← Back to all news
arXiv AI By Yi Wen, Hao Chen, Wanyu Wang, Maolin Wang, Pengyue Jia, Derong Xu, Huize Tan, Yingyi Zhang, Wenlin Zhang, Weihong Luo, Xiku Du, Xiangyu Zhao

TrajEvolve: Trajectory Evolution for Reinforcement Learning with Hindsight Credit Assignment

Read the original on arXiv AI →

TrajEvolve introduces a trajectory evolution paradigm with hindsight credit assignment to improve reinforcement learning for large language models on long-horizon tasks. It refines low-quality steps in historical trajectories to expose the policy to high-quality compositions that are rarely sampled, and reformulates step-level continuous credit assignment as a binary classification problem to identify redundant steps. Experiments on two datasets show that this approach outperforms existing methods.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Jun 16

STRIDE: Strategic Trajectory Reasoning via Discriminative Estimation for Verifiable Reinforcement Learning

arXiv:2606. 15866v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become an effective post-training paradigm for improving the reasoning abilities of large language models.

By Qinjian Zhao, Zhihao Dou, Dinggen Zhang, Xiangyu Li, Chaoda Song, Zhongwei Wan, Xinpeng Li, Yanyan Zhang, Kaijie Chen, Qingtao Pan, Chengcheng Feng, Zhiqiang Gao, Xiaoyu Xia
llmsagentsreinforcement-learning
More like this →
arXiv AI
Jun 10

HIPIF: Hierarchical Planning and Information Folding for Long-Horizon LLM Agent Learning

arXiv:2606. 10507v1 Announce Type: new Abstract: While Large Language Models (LLMs) have demonstrated strong capabilities as autonomous agents across a wide range of tasks, their performance often degrades in multi-turn long-horizon agentic tasks.

By Juncheng Diao, Zhicong Lu, Peiguang Li, Yongwei Zhou, Changyuan Tian, Qingbin Li, Rongxiang Weng, Jingang Wang, Xunliang Cai
llmsagentsnlpreinforcement-learningbenchmarks
More like this →
arXiv AI
Oct 7

Rationale-Guided Policy Optimization: Learning to Reason with Adaptive Rationale Scaffolding

Rationale-Guided Policy Optimization (RGPO) is a reinforcement‑learning framework that adaptively uses ground‑truth rationale information to scaffold a language model’s reasoning process. Instead of treating reference solutions as fixed imitation targets, RGPO temporarily incorporates rationales to help the model generate better responses, then reverts to unguided learning with higher‑reward, model‑generated solutions. Experiments in both language‑only and vision‑language tasks show that RGPO consistently outperforms RLVR baselines, with ablation studies confirming that adaptive rationale guidance is a key factor in its success.

By Hoang Phan, Minh Pham, Chau Pham, Chinmay Hegde, Trung Le, Qi Lei
llmsreinforcement-learningefficiencymultimodalbenchmarks
More like this →
arXiv AI
Aug 11

Beyond Solvability: Task Learnability as a Static Prior for LLM RL Post-Training

arXiv:2608. 09217v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a central post-training paradigm for eliciting reasoning capabilities in large language models, yet uniform task sampling allocates compute without regard to differences in how tasks respond to optimization.

By Ting Zhou, Zhenqing Ling, Daoyuan Chen, Qianli Shen, Yilun Huang, Ying Shen, Yaliang Li
llmsreinforcement-learningbenchmarks
More like this →