are identified and falls back to episode-level skills as default guidance otherwise. The selected skill is injected into the interaction history, allowing the old policy to re-score the same sampled response under both original and skill-augmented contexts. The resulting log-probability shift yields a token-level self-distillation advantage, which is combined with the outcome advantage for policy optimization. OPID thus preserves RL as the primary training objective while introducing dense, distribution-matched hindsight supervision. Experiments on ALFWorld, WebShop and Search-based QA demonstrate that OPID generally improves agent performance, sample efficiency, and robustness over outcome-only RL and existing skill-distillation baselines. Our code is available at https://github.com/jinyangwu/OPID/tree/main.

Shuo Yang, Jinyang Wu, Zhengxi Lu +8

1Tsinghua University · 2Zhejiang University · 3The Chinese University of Hong Kong +2

Agentic RL LLM Agent Skill Learning On-Policy Distillation Policy Learning

Jun 23, 2026cs.CL

Qwen-AgentWorld: Language World Models for General Agents

A world model predicts environment dynamics based on current observations and actions, serving as a core cognitive mechanism for reasoning and planning. In this work, we investigate how world modeling based on language models can further push the boundaries of general agents. (i) We first focus on building foundation models for agentic environment simulation. We introduce Qwen-AgentWorld-35B-A3B and Qwen-AgentWorld-397B-A17B, the first language world models capable of simulating agentic environments covering 7 domains via long chain-of-thought reasoning. Leveraging more than 10M environment interaction trajectories of 7 domains in real-world environments, we develop Qwen-AgentWorld through a three-stage training pipeline: CPT injects general-purpose world modeling capabilities from the state transition dynamics and augmented professional corpora, SFT activates next-state-prediction reasoning, and RL sharpens simulation fidelity through a tailored framework with hybrid rubric-and-rule rewards. To evaluate language world models, we present AgentWorldBench, a comprehensive benchmark constructed from real-world interactions of 5 frontier models on 9 established benchmarks. Empirical results demonstrate that Qwen-AgentWorld significantly outperforms existing frontier models. (ii) Beyond foundation models, we further investigate two complementary paradigms through which world modeling enhances general agents. First, as a decoupled environment simulator, Qwen-AgentWorld supports scalable and controllable simulation of thousands of real-world environments for agentic RL, yielding gains that surpass real-environment training alone. Second, as a unified agent foundation model, world-model training acts as a highly effective warm-up that improves downstream performance across 7 agentic benchmarks. Code: https://github.com/QwenLM/Qwen-AgentWorld

Yuxin Zuo, Zikai Xiao, Li Sheng +30

Qwen Team

LLM World Models Agentic RL World Model Learning World Model Evaluation

Jun 22, 2026cs.LG

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

Group-based Reinforcement Learning (RL) has significantly enhanced Large Language Models (LLMs) in agentic scenarios. To achieve finer-grained policy updates, recent agentic RL frameworks have shifted from trajectory-level to step-level training. However, long-horizon agentic RL suffers from severe reward sparsity and delay, as feedback is often deferred for dozens of interaction steps. While existing step-level frameworks refine training granularity, their credit assignment remains coarse-grained and still treats agent exploration as isolated, linear trajectories. This oversimplified perspective ignores the inherent graph structure of state transitions, leading to high-variance state-value estimation and myopic, localized credit assignment. To overcome these critical bottlenecks, we propose Group-Graph Policy Optimization (G2PO), a novel group-based RL algorithm tailored for multi-turn agentic tasks. G2PO explicitly transforms linear interaction trajectories into a global state-transition graph. By aggregating identical observations across different trajectories, we introduce group-aggregation state-value estimation that reduces sampling variance and trajectory-dependent bias. Furthermore, we redefine agent actions as transitions between state nodes and propose an edge-centric advantage estimation strategy. By globally standardizing Temporal Difference (TD) errors across the entire graph, G2PO explicitly identifies and prioritizes critical transitions that drive absolute task progress. Extensive experiments on representative long-horizon benchmarks-WebShop, ALFWorld, and AppWorld-demonstrate that G2PO substantially outperforms state-of-the-art prompt-based and RL baselines, achieving remarkable success rate improvements of up to 22.2% over GRPO.

