Agentic RL

RL: Reinforcement Learning

Follow this topic Ask about this topic

Agentic reinforcement learning studies how language and multimodal models can learn to act over multiple steps in environments, using tools, memory, and feedback to complete tasks. Common approaches extend policy-gradient methods such as PPO and GRPO with process rewards, step-level credit assignment, exploration strategies, and skill or experience reuse; some also use teacher guidance or learned world models. Training and evaluation span simulated and executable tool environments, web and coding tasks, embodied control, and real-world workflows, with systems work addressing the cost of generating long interaction trajectories. A central challenge is balancing sparse or imperfect outcome signals against fine-grained supervision while keeping learning stable, efficient, and robust beyond the training environment.

Latest papers

232 papers63 papers in the last four weeks, up 294% on the four weeks before. 0.4% of all new papers.

Mar 5, 2026

Scaling Agentic Capabilities, Not Context: Efficient Reinforcement Finetuning for Large Toolspaces

Agentic systems operating over large tool ecosystems must plan and execute long-horizon workflows under weak or non-verifiable supervision. While frontier models mitigate these challenges through scale and large context budgets, small language models (SLMs) remain brittle: eager tool loading saturates context, execution errors compound over time, and sparse rewards limit learning. We introduce ATLAS, a reinforcement finetuning framework that enables SLMs to operate effectively in large-scale toolspace environments by learning how to acquire context and how to execute actions. Our approach makes two key contributions. First, we treat context control and execution structure as learnable decisions, combining iterative tool loading with programmatic tool orchestration to bound context growth and stabilize long-horizon trajectories. Second, we propose rubric-based reinforcement finetuning, which decomposes task success into structured, task-aligned criteria and enables scalable training using small judge models. Across MCP benchmarks, these design choices yield large and consistent gains over generic RL baselines, allowing a 4B SLM to approach frontier-agent performance under far tighter parameter and context budgets.

Karan Gupta, Pranav Vajreshwari, Yash Pandya +3

Microsoft Research

RL for Tool Use Agentic RL RL Fine-Tuning LLM Context Management Rubric-Based RL

Mar 3, 2026

RAPO: Expanding Exploration for LLM Agents via Retrieval-Augmented Policy Optimization

Agentic Reinforcement Learning (Agentic RL) has shown remarkable potential in large language model-based (LLM) agents. These works can empower LLM agents to tackle complex tasks via multi-step, tool-integrated reasoning. However, an inherent limitation of existing Agentic RL methods is their reliance on a pure on-policy paradigm for exploration, restricting exploration to the agent's self-generated outputs and preventing the discovery of new reasoning perspectives for further improvement. While recent efforts incorporate auxiliary off-policy signals to enhance exploration, they typically utilize full off-policy trajectories for trajectory-level policy estimation, overlooking the necessity for the fine-grained, step-level exploratory dynamics within agentic rollout. In this paper, we revisit exploration in Agentic RL and propose Retrieval-Augmented Policy Optimization (RAPO), a novel RL framework that introduces retrieval to explicitly expand exploration during training. To achieve this, we decompose the Agentic RL training process into two phases: (i) Hybrid-policy Agentic Rollout, and (ii) Retrieval-aware Policy Optimization. Specifically, we propose a Hybrid-policy Agentic Rollout strategy, which allows the agents to continuously reason over the retrieved off-policy step-level traces. It dynamically extends the reasoning receptive field of agents, enabling broader exploration conditioned on external behaviors. Subsequently, we introduce the Retrieval-aware Policy Optimization mechanism, which calibrates the policy gradient estimation with retrieval reward and importance shaping, stabilizing training and prioritizing retrieval-illuminating exploration. Extensive experiments show that RAPO achieves an +5.0% average gain on fourteen datasets across three agentic reasoning tasks, while delivering 1.2x faster training efficiency.

