Pith. sign in

REVIEW 21 cited by

AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2509.08755 v1 pith:HODV7EKF submitted 2025-09-10 cs.LG cs.AIcs.CL

AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning

classification cs.LG cs.AIcs.CL
keywords agentsframeworkagentgym-rldiverseacrossapproachcommunitydeveloping
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Developing autonomous LLM agents capable of making a series of intelligent decisions to solve complex, real-world tasks is a fast-evolving frontier. Like human cognitive development, agents are expected to acquire knowledge and skills through exploration and interaction with the environment. Despite advances, the community still lacks a unified, interactive reinforcement learning (RL) framework that can effectively train such agents from scratch -- without relying on supervised fine-tuning (SFT) -- across diverse and realistic environments. To bridge this gap, we introduce AgentGym-RL, a new framework to train LLM agents for multi-turn interactive decision-making through RL. The framework features a modular and decoupled architecture, ensuring high flexibility and extensibility. It encompasses a wide variety of real-world scenarios, and supports mainstream RL algorithms. Furthermore, we propose ScalingInter-RL, a training approach designed for exploration-exploitation balance and stable RL optimization. In early stages, it emphasizes exploitation by restricting the number of interactions, and gradually shifts towards exploration with larger horizons to encourage diverse problem-solving strategies. In this way, the agent develops more diverse behaviors and is less prone to collapse under long horizons. We perform extensive experiments to validate the stability and effectiveness of both the AgentGym-RL framework and the ScalingInter-RL approach. Our agents match or surpass commercial models on 27 tasks across diverse environments. We offer key insights and will open-source the complete AgentGym-RL framework -- including code and datasets -- to empower the research community in developing the next generation of intelligent agents.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 21 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Entropy Polarity in Reinforcement Fine-Tuning: Direction, Asymmetry, and Control

    cs.LG 2026-05 unverdicted novelty 7.0

    Entropy polarity from a first-order entropy change approximation enables Polarity-Aware Policy Optimization (PAPO) that preserves complementary polarity branches and outperforms baselines on math and agentic RL fine-t...

  2. AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems

    cs.CL 2026-05 unverdicted novelty 7.0

    AgentForesight introduces an online auditor model that predicts decisive errors in multi-agent trajectories at the earliest step using a coarse-to-fine reinforcement learning recipe on a new curated dataset AFTraj-2K.

  3. AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems

    cs.CL 2026-05 unverdicted novelty 7.0

    AgentForesight trains a 7B model to perform online auditing of multi-agent LLM trajectories, detecting early decisive errors and outperforming larger models on custom and external benchmarks.

  4. Weblica: Scalable and Reproducible Training Environments for Visual Web Agents

    cs.AI 2026-05 unverdicted novelty 7.0

    Weblica scales RL training for visual web agents by building thousands of reproducible environments through HTTP caching for stable replays and LLM synthesis from real sites, yielding an 8B model that beats similar op...

  5. Agentic-DPO: From Imitation to Agentic Policy Optimization on Expert Trajectories

    cs.AI 2026-07 accept novelty 6.0

    Offline DPO on expert states with one-step student negatives and schema-preserving augmentation improves LLM agents beyond SFT and can match online GRPO without environment interaction.

  6. SkillGrad: Optimizing Agent Skills Like Gradient Descent

    cs.AI 2026-05 unverdicted novelty 6.0

    SkillGrad applies a gradient-descent-inspired optimization to structured agent skill packages using trajectory-level losses, diagnostic text gradients, momentum accumulation, and LLM-based patching, yielding 6.7 perce...

  7. Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents

    cs.CL 2026-05 unverdicted novelty 6.0

    ReBel uses belief-consistency supervision and belief-aware grouping to improve credit assignment in long-horizon RL for LLM agents, achieving up to 20.4 percentage points higher success and 2.1x better sample efficien...

  8. Resolving Action Bottleneck: Agentic Reinforcement Learning Informed by Token-Level Energy

    cs.LG 2026-05 conditional novelty 6.0

    ActFocus resolves the action bottleneck in agentic RL by reweighting token gradients toward action tokens using observed reward variance and an energy-based uncertainty term, outperforming PPO and GRPO by up to 65 per...