Yunan Wang, Minghui Song, Zihan Zhang +6

1Peking University · 2Microsoft Corporation

Agentic RL Reinforcement Learning Group Relative Policy Optimization Sparse-Reward RL Long-Horizon Agent Tasks

Jun 18, 2026cs.AI

Automating SKILL.md Generation for Computer-Using Agents via Interaction Trajectory Mining

Explicit skill libraries make computer-using agents easier to inspect, but it remains unclear whether such libraries can be mined from interaction data in a way that improves downstream policies. We study this question through a three-stage pipeline that segments GUI trajectories, clusters segments into candidate skills, and trains a skill-aware policy from the resulting annotations. The mined clusters are readable on the source benchmark: five of eight clusters have at least 0.95 purity against InteraSkill Workflows labels. However, readability does not imply transfer. GRPO improves IW skill-step accuracy only from 18.5% to 20.5%, leaves BrowseComp+ essentially unchanged, and underperforms trivial frequency priors on key source-domain metrics. We therefore present the method as a diagnostic study: trajectory mining can expose inspectable skill structure, but the current boundary detector, orderless segment representation, and offline reward model are insufficient for reliable cross-domain policy improvement.

Yuexing Hao, Xiaomin Li

Massachusetts Institute of Technology · Harvard University

Agentic RL Computer-Use Agents LLM Agent Skill Retrieval Agent Skill Learning

Jun 16, 2026cs.AI

StepGuard: Guarding Web Navigation via Single-Step Calibration

Web navigation requires agents to follow natural language goals, interact with web pages, and produce accurate answers. While recent advances leverage vision-language models and reinforcement learning, existing methods still suffer from single-step fragility due to reward misalignment and error propagation. To tackle the reward entanglement, we design Dynamic Dual-Policy Optimization (DDPO), which dynamically switches between a navigation-first mode for exploration and an answer-first mode for question-answering to mitigate reward conflict. To calibrate the single-step error, we propose Confidence-Guided Adaptive Navigation Reflection (CANR), a mechanism that estimates per-step confidence, triggers reflection only when necessary, and uses contrastive rewards to encourage self-correction to calibrate the single-step inaccuracy. With the above as the main components, we finally develop our StepGuard, a new framework of Guarding Web Navigation via Single-Step Calibration. Experiments demonstrate that our approach significantly improves navigation and answer accuracy, setting new state-of-the-art performance on standard web navigation benchmarks.

Zhihao Cui, Yuchen Zhang, Xiyang Sun +6

School of Software Engineering, Xi’an Jiaotong University · Xiamen University · School of Computer Science and Information Engineering, Hefei University of Technology +2

Agentic RL Reinforcement Learning Web Agents

Jun 16, 2026cs.LG

EnvRL: Learn from Environment Dynamics in Agentic Reinforcement Learning

Reinforcement learning (RL) has emerged as a powerful paradigm for training Large Language Models (LLMs) as agents. However, conventional RL methods for long-horizon agentic tasks often struggle with sparse outcome rewards. Intuitively, this overlooks the rich environment dynamics information contained in rollout interaction trajectories. We argue that the interaction experience inherently serves as an implicit supervision signal, reveals the underlying transition mechanisms of the environment, and enables the agent to construct a more accurate internal model of the environment.. Therefore, in this work, we investigate how to leverage this additional signal to improve policy learning. Specifically, we propose EnvRL, a framework that incorporates environment dynamics learning into agentic RL via two auxiliary objectives: state prediction and inverse dynamics. By jointly optimizing with the primary RL objective, we encourage the agent to internalize environment dynamics from its own interaction experience. Extensive experiments on two long-horizon agentic benchmarks demonstrate that EnvRL achieves significant improvements on success-rates over RL-only baselines, e.g., when trained with GRPO, lifting Qwen-2.5-1.5B-Instruct from 72.8% to 77.4% on ALFWorld, and from 56.8% to 67.0% on WebShop.

Zhitong Wang, Songze Li, Hao Peng +4

Department of Computer Science and Technology, Tsinghua University · Shanghai AI Laboratory

Agentic RL World Model Learning Policy Learning RL for LLM Agents

Jun 11, 2026cs.AI

From Verdict to Process: Agentic Reinforcement Learning for Multi-Stage Fact Verification

Recent approaches combining Large Language Models (LLMs) with retrieval-augmented reasoning have shown promise for automated fact verification. To process complex claims, these verification pipelines typically execute multi-stage workflows that coordinate tightly coupled modules, including claim decomposition, evidence gathering, and verdict prediction. However, existing methods optimize individual stages in isolation or rely on fixed heuristics, which limits adaptive coordination among stages and can lead to suboptimal outcomes. In this work, we propose ProFact, an agentic reinforcement learning framework for end-to-end optimization of multi-stage fact verification trajectories. ProFact trains a unified policy to coordinate claim decomposition, evidence seeking, answer generation, and verdict prediction. To address the sparse and delayed supervision provided by final veracity labels, ProFact introduces process-aware rewards that provide stage-level learning signals throughout the verification process. Empirical evaluation shows that ProFact consistently outperforms strong baselines in both verification performance and inference efficiency. These results highlight the effectiveness of process-aware trajectory optimization for multi-stage fact verification.