Siwei Zhang, Yun Xiong, Xi Chen +4

Fudan University · Zhejiang University · UC Davis

Agentic RL RL for Language Model Reasoning RL Exploration Policy Learning Off-Policy RL

Mar 2, 2026

Selection as Power: Constrained Reinforcement for Bounded Decision Authority

Selection as Power argued that upstream selection authority, rather than internal objective misalignment, constitutes a primary source of risk in high-stakes agentic systems. However, the original framework was static: governance constraints bounded selection power but did not adapt over time. In this work, we extend the framework to dynamic settings by introducing incentivized selection governance, where reinforcement updates are applied to scoring and reducer parameters under externally enforced sovereignty constraints. We formalize selection as a constrained reinforcement process in which parameter updates are projected onto governance-defined feasible sets, preventing concentration beyond prescribed bounds. Across multiple regulated financial scenarios, unconstrained reinforcement consistently collapses into deterministic dominance under repeated feedback, especially at higher learning rates. In contrast, incentivized governance enables adaptive improvement while maintaining bounded selection concentration. Projection-based constraints transform reinforcement from irreversible lock-in into controlled adaptation, with governance debt quantifying the tension between optimization pressure and authority bounds. These results demonstrate that learning dynamics can coexist with structural diversity when sovereignty constraints are enforced at every update step, offering a principled approach to integrating reinforcement into high-stakes agentic systems without surrendering bounded selection authority.

Jose Manuel de la Chica Rodriguez, Juan Manuel Vera Díaz

AI Lab, Grupo Santander Madrid, Spain

AI Agent Governance Constrained RL Agentic RL

Mar 2, 2026

Federated Agentic AI for Wireless Networks: Fundamentals, Approaches, and Applications

Agentic artificial intelligence (AI) presents a promising pathway toward realizing autonomous and self-improving wireless network services. However, resource-constrained, widely distributed, and data-heterogeneous nature of wireless networks poses significant challenges to existing agentic AI that relies on centralized architectures, leading to high communication overhead, privacy risks, and non-independent and identically distributed (non-IID) data. Federated learning (FL) has the potential to improve the overall loop of agentic AI through collaborative local learning and parameter sharing without exchanging raw data. This paper proposes new federated agentic AI approaches for wireless networks. We first summarize fundamentals of agentic AI and mainstream FL types. Then, we illustrate how each FL type can strengthen a specific component of agentic AI's loop. Moreover, we conduct a case study on using FRL to improve the performance of agentic AI's action decision in low-altitude wireless networks (LAWNs). Finally, we provide a conclusion and discuss future research directions.

Lingyi Cai, Yu Zhang, Ruichen Zhang +5

Research Center of 6G Mobile Communications, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, 430074, China · College of Computing and Data Science, Nanyang Technological University, Singapore · School of Engineering, Edith Cowan University, Perth, WA 6027, and the School of Computer Science and Engineering, University of New South Wales (UNSW), Sydney, NSW 2033, Australia +2

Wireless Communications Agentic RL Federated RL

Mar 1, 2026

HiMAC: Hierarchical Macro-Micro Learning for Long-Horizon LLM Agents

Large language model (LLM) agents have recently demonstrated strong capabilities in interactive decision-making, yet they remain fundamentally limited in long-horizon tasks that require structured planning and reliable execution. Existing approaches predominantly rely on flat autoregressive policies, where high-level reasoning and low-level actions are generated within a single token sequence, leading to inefficient exploration and severe error propagation over extended trajectories. In this work, we propose HiMAC, a hierarchical agentic RL framework that explicitly decomposes long-horizon decision-making into macro-level planning and micro-level execution. HiMAC models reasoning as a structured blueprint generation process followed by goal-conditioned action execution, enabling robust long-horizon planning within LLM-based agents. To train this hierarchy efficiently, we introduce a critic-free hierarchical policy optimization paradigm that extends group-based reinforcement learning to bi-level structures through hierarchical relative advantage estimation. Furthermore, we propose an iterative co-evolution training strategy that alternates between planner exploration and executor adaptation, mitigating the non-stationarity inherent in hierarchical learning. Extensive experiments on ALFWorld, WebShop, and Sokoban demonstrate that HiMAC consistently outperforms strong prompting and reinforcement learning baselines, achieving state-of-the-art performance and substantially improved sample efficiency across both text-based and visually grounded environments. Our results show that introducing structured hierarchy, rather than increasing model scale alone, is a key factor for enabling robust long-horizon agentic intelligence.

