Alfredo Garcia

Quan Wei, Siliang Zeng, Chenliang Li et al.

This paper investigates Reinforcement Learning (RL) approaches to enhance the reasoning capabilities of Large Language Model (LLM) agents in long-horizon, multi-turn scenarios. Although RL algorithms such as Group Relative Policy Optimization (GRPO) and Proximal Policy Optimization (PPO) have been widely applied to train multi-turn LLM agents, they typically rely only on sparse outcome rewards and lack dense intermediate signals across multiple decision steps, limiting their performance on complex reasoning tasks. To bridge this gap, we present the first systematic study of \textit{turn-level reward design} for multi-turn RL algorithms and agent applications. By integrating turn-level rewards, we extend GRPO and PPO to their respective multi-turn variants, enabling fine-grained credit assignment. We conduct case studies on multi-turn reasoning-augmented search agents, where we carefully design two types of turn-level rewards: verifiable and LLM-as-judge. Our experiments on multi-turn search tasks demonstrate that incorporating well-designed turn-level rewards enables RL algorithms to significantly outperform baseline methods with trajectory-level rewards. Both training and validation reward curves illustrate that our method achieves \textit{greater stability}, \textit{faster convergence}, and \textit{higher accuracy}. Numerical results across diverse question-answering datasets further show that our approach consistently delivers highest answer correctness and 100\% format correctness.

Chenliang