Rongxin Yang, Shenghong He, Siyuan Zhu +1

School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou 510006, China

Agentic RL Process Reward Models Automated Fact-Checking RL for LLM Agents

Jun 10, 2026cs.LG

APPO: Agentic Procedural Policy Optimization

Recent advances in agentic Reinforcement Learning (RL) have substantially improved the multi-turn tool-use capabilities of large language model agents. However, most existing methods assign credit over coarse heuristic units, such as tool-call boundaries or fixed workflows, making it difficult to identify which intermediate decisions influence downstream outcomes. In this work, we study agentic RL from two perspectives: \textit{where to branch and how to assign credit after branching}. Our pilot analysis shows that influential decision points are broadly distributed throughout the generated sequence rather than concentrated at tool calls, while token entropy alone does not reliably reflect their impact on final outcomes. Motivated by these observations, we propose \textbf{Agentic Procedural Policy Optimization (APPO)}, which shifts branching and credit assignment from coarse interaction units to fine-grained decision points in the sequence. APPO selects branching locations using a Branching Score that combines token uncertainty with policy-induced likelihood gains of subsequent continuations, enabling more targeted exploration while filtering out spurious high-entropy positions. It further introduces procedure-level advantage scaling to better distribute credit across branched rollouts. Experiments on 13 benchmarks show that APPO consistently improves strong agentic RL baselines by nearly 4 points, while keeping efficient tool-calls and maintaining behavior interpretability.

Xucong Wang, Ziyu Ma, Yong Wang +5

University of Science and Technology of China · AMAP, Alibaba Group · Southern University of Science and Technology

Agentic RL Credit Assignment in RL Proximal Policy Optimization Policy Learning RL for Tool Use

Jun 10, 2026cs.RO

UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement Learning

Human-in-the-loop reinforcement learning (HiL-RL) has emerged as an effective paradigm for real-world robotic manipulation, enabling online policy improvement with human guidance. However, current HiL-RL frameworks remain intervention-intensive, relying on frequent human corrections to redirect the policy out of unproductive exploration, which incurs high labor cost and limits real-world scalability. To address this, we propose UniIntervene, an agentic intervention model that detects unproductive exploration and autonomously recovers the policy toward high-value states, taking over the bulk of interventions from human operators. Specifically, UniIntervene first performs future-conditioned action-value estimation, predicting the latent consequence of the current action and evaluating its induced value, which provides a more stable progress signal. Building on this, a temporal value-risk critic aggregates recent value dynamics and triggers intervention when the estimated value exhibits sustained stagnation or degradation. When intervention is required, UniIntervene retrieves a high-value recovery target from a memory of past intervention episodes and produces executable corrective actions through a goal-conditioned recovery policy. In this way, UniIntervene turns intervention from passive human correction into a value-aware recovery process for efficient real-world RL. Extensive experiments on diverse real-world manipulation tasks demonstrate that UniIntervene improves the average success rate by 8.6% while reducing human interventions by 57% relative to state-of-the-art HiL-RL baselines.

Haoyuan Deng, Yitong Gao, Yudong Lin +3

Nanyang Technological University · Beijing University of Posts and Telecommunications

Agentic RL Reinforcement Learning Robotic RL Human-in-the-Loop AI

Jun 10, 2026cs.AI

The Artificial Experimentalist: Discovery and Control of Self-Organizing Phenomena with Autotelic Reinforcement Learning

Existing methods for exploring cellular automata and other complex systems mostly operate in open loop: they set initial conditions, execute a full simulation, and observe the outcome, without intervening during execution. We introduce a closed-loop framework based on autotelic reinforcement learning, in which an agent autonomously samples diverse goals and learns a goal-conditioned policy to intervene in a complex system through minimal, local perturbations. We instantiate this framework on Lenia, a continuous cellular automaton known for life-like self-organizing patterns, in an agentic system we call CARL, and demonstrate three capabilities. First, CARL discovers stable solitons across a wide range of Lenia update rules at a higher rate than heuristic baselines. Second, it learns to steer the movement direction of existing solitons with few interventions, showing that CARL can control self-organizing patterns, not only create them. Third, humans can use trained agents to guide solitons through maze environments in real time by specifying high-level directional commands that the agent translates into low-level interventions. Trained across diverse goals, update rules, and random initial states, the agents acquire policies that generalize zero-shot to various out-of-distribution conditions. These results suggest a path toward artificial experimentalist agents that, autonomously or with human guidance, discover and control emergent phenomena in complex systems.