  9. ICRL: Learning to Internalize Self-Critique with Reinforcement Learning

    cs.AI 2026-05 unverdicted novelty 6.0

    ICRL uses joint RL training of solver and critic with distribution-calibration re-weighting and role-wise advantage estimation to internalize critique into unassisted LLM performance, yielding 6.4-point gains on agent...

  10. PriorZero: Bridging Language Priors and World Models for Decision Making

    cs.LG 2026-05 unverdicted novelty 6.0

    PriorZero uses root-only LLM prior injection in MCTS and alternating world-model training with LLM fine-tuning to raise exploration efficiency and final performance on Jericho text games and BabyAI gridworlds.

  11. Entropy Polarity in Reinforcement Fine-Tuning: Direction, Asymmetry, and Control

    cs.LG 2026-05 unverdicted novelty 6.0

    Entropy polarity is a signed token-level quantity derived from a first-order approximation of entropy change that predicts whether RL updates expand or contract policy entropy in LLM fine-tuning, revealing an asymmetr...

  12. GRAFT: Graph-Tokenized LLMs for Tool Planning

    cs.LG 2026-05 unverdicted novelty 6.0

    GRAFT internalizes tool dependency graphs via dedicated special tokens in LLMs and applies on-policy context distillation to achieve higher exact sequence matching and dependency legality than prior external-graph methods.

  13. Ask Only When Needed: Proactive Retrieval from Memory and Skills for Experience-Driven Lifelong Agents

    cs.CL 2026-04 unverdicted novelty 6.0

    ProactAgent learns a proactive retrieval policy via reinforcement learning on paired task continuations, improving lifelong agent performance and cutting retrieval overhead on SciWorld, AlfWorld, and StuLife.

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

    cs.AI 2026-03 unverdicted novelty 6.0

    HiMAC decomposes LLM agent tasks into macro planning and micro execution using critic-free hierarchical RL and iterative co-evolution, outperforming baselines on ALFWorld, WebShop, and Sokoban.

  15. No More Stale Feedback: Co-Evolving Critics for Open-World Agent Learning

    cs.AI 2026-01 unverdicted novelty 6.0

    ECHO jointly optimizes policy and critic via co-evolution, cascaded rollouts, and saturation-aware shaping to deliver non-stale feedback and higher success in open-world LLM agent RL.

  16. From Refusal to Recovery: A Control-Theoretic Approach to Generative AI Guardrails

    cs.AI 2025-10 unverdicted novelty 6.0

    Control-theoretic guardrails enable proactive correction of risky LLM agent actions in latent space, preventing catastrophes like collisions or bankruptcy while preserving task performance in simulated environments.

  17. StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction

    cs.CL 2026-05 unverdicted novelty 5.0

    StraTA improves LLM agent success rates to 93.1% on ALFWorld and 84.2% on WebShop by sampling a compact initial strategy and training it jointly with action execution via hierarchical GRPO-style rollouts.

  18. On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length

    cs.AI 2026-05 unverdicted novelty 5.0

    Longer action horizons bottleneck LLM agent training through instability, but training with reduced horizons stabilizes learning and enables better generalization to longer horizons.

  19. Ask Only When Needed: Proactive Retrieval from Memory and Skills for Experience-Driven Lifelong Agents

    cs.CL 2026-04 unverdicted novelty 5.0

    ProactAgent treats memory retrieval as a learned policy action and reports large gains in success rate and fewer interaction rounds on SciWorld, AlfWorld, and StuLife.

  20. Gated Coordination for Efficient Multi-Agent Collaboration in Minecraft Game

    cs.MA 2026-04 unverdicted novelty 5.0

    Gated escalation and partitioned states enable more efficient multi-agent collaboration in Minecraft by making communication selective rather than automatic.

  21. Multi-Agent Systems: From Classical Paradigms to Large Foundation Model-Enabled Futures

    cs.AI 2026-04 unverdicted novelty 4.0

    A survey comparing classical multi-agent systems with large foundation model-enabled multi-agent systems, showing how the latter enables semantic-level collaboration and greater adaptability.