Hongbo Jin, Rongpeng Zhu, Jiayu Ding +2

School of Electronic and Computer Engineering, Peking University

Long-Horizon LLM Agents Long-Horizon Agent Tasks Agentic RL RL for LLM Agents Long-Horizon RL Hierarchical RL

Feb 28, 2026

RLAR: An Agentic Reward System for Multi-task Reinforcement Learning on Large Language Models

Large language model alignment via reinforcement learning depends critically on reward function quality. However, static, domain-specific reward models are often costly to train and exhibit poor generalization in out-of-distribution scenarios encountered during RL iterations. We present RLAR (Reinforcement Learning from Agent Rewards), an agent-driven framework that dynamically assigns tailored reward functions to individual queries. Specifically, RLAR transforms reward acquisition into a dynamic tool synthesis and invocation task. It leverages LLM agents to autonomously retrieve optimal reward models from the Internet and synthesize programmatic verifiers through code generation. This allows the reward system to self-evolve with the shifting data distributions during training. Experimental results demonstrate that RLAR yields consistent performance gains ranging from 10 to 60 across mathematics, coding, translation, and dialogue tasks. On RewardBench-V2, RLAR significantly outperforms static baselines and approaches the performance upper bound, demonstrating superior generalization through dynamic reward orchestration. The data and code are available on this link: https://github.com/ZhuoerFeng/RLAR.

Andrew Zhuoer Feng, Cunxiang Wang, Bosi Wen +4

Tsinghua Univeristy · Peking University

RL for Language Models Reward Design for RL Reward Modeling Reinforcement Learning with Verifiable Rewards Multi-Task RL Agentic RL

Feb 27, 2026

CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation

GPU kernel optimization is fundamental to modern deep learning but remains a highly specialized task requiring deep hardware expertise. Despite strong performance in general programming, large language models (LLMs) remain uncompetitive with compiler-based systems such as torch.compile for CUDA kernel generation. Existing CUDA code generation approaches either rely on training-free refinement or fine-tune models within fixed multi-turn execution-feedback loops, but both paradigms fail to fundamentally improve the model's intrinsic CUDA optimization ability, resulting in limited performance gains. We present CUDA Agent, a large-scale agentic reinforcement learning system that develops CUDA kernel expertise through three components: a scalable data synthesis pipeline, a skill-augmented CUDA development environment with automated verification and profiling to provide reliable reward signals, and reinforcement learning algorithmic techniques enabling stable training. CUDA Agent achieves state-of-the-art results on KernelBench, delivering 100%, 100%, and 92% faster rate over torch.compile on KernelBench Level-1, Level-2, and Level-3 splits, outperforming the strongest proprietary models such as Claude Opus 4.5 and Gemini 3 Pro by about 40% on the hardest Level-3 setting.

Weinan Dai, Hanlin Wu, Qiying Yu +13

ByteDance Seed · Institute for AI Industry Research (AIR), Tsinghua University · SIA-Lab of Tsinghua AIR and ByteDance Seed

GPU Kernel Generation GPU Kernel Optimization RL for Code Generation Agentic RL

Feb 26, 2026

Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks

Group-based reinforcement learning (RL), such as GRPO, has advanced the capabilities of large language models on long-horizon agentic tasks. To enable more fine-grained policy updates, recent research has increasingly shifted toward stepwise group-based policy optimization, which treats each step in a rollout trajectory independently while using a memory module to retain historical context. However, we find a key issue in estimating stepwise relative advantages, namely context inconsistency, where steps within the same group may differ in their historical contexts. Empirically, we reveal that this issue can lead to severely biased advantage estimation, thereby degrading policy optimization significantly. To address the issue, in this paper, we propose Hierarchy-of-Groups Policy Optimization (HGPO) for long-horizon agentic tasks. Specifically, within a group of rollout trajectories, HGPO assigns each step to multiple hierarchical groups according to the consistency of historical contexts. Then, for each step, HGPO computes distinct advantages within each group and aggregates them with an adaptive weighting scheme. In this way, HGPO can achieve a favorable bias-variance trade-off in stepwise advantage estimation, without extra models or rollouts. Evaluations on two challenging agentic tasks, ALFWorld and WebShop with Qwen2.5-1.5B-Instruct and Qwen2.5-7B-Instruct, show that HGPO significantly outperforms existing agentic RL methods under the same computational constraints. Code is available at https://github.com/langfengQ/verl-agent/tree/master/recipe/hgpo.