Marko Cvjetko, Benedikt Hartl, Michael Levin +2

Inria Centre at the University of Bordeaux, Bordeaux, France · Allen Discovery Center at Tufts University, Medford, MA, USA · Wyss Institute for Biologically Inspired Engineering at Harvard University, Boston, MA, USA +1

Agentic RL Reinforcement Learning Cellular Automata Goal-Conditioned RL Autonomous Experimentation

Jun 9, 2026cs.LG

TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning

Reinforcement learning with verifiable rewards (RLVR) is a promising approach for enhancing reasoning and agentic behavior in large language models. However, rollout-intensive policy optimization is often limited by insufficient reward contrast, arising when overly simple or complex prompts generate low-variance feedback and when outcome-only rewards assign the same terminal assessment to every decision in a multi-turn rollout. Past efforts have focused on allocating available rollout resources to promising prompts, yet they only leverage sample informativeness at the prompt level and neglect variation in prefix-level informativeness across turns within the same rollout. This work targets multi-turn agentic RL by modeling each ReAct-style thought-action-observation turn as a semantically distinct node, allowing budget allocation to extend from prompt roots to turn-level prefixes with further continuations, which naturally forms tree-structured rollouts. We introduce Tree Rollout Allocation for Contrastive Exploration (TRACE), a unified rollout allocation framework that enhances reward contrast within a fixed sampling budget. Technically, TRACE allocates rollout budget to both prompt roots and intermediate prefixes that are most likely to yield mixed terminal rewards. A shared generalizable predictor estimates conditional success probability at these anchors from prefix histories to guide this allocation. The resulting adaptive tree structure enriches outcome-only feedback and amplifies the policy-update signal. Empirically, TRACE achieves competitive performance and efficiency gains on typical agentic benchmarks, e.g., improving Qwen3-14B Multi-Hop QA average accuracy by 2.8 points over competitive baselines at equal sampling cost.

Heming Zou, Qi Wang, Yun Qu +9

1Tsinghua University · 2LLM Department, Tencent

Agentic RL Reinforcement Learning with Verifiable Rewards Sample-Efficient RL

Jun 8, 2026cs.LG

Claw-R1: A Step-Level Data Middleware System for Agentic Reinforcement Learning

Agentic reinforcement learning (RL) has become an important post-training paradigm for turning LLMs from static chatbots into interactive agents, giving rise to representative applications such as OpenClaw. Existing work mainly focuses on policy optimization algorithms and training frameworks, but pays less attention to the full data lifecycle of agent-environment interactions, from data production to training consumption. To bridge this gap, we present Claw-R1, an interactive step-level data middleware system for agentic RL. Claw-R1 connects heterogeneous agent runtimes with RL training backends through two core components: a Gateway Server and a Data Pool. The Gateway Server captures multi-turn interaction steps through a unified LLM API entry point, while the Data Pool organizes them into step-level records consisting of prompt IDs, response IDs, rewards and other metadata. In our demo, users can interactively inspect live trajectories, examine the state, action, and reward of each step, curate data by quality and readiness, and configure training-ready batches for different downstream RL algorithms. Overall, Claw-R1 treats agent interaction traces as managed data assets rather than temporary runtime logs. Through this demonstration, we hope to encourage the community to recognize the importance of data management in agentic RL. Our code is available at https://github.com/AgentR1/Claw-R1 and the demonstration video can be found at link https://youtu.be/Pw47dAOw6B0.

