arXiv Machine Learning

Success Leaves Detours: Learning Executable Walkthroughs for Long-Horizon Agents

The paper introduces Trace, a framework that transforms sparse-reward trajectories into executable walkthroughs by identifying progress anchors, propagating credit, and estimating action prerequisites. Trace compiles noisy trajectories into state‑conditioned, verifiable procedures that remove loops and detours, enabling reuse, intermediate‑state resumption, and programmatic verification. Experiments on J‑TTL, WebShop, and ScienceWorld with three open‑source LLMs show that Trace outperforms eight baselines, improving average AUC and Final‑$3$ by 30.0% and 40.5% while using fewer inference tokens.

arXiv Machine Learning

Aug 31

VICT: Verifier-Instrumented Credit Tracing for Long-Horizon LLM Agent Reinforcement Learning

The paper introduces VICT, a method that leverages the internal structure of verifiable tasks to perform fine‑grained credit assignment for long‑horizon LLM agents. VICT exposes executable or evidence‑backed atoms from a task’s terminal verifier and traces them back to actions via dependency‑valid proof edges, redistributing advantage only along these edges. This approach improves performance on ALFWorld and WebShop compared to outcome‑only training and matches recent fine‑grained credit methods without requiring additional critics, labels, or inference‑time verifier access.

By Pengcheng Li, Zhengyang Zhang, Dongxu Zhang, Sui Huang, Shaohua Ma

llms agents reinforcement-learning efficiency

arXiv Machine Learning

Jul 16

TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents

arXiv:2607. 13988v1 Announce Type: new Abstract: Multi-turn agents solve complex tasks through extended sequences of tool interactions before producing a final answer, making credit assignment a fundamental challenge during post-training.

By Leitian Tao, Baolin Peng, Wenlin Yao, Tao Ge, Hao Cheng, Mike Hang Wang, Jianfeng Gao, Sharon Li

agents reinforcement-learning fine-tuning benchmarks

Hugging Face Trending Papers

Aug 17

TRCA: Transition-wise Rubric Credit Assignment for Long-horizon LLM Agents

Long-horizon large language model (LLM) agents are typically optimized with sparse terminal outcomes, making fine-grained credit assignment across multi-step interactions difficult. Existing approache...

llms agents reinforcement-learning benchmarks

arXiv AI

Aug 18

TRCA: Transition-wise Rubric Credit Assignment for Long-horizon LLM Agents

arXiv:2608. 16156v1 Announce Type: new Abstract: Long-horizon large language model (LLM) agents are typically optimized with sparse terminal outcomes, making fine-grained credit assignment across multi-step interactions difficult.

By Huan Zhang, Mingju Chen, Dongxu Zhou, Can Lv, Heng Chang, Sen Cui, Faguo Wu, Shiji Zhou

llms agents reinforcement-learning benchmarks

arXiv AI

Sep 10

AgentBrew: Offline Tool-Use Agent Learning from Raw Real-World Trajectories

arXiv:2609.05837v1 Announce Type: new Abstract: LLM-based agents are increasingly deployed in real-world applications through tool-use APIs, yet training them for specific environments remains fundam...

By Zhiyi Lyu, Yewen Li, Longtao Zheng, Shengtian Yang, Lang Feng, Lei Feng, Peng Jiang, Kun Gai, Qingpeng Cai, Bo An

llms agents

arXiv AI

Aug 3

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

arXiv:2605. 17877v2 Announce Type: replace Abstract: A significant hurdle for current LLMs is the execution of complex, multi-stage tasks.

By Wonjoong Kim, Yeonjun In, Sangwu Park, Dongha Lee, Chanyoung Park

llms agents reinforcement-learning

arXiv AI

Aug 10

Gated-BEPO: Confidence-Gated Bellman Credit Assignment for Large Language Model Agents

arXiv:2608. 06861v1 Announce Type: new Abstract: Training large language model agents in long-horizon environments requires assigning credit from sparse terminal outcomes to individual actions.

By Hongxi Yan, Ziyue Huang, Shichao Fan, Qingjie Liu

llms agents multimodal

arXiv AI

Aug 6

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment

arXiv:2608. 05102v1 Announce Type: new Abstract: Long-horizon search agents must make multiple sequential actions (steps) to search, retrieve, verify, and integrate evidence to reach a final answer.

By Yijun Lu, Rui Ye, Jiajun Wang, Yuwen Du, Tian Jin, Songhua Liu, Siheng Chen

agents reinforcement-learning fine-tuning

arXiv Computation and Language

2d ago

FLARE: A Full-Lifecycle Dense Supervision Paradigm for Long-Horizon Coding Agents via Generative Reward Model

FLARE introduces a dense supervision paradigm for long‑horizon coding agents, leveraging a Generative Reward Model (GRM) trained via the RADAR diagnostic framework. The GRM provides real‑time, step‑level risk feedback, enabling FLARE to act as an active scaffold that intercepts high‑risk steps during inference and supplies structured signals for post‑training fine‑tuning and reinforcement learning. Experiments show FLARE outperforms existing methods, achieving a 5× reduction in token consumption and significant performance gains in both supervised fine‑tuning and RL settings.

By Jingxuan Xu, Gang Wu, Yanan Wu, Yutao Mou, Songwei Yu, Tianzhuang He, Zhengshuo Gong, Zhao Liu, Zihang Xu, Wenqiang Zhu, Xinping Lei, Weihao Li, Yuhui Bai, Zhongqiu Wang, Yan Wu, Ariel Deng

llms rag agents reinforcement-learning fine-tuning safety

arXiv AI

Jul 13

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading

arXiv:2607. 08964v1 Announce Type: new Abstract: AI agents have become capable of autonomously completing short, well-specified tasks.

By Zongxia Li, Zhongzhi Li, Yucheng Shi, Ruhan Wang, Junyao Yang, Zhichao Liu, Xiyang Wu, Anhao Li, Yue Yu, Ninghao Liu, Lichao Sun, Haotao Mi, LeoweiLiang

agents multimodal benchmarks

arXiv Machine Learning

Sep 3

Act More, Decide Less: Skill-Guided Adaptive Action Chunking for Long-Horizon LLM Agents

The paper introduces SPACE, a method for enabling large language model agents to emit variable-length action chunks in long-horizon tasks. By distilling chunk-boundary supervision from programmatic skills derived from successful trajectories, SPACE overcomes the tendency of agents to either act one step at a time or commit to overly long sequences. Experiments on ALFWorld and ScienceWorld demonstrate that SPACE raises success rates by 7.0%–31.3% and cuts LLM decision rounds by up to 78.9%.

By Yanting Yang, Can Jin, Jinman Zhao, Jiahao Wu, Yang Zhou, Zhepeng Wang, Zhendong Wang, Mu Zhou, Dimitris N. Metaxas

llms rag agents reinforcement-learning

arXiv Machine Learning

19h ago

Giving Credit Where It's Due: Redundancy-Aware Learning for Efficient Reasoning

arXiv:2609.27156v1 Announce Type: cross Abstract: Large reasoning models can produce correct yet unnecessarily long reasoning traces. Existing methods improve reasoning efficiency with trajectory-lev...

By Yuqing Zhou, Hong Wang, Manqing Mao, Zhuoer Wang, Samson Koelle, Jie Yuan, Yanjun Lin, James Feng, Nikki Lijing Kuang, Ziwei Zhu, Wei Niu

llms reinforcement-learning benchmarks

Related stories