Shuo He, Lang Feng, Qi Wei +3

Nanyang Technological University · Southeast University

Agentic RL RL for LLM Agents Group Relative Policy Optimization Long-Horizon Agent Tasks

Feb 25, 2026

ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning

Agentic reinforcement learning (ARL) has rapidly gained attention as a promising paradigm for training agents to solve complex, multi-step interactive tasks. Despite encouraging early results, ARL remains highly unstable, often leading to training collapse. This instability limits scalability to larger environments and longer interaction horizons, and constrains systematic exploration of algorithmic design choices. In this paper, we first propose ARLArena, a stable training recipe and systematic analysis framework that examines training stability in a controlled and reproducible setting. ARLArena first constructs a clean and standardized testbed. Then, we decompose policy gradient into four core design dimensions and assess the performance and stability of each dimension. Through this fine-grained analysis, we distill a unified perspective on ARL and propose SAMPO, a stable agentic policy optimization method designed to mitigate the dominant sources of instability in ARL. Empirically, SAMPO achieves consistently stable training and strong performance across diverse agentic tasks. Overall, this study provides a unifying policy gradient perspective for ARL and offers practical guidance for building stable and reproducible LLM-based agent training pipelines.

Xiaoxuan Wang, Han Zhang, Haixin Wang +11

Department of Computer Science, University of California, Los Angeles, California, USA · University of Wisconsin–Madison, Madison, Wisconsin, USA

Agentic RL Reinforcement Learning Policy Gradient Methods LLM Agent Training Policy Learning RL Stability

Feb 24, 2026

PyVision-RL: Forging Open Agentic Vision Models via RL

Reinforcement learning for agentic multimodal models often suffers from interaction collapse, where models learn to reduce tool usage and multi-turn reasoning, limiting the benefits of agentic behavior. We introduce PyVision-RL, a reinforcement learning framework for open-weight multimodal models that stabilizes training and sustains interaction. Our approach combines an oversampling-filtering-ranking rollout strategy with an accumulative tool reward to prevent collapse and encourage multi-turn tool use. Using a unified training pipeline, we develop PyVision-Image and PyVision-Video for image and video understanding. For video reasoning, PyVision-Video employs on-demand context construction, selectively sampling task-relevant frames during reasoning to significantly reduce visual token usage. Experiments show strong performance and improved efficiency, demonstrating that sustained interaction and on-demand visual processing are critical for scalable multimodal agents.

Shitian Zhao, Shaoheng Lin, Ming Li +4

Shanghai AI Lab · UMD · CUHK +3

Adaptive Video Frame Sampling Multimodal Agents RL for VLMs Agentic RL Video Reasoning

Feb 19, 2026

Phase-Aware Mixture of Experts for Agentic Reinforcement Learning

Reinforcement learning (RL) has equipped LLM agents with a strong ability to solve complex tasks. However, existing RL methods normally use a single policy network, causing simplicity bias where simple tasks occupy most parameters and dominate gradient updates, leaving insufficient capacity for complex tasks. A plausible remedy could be employing the Mixture-of-Experts (MoE) architecture in the policy network, as MoE allows different parameters (experts) to specialize in different tasks, preventing simple tasks from dominating all parameters. However, a key limitation of traditional MoE is its token-level routing, where the router assigns each token to specialized experts, which fragments phase-consistent patterns into scattered expert assignments and thus undermines expert specialization. In this paper, we propose Phase-Aware Mixture of Experts (PA-MoE). It first features a lightweight phase router that learns latent phase boundaries directly from the RL objective without pre-defining phase categories. Then, the phase router allocates temporally consistent assignments to the same expert, allowing experts to preserve phase-specific expertise. Experimental results demonstrate the effectiveness of our proposed PA-MoE.