Daoyu Wang, Mingyue Cheng, Qingchuan Li +3

State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China Hefei, China

Agentic RL Reinforcement Learning LLM Agent Training

Jun 7, 2026cs.RO

HARBOR: A Harness Framework for Agentic Robot Reinforcement Learning

Reinforcement learning (RL) has become a powerful paradigm for robot learning, particularly in sim-to-real settings, but its broader adoption remains limited by the engineering pipeline surrounding the algorithms. Building tasks, shaping rewards, and tuning hyperparameters require substantial expert effort, making RL workflows costly and difficult to scale. We introduce HARBOR, an agentic framework that frames robot RL automation as a harness-engineering problem: given a simulator codebase and a task specification, it automates the workflow from environment setup to policy training in simulation. HARBOR decomposes such high-level objectives into bounded stages executed by specialized agents through standardized commands, persistent artifacts, executable gates, and reusable knowledge, and scales iteration via decentralized parallel trials and experience learning across runs. We evaluate HARBOR across 6 benchmarks and 16 tasks in total, spanning manipulation, locomotion, and bimanual dexterous control. We demonstrate that HARBOR automates the simulation RL workflow end-to-end, designs rewards, tunes algorithms to match or improve over default configurations, and reduces engineering effort at practical token and wall-clock cost; the resulting policies can also be transferred to real robots.

Zechu Li, Yufeng Jin, Xiaoyang Liu +4

TU Darmstadt 1 · Hessian.AI 7 · Honda Research Institute Europe 2 +4

Agentic RL Reinforcement Learning Robotics Simulation Robotic RL

Jun 3, 2026cs.AI

AgentJet: A Flexible Swarm Training Framework for Agentic Reinforcement Learning

We present AgentJet, a distributed swarm training framework for large language model (LLM) agent reinforcement learning. Unlike centralized frameworks that tightly couple agent rollouts with model optimization, AgentJet adopts a decoupled multi-node architecture in which swarm server nodes host trainable models and run optimization on GPU clusters, whereas swarm client nodes execute arbitrary agents on arbitrary devices. This design provides capabilities that are difficult to support in centralized frameworks: (1) heterogeneous multi-model reinforcement learning, enabling the training of heterogeneous multi-agent teams with multiple LLM as brains; (2) multi-task cocktail training with isolated agent runtimes; (3) fault-tolerant execution that prevents external environment failures from interrupting the training process; and (4) live code iteration, which allows agents to be edited during training by replacing swarm client nodes. To support efficient RL in multi-model, multi-turn, and multi-agent settings, AgentJet introduces a context tracking module with timeline merging, which consolidates redundant context and achieves a 1.5-10x training speedup. Finally, AgentJet introduces an automated research system that takes a research topic as input and autonomously conducts long-horizon, multi-day RL studies on large-scale clusters. By leveraging the swarm architecture, this system reproduces key exploratory workflows of RL researchers without human intervention during execution.

Qingxu Fu, Boyin Liu, Shuchang Tao +2

Tongyi Lab, Alibaba Group

Multi-Agent LLM Systems Agentic RL Reinforcement Learning Distributed RL LLM Agent Training

Jun 2, 2026cs.RO

AgenticRL: Self-Refining Agentic Reinforcement Learning for Vision-Conditioned UAV Navigation

Deep reinforcement learning has shown strong potential for enabling autonomous robots to learn complex navigational tasks. However, its practical use still depends heavily on human designed reward functions and repeated manual fine tuning, which is time consuming and does not guarantee high success in the desired task. This paper presents AgenticRL, agent guided reinforcement learning framework that increases autonomy in reward design, policy refinement, and real world deployment for unmanned aerial vehicles (UAV) navigation tasks. AgenticRL uses a multimodal generative pre-trained transformer (GPT) agent to interpret task information and visual scene observations, generate task specific reward functions, train policies using Proximal Policy Optimization (PPO) algorithm, and then act as a critic by evaluating the trained policy through diagnosis packets to generate feedback. Based on this feedback, the agent identifies failure modes and refines the reward function in a closed loop self improvement process. To further leverage the multimodal GPT agent during inference, AgenticRL uses real world images and natural language task information to automatically identify the active scenario and select the appropriate trained policy for execution. The framework is evaluated on multiple navigational tasks, including gate traversal, obstacle avoidance, wall barrier crossing with landing, trajectory following, and motion behavior learning. Experimental results show that the closed loop refinement process improves policy behavior compared with initial rewards by 71%. We also demonstrate sim-to-real transfer of the proposed framework, achieving a real world success rate of 91% and a sim-to-real accuracy of 94%.

