← Back to all news
arXiv Machine Learning By Quan Wei, Siliang Zeng, Chenliang Li, Zhongruo Wang, William Brown, Oana Frunza, Wei Deng, Anderson Schneider, Yuriy Nevmyvaka, Yang Katie Zhao, Alfredo Garcia, Mingyi Hong

Reinforcing Multi-Turn Reasoning in LLM Agents via Fine-Grained Reward Structure and Credit Assignment

Read the original on arXiv Machine Learning →

The paper explores how dense, turn-level reward structures can improve reinforcement learning for large language model agents in multi-turn tasks. It introduces three reward granularity types—terminal, delayed, and per-turn—and adapts Group Relative Policy Optimization and Proximal Policy Optimization to each. Experiments on search and game agents show that per-turn rewards consistently yield better training dynamics, faster convergence, and higher answer correctness compared to sparse terminal or delayed rewards.

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 Machine Learning.

Related stories

arXiv AI
Jul 23

In-the-Flow Agentic System Optimization for Effective Planning and Tool Use

arXiv:2510. 05592v2 Announce Type: replace Abstract: Outcome-driven reinforcement learning has advanced reasoning in large language models (LLMs), but prevailing tool-augmented approaches train a single, monolithic policy that interleaves thoughts and tool calls under full context; this scales poorly with long horizons and diverse tools and generalizes weakly to new scenarios.

By Zhuofeng Li, Haoxiang Zhang, Seungju Han, Sheng Liu, Jianwen Xie, Yu Zhang, Yejin Choi, James Zou, Pan Lu
llmsagentsreinforcement-learningbenchmarks
More like this →
arXiv AI
Aug 20

RTPO: Reverse-Turn Policy Optimization for Stabilizing Agentic RL Training

The paper introduces Reverse‑Turn Policy Optimization (RTPO), a method that restructures multi‑turn agentic reinforcement learning rollouts into sparse reverse trees and updates policies in temporal reverse order. This approach addresses three key instability sources—context mismatch, weak turn‑level credit assignment, and asynchronous policy drift—by aligning each decision with its downstream continuation. Theoretical analysis shows RTPO eliminates context mismatch and drift, reduces credit bias, and converges to recursive optimality, while experiments demonstrate performance gains of 21.50% over trajectory‑level and 10.76% over turn‑level baselines on multi‑turn agentic RL benchmarks.

By Yugu Li, Jimmy Cao, Jianglin Qiao, Siyi Hu
llmsagentsreinforcement-learningbenchmarkssafety
More like this →