Shengtian Yang, Yu Li, Shuo He +4

School of Computer Science and Engineering, Southeast University, Nanjing, China · Kuaishou Technology, Beijing, China · College of Computing and Data Science, Nanyang Technological University, Singapore

Reinforcement Learning RL for LLM Agents Mixture-of-Experts Models Agentic RL Expert Routing

Feb 18, 2026

LLM4Cov: Execution-Aware Agentic Learning for High-coverage Testbench Generation

Execution-aware LLM agents offer a promising paradigm for learning from tool feedback, but such feedback can be expensive and slow to obtain, making online reinforcement learning (RL) less practical in certain scenarios. High-coverage hardware verification exemplifies this challenge due to its reliance on industrial simulators and non-differentiable execution signals. We propose LLM4Cov, an offline agent-learning framework that models verification as single-step state transitions guided by deterministic evaluators. Building on this formulation, we introduce execution-validated data curation, policy-aware agentic data synthesis, and worst-state-prioritized sampling to enable scalable learning under execution constraints. We further curate a reality-aligned benchmark adapted from an existing verification suite through a revised evaluation protocol. Using the proposed pipeline, a compact 4B-parameter model achieves 69.2% pass rate and 90.4% average coverage in CVDP-ECov under agentic evaluation, outperforming its teacher by 5.3% and 10.5%, demonstrating competitive performance against models an order of magnitude larger.

Hejia Zhang, Zhongming Yu, Chia-Tung Ho +3

University of California San Diego, USA · NVIDIA · Agentrys

LLM Agent Training Automated Test Generation Agentic RL

Feb 17, 2026

GLM-5: from Vibe Coding to Agentic Engineering

We present GLM-5, a next-generation foundation model designed to transition the paradigm of vibe coding to agentic engineering. Building upon the agentic, reasoning, and coding (ARC) capabilities of its predecessor, GLM-5 adopts DSA to significantly reduce training and inference costs while maintaining long-context fidelity. To advance model alignment and autonomy, we implement a new asynchronous reinforcement learning infrastructure that drastically improves post-training efficiency by decoupling generation from training. Furthermore, we propose novel asynchronous agent RL algorithms that further improve RL quality, enabling the model to learn from complex, long-horizon interactions more effectively. Through these innovations, GLM-5 achieves state-of-the-art performance on major open benchmarks. Most critically, GLM-5 demonstrates unprecedented capability in real-world coding tasks, surpassing previous baselines in handling end-to-end software engineering challenges. Code, models, and more information are available at https://github.com/zai-org/GLM-5.

GLM-5-Team, :, Aohan Zeng +184

LLM Agent Training Agentic RL RL for Code Generation

Feb 12, 2026

Learning to Configure Agentic AI Systems

Configuring LLM-based agent systems involves choosing workflows, tools, token budgets, and prompts from a large combinatorial design space, and is typically handled today by fixed templates or hand-tuned heuristics that apply the same configuration regardless of query difficulty, leading to brittle behavior and wasted compute. To address this, we formulate agent configuration as a semi-Markov decision process (SMDP) where each configuration acts as a temporally extended option that determines how an agent system processes a query, and introduce introduce ARC (Agentic Resource & Configuration learner), a lightweight hierarchical policy that dynamically selects query-specific agent configurations. Across reasoning, tool-use, and agentic benchmarks, ARC consistently improves over budget-matched tool-augmented LLMs, increasing average reasoning accuracy by 31.3%, tool-use accuracy by 13.95%, and doubling τ-Bench (Airline) Pass^1 success from 9.0% to 18.0%. These results demonstrate that learning per-query agent configurations is a powerful alternative to "one size fits all" designs.

Aditya Taparia, Som Sagar, Ransalu Senanayake

School of Computing and Augmented Intelligence Arizona State University Tempe, AZ, USA

LLM Agent Workflow Optimization Agentic RL

Feb 11, 2026

Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization

Proactive large language model (LLM) agents aim to actively plan, query, and interact over multiple turns, enabling efficient task completion beyond passive instruction following and making them essential for real-world, user-centric applications. Agentic reinforcement learning (RL) has recently emerged as a promising solution for training such agents in multi-turn settings, allowing them to learn long-horizon decision-making strategies. However, existing pipelines face a critical challenge in balancing task performance with user engagement, as passive agents cannot efficiently adapt to users' intentions while overuse of human feedback increases the burden on users, which forms a Pareto Frontier between these two objectives. To push forward this frontier, we propose Behavior Agentic Optimization (BAO), an agentic RL framework that enhances and regularizes inter-turn behaviors to improve information-gathering capabilities and suppress inefficient or redundant interactions with users. We evaluate BAO on multiple tasks from the UserRL benchmark suite and demonstrate that it substantially outperforms proactive agentic RL baselines in terms of both higher task performance and lower user efforts, while achieving comparable or even superior performance to commercial LLM agents, highlighting its effectiveness for training proactive, user-centric LLM agents in complex multi-turn scenarios. Our website: https://proactive-agentic-rl.github.io/.

Yihang Yao, Zhepeng Cen, Haohong Lin +6

Carnegie Mellon University · Salesforce AI Research · Massachusetts Institute of Technology +2

Agentic RL LLM Agents Long-Horizon LLM Agents

Jan 21, 2026

CLEANER: Self-Purified Trajectories Boost Agentic Reinforcement Learning

Agentic Reinforcement Learning (RL) has empowered Large Language Models (LLMs) to utilize tools like Python interpreters for complex problem-solving. However, for parameter-constrained models (e.g., 4B--7B), the exploration phase is often plagued by frequent execution failures, creating noisy trajectories that hinder policy optimization. Under standard outcome-based reward settings, this noise leads to a critical credit assignment issue, where erroneous actions are inadvertently reinforced alongside successful outcomes. Existing mitigations face a dilemma: dense rewards often trigger reward hacking, while supersampling incurs prohibitive computational costs. To address these challenges, we propose CLEANER. Distinct from external filtering methods, CLEANER exploits the model's intrinsic self-correction capabilities to eliminate error-contaminated context directly during data collection. At its core, the Similarity-Aware Adaptive Rollback (SAAR) mechanism autonomously constructs clean, purified trajectories by retrospectively replacing failures with successful self-corrections. Based on semantic similarity, SAAR adaptively regulates replacement granularity from shallow execution repairs to deep reasoning substitutions. By training on these self-purified paths, the model internalizes correct reasoning patterns rather than error-recovery loops. Empirical results on AIME24/25, GPQA, and LiveCodeBench show average accuracy gains of 6%, 3%, and 5% over baselines. Notably, CLEANER matches state-of-the-art performance using only one-third of the training steps, highlighting trajectory purification as a scalable solution for efficient agentic RL. Our models and code are available at GitHub

Tianshi Xu, Yuteng Chen, Meng Li

Peking University · NTU, Singapore

Agentic RL Reinforcement Learning RL for Language Model Reasoning Sample-Efficient RL RL for LLM Agents

Jan 15, 2026

PaperScout: An Autonomous Agent for Academic Paper Search with Process-Aware Sequence-Level Policy Optimization

Academic paper search is a fundamental task in scientific research, yet most existing approaches organize retrieval around predefined workflows or structured interaction protocols that struggle with complex, conditional queries. To address this limitation, we propose PaperScout, an autonomous agent that reformulates paper search as a sequential decision-making process. Unlike static workflows, PaperScout dynamically decides whether, when, and how to invoke search and expand tools based on accumulated retrieval context. However, training such agents presents a fundamental challenge: standard reinforcement learning methods, typically designed for single-turn tasks, suffer from a granularity mismatch when applied to multi-turn agentic tasks, where token-level optimization diverges from the granularity of sequence-level interactions, leading to noisy credit assignment and unstable training dynamics. We introduce Proximal Sequence Policy Optimization (PSPO), a process-aware, sequence-level policy optimization method that aligns optimization with agent--environment interaction. Comprehensive experiments on both synthetic and real-world benchmarks demonstrate that PaperScout significantly outperforms strong structured retrieval and RL baselines in both recall and relevance, validating the effectiveness of our adaptive agentic framework and optimization strategy.

Tingyue Pan, Jie Ouyang, Mingyue Cheng +7

State Key Lab of Cognitive Intelligence, University of Science and Technology of China

Agentic RL Policy Optimization Information Retrieval Autonomous Research Agents RL for Tool Use

Jan 12, 2026

OpenTinker: Separating Concerns in Agentic Reinforcement Learning

We introduce OpenTinker, an open infrastructure for training large language model (LLM) agents with many LoRA-backed policies over shared execution resources. Modern agent workloads mix supervised fine-tuning (SFT), online reinforcement learning (RL), rollout generation, validation, and multi-turn environment interaction. In such workloads, LoRA adapters are not static inference artifacts: they are frequently updated policy states whose optimizer state, rollout snapshot, and training data attribution must remain consistent. OpenTinker centers the runtime around this policy lifecycle. Users define environments, agents, and learning objectives, while the system manages training clients, rollout samplers, checkpoint handles, and policy-version refresh. The same data path supports SFT and RL by converting trajectories into token sequences with explicit masks: context and environment observations condition the model, while generated action tokens carry supervised weights or RL advantages. This design enables multi-LoRA SFT/RL training in which many users, tasks, or agents can share a base model while keeping adapter updates, checkpoints, and rollout snapshots isolated. We describe the system architecture, the adapter lifecycle, the service-backed snapshot handoff used by the current implementation, the backend contract for mixed-adapter rollout kernels, and the training scheduler that isolates adapter-local gradients and optimizer state. Representative validation tasks exercise single-turn, multi-turn, LoRA, and multi-agent agentic training.

Siqi Zhu, Jiaxuan You

University of Illinois Urbana-Champaign

Agentic RL LLM Agent Training RL Fine-Tuning

Oct 13, 2025

LLM-Empowered Agentic MAC Protocols: A Dynamic Stackelberg Game Approach

Medium Access Control (MAC) protocols, essential for wireless networks, are typically manually configured. While deep reinforcement learning (DRL)-based protocols enhance task-specified network performance, they suffer from poor generalizability and resilience, demanding costly retraining to adapt to dynamic environments. To overcome this limitation, we introduce a game-theoretic LLM-empowered multi-agent DRL (MARL) framework, in which the uplink transmission between a base station and a varying number of user equipments is modeled as a dynamic multi-follower Stackelberg game (MFSG), capturing the network's natural hierarchical structure. Within this game, LLM-driven agents, coordinated through proximal policy optimization (PPO), synthesize adaptive, semantic MAC protocols in response to network dynamics. Protocol action grammar (PAG) is employed to ensure the reliability and efficiency of this process. Under this system, we further analyze the existence and convergence behavior in terms of a Stackelberg equilibrium by studying the learning dynamics of LLM-empowered unified policies in response to changing followers. Simulations corroborate that our framework achieves a 77.6% greater throughput and a 65.2% fairness improvement over conventional baselines. Besides, our framework generalizes excellently to a fluctuating number of users without requiring retraining or architectural changes.

Renxuan Tan, Rongpeng Li, Fei Wang +4

College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China · Huawei Technologies Company Ltd., Shanghai 210026, China · Zhejiang Lab as well as Zhejiang University, Hangzhou 310027, China +1

Agentic RL Stackelberg Games Wireless Communications Wireless Resource Allocation Multi-Agent Reinforcement Learning

Sep 26, 2025

DeepTravel: An End-to-End Agentic Reinforcement Learning Framework for Autonomous Travel Planning Agents

Travel planning (TP) agent has recently worked as an emerging building block to interact with external tools/resources for travel itinerary generation, ensuring an enjoyable user experience. Despite its benefits, existing studies rely on hand-craft prompt and fixed agent workflow, hindering more flexible and autonomous TP agents. This paper proposes DeepTravel, an end-to-end agentic reinforcement learning framework for building an autonomous travel planning agent, capable of autonomously planning, executing tools, and reflecting on tool responses to explore, verify, and refine intermediate actions in multi-step reasoning. To achieve this, we first construct a robust travel sandbox by caching transportation, accommodation and POI data, facilitating TP agent training without being constrained by real-world APIs limitations (e.g., inconsistent outputs). Moreover, we develop a hierarchical reward modeling system, where a trajectory-level verifier first checks spatiotemporal feasibility and filters unsatisfied travel itinerary, and then the turn-level verifier further validate itinerary's detail consistency with tool responses, enabling efficient and precise reward service. Finally, we propose the reply-augmented reinforcement learning method that enables TP agent to periodically replay from a failure experience buffer, emerging notable agentic capacity. We deploy the trained TP agent in the DiDi Enterprise Solutions application. A three-month online test shows that it achieves 82% accuracy in travel itinerary generation. Comprehensive offline evaluations further demonstrate that DeepTravel enables small-sized LLMs (e.g., Qwen3-32B) to significantly outperform frontier LLMs (e.g., OpenAI o1/o3 and DeepSeek-R1) and existing TP agent frameworks.

Yansong Ning, Rui Liu, Jun Wang +6

The Hong Kong University of Science and Technology (Guangzhou) · Didichuxing Co. Ltd

Agentic RL Travel Planning LLM Agent Training LLM Agent Planning RL for Tool Use

Jul 20, 2025

AgentFly: Scaling Agentic Reinforcement Learning with Unified Resource System

Methods to build LLM agents have evolved from prompt engineering and supervised finetuning to agentic reinforcement learning (agentic RL). However, agentic RL remains bottlenecked by its surrounding systems: agents must interact with heterogeneous environments, such as sandboxes, model services, and external APIs. Their allocation, reuse, and lifecycle dominate rollout cost and cap the scale at which training becomes practical. In this work, we present AgentFly, an agentic RL framework built with a unified resource layer that treats each of these environments as a distinct, typed resource scheduled through one engine, with per-tool acquisition for multi-turn reuse, asynchronous backpressure, and rollout versus global-scoped lifecycles. AgentFly adopts a four-layer design: (I) agent layer that abstracts the agent, tool, and reward concepts, decomposing agentic RL into defining agents, tools, and reward functions; (II) rollout layer that composes these into agent loops and computes rewards; (III) context layer that organizes rollouts, injects contextual information, and arranges resources; and (IV) a low-level resource layer that performs resource management. We provide a suite of prebuilt tools and environments, demonstrate successful agent training across multiple tasks and models, and report the first controlled cross-framework throughput comparison against agentic RL frameworks.

Renxi Wang, Bilal El Bouardi, Rifo Ahmad Genadi +6

Mohamed bin Zayed University of Artificial Intelligence · University of California, Los Angeles

Agentic RL LLM Agent Training LLM Agent Harnesses

Jun 2, 2025

Agentic Episodic Control

Reinforcement learning (RL) remains fundamentally limited by poor data efficiency and weak generalization. Prior episodic RL methods attempt to alleviate this via external memory modules, yet they suffer from two key limitations: a representation bottleneck caused by shallow encoders, and a retrieval dilemma where episodic memory is accessed indiscriminately. To address these challenges, we propose Agentic Episodic Control (AEC), a novel architecture that integrates large language models (LLMs) into episodic RL. AEC uses an LLM-based semantic augmenter to generate semantic representations from raw observations, and a critical state recognizer to selectively retrieve valuable experiences. This transforms memory usage from passive similarity matching into strategic, context-aware recall. Across five BabyAI-Text environments, AEC achieves 2-6x higher data efficiency than baselines and is the only method to solve complex tasks like UnlockLocal with over 90% success. It further demonstrates strong cross-task and cross-environment generalization, maintaining performance even under distribution shifts. AEC shows that combining LLM-derived priors with reinforcement learning yields more sample-efficient and adaptable agents.

Xidong Yang, Wenhao Li, Junjie Sheng +4

East China Normal University · Tongji University · Shanghai Jiao Tong University +2

Agentic RL Reinforcement Learning LLM-Guided RL Sample-Efficient RL