Roohan Ahmed Khan, Yasheerah Yaqoot, Amir Atef Habel +2

RL for Robotics Agentic RL UAV Navigation LLM-Guided RL

Jun 2, 2026cs.AI

EvoDS: Self-Evolving Autonomous Data Science Agent with Skill Learning and Context Management

Recent progress in Large Language Model (LLM) agents has enabled promising advances in automated data science. However, existing approaches remain fundamentally limited by their static action sets and lack of principled long-horizon context management, hindering their ability to accumulate reusable experience across tasks and operate reliably in multi-stage, iterative data science pipelines. To address these challenges, we introduce EvoDS, a self-evolving autonomous data science agent that learns to expand its skills and adaptively managing long-term context through agentic reinforcement learning. Specifically, EvoDS introduces two key strategies: (1) Autonomous Skill Acquisition (ASA) mechanism, which enables agents to synthesize, validate, and reuse executable skills; and (2) Adaptive Context Compression (ACC) strategy, which treats context management as a learned control problem rather than passive truncation. These strategies are orchestrated within a two-stage multi-agent training scheme, enabling EvoDS to autonomously improve over time. Theoretically, we prove that EvoDS's hierarchical design reduces tool-selection error, and its optimization objective aligns with an information bottleneck principle, ensuring efficient context use. Empirically, EvoDS outperforms state-of-the-art open-source data science agents by an average of 28.9% across four diverse benchmarks while eliminating out-of-token failures. Our code and data are available at https://github.com/usail-hkust/EvoDS.

Zherui Yang, Fan Liu, Yansong Ning +1

The Hong Kong University of Science and Technology (Guangzhou)

Agentic RL LLM Agent Skill Learning LLM Context Management Self-Evolving Agents

Jun 2, 2026cs.LG

Tool-Aware Optimization with Entropy Guidance for Efficient Agentic Reinforcement Learning

Agentic reinforcement learning (RL) equips large language models (LLMs) with tool-use capabilities that substantially improve reasoning on complex tasks. However, integrating external tools often destabilizes training: over-reliance on tools can induce input distribution shift, while overly conservative tool use limits effective exploration. To address this issue, we propose a unified framework TAO-RL that couples tool-aware trajectory filtering with entropy-guided exploration for efficient policy optimization. Specifically, at the data level, TAO-RL filters rollout trajectories along two criteria: discarding those where all tool invocations fail to execute, and removing those where all rollouts are either correct or incorrect, as both cases yield degenerate advantage estimates that contribute no discriminative learning signal. This joint filtering retains data that are both tool-capable and informative, establishing a high-quality training distribution. At the algorithmic level, we introduce a tool-aware entropy-guided bonus that reshapes the advantage function at post-tool-call tokens, encouraging the policy to explore more diverse reasoning paths at critical decision points. These two components are mutually reinforcing: trajectory filtering establishes a clean and informative training foundation, while entropy-guided exploration drives stronger reasoning behaviors at critical tool-interaction junctures. Extensive experiments on 7 challenging reasoning benchmarks across 3 model scales demonstrate the superiority of TAO-RL over existing methods.

Hongye Cao, Nuo Yan, Haoyuan Deng +5

National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210093, China · Nanyang Technological University, Singapore · China Mobile NineVerse Artificial Intelligence Technology (Beijing) Co., Ltd., and Institute of Artificial Intelligence, NineVerse, Beijing 100032, China

Agentic RL RL for Language Model Reasoning RL Exploration RL for Tool Use

Jun 2, 2026cs.AI

EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning

Autonomous LLM training is often framed as recipe search, which leaves the training harness largely static. This limitation sharpens in agentic RL, where shifting bottlenecks and scalar rewards mask diverse failure modes. We introduce EvoTrainer, an autonomous training framework that co-evolves LLM policies and training-side harnesses through empirical feedback: it diagnoses rollout-level evidence, revises diagnostics, backtests interventions, and accumulates reusable skills. Evaluated on mathematical reasoning, competitive-programming code generation, and repository-level software engineering, EvoTrainer matches or exceeds the human-engineered RL references under the same data, codebase, and evaluation protocol, with the largest gain on long-horizon agentic SWE. Trajectory analyses show that retained strategies diverge across domains, evolving diagnostics prevent invalid high-scoring branches from being promoted, and reusable skills shape later search. Autonomous LLM RL should move beyond recipe search toward joint evolution of policies and the training harnesses that interpret them.

Guhong Chen, Yingcheng Shi, Yongbin Li +6

1Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences · 2Tongyi Lab , Alibaba Group · 3Alibaba Group +1

RL for Code Generation Agentic RL Reinforcement Learning Agent Harness Optimization LLM Agent Skill Learning LLM Agent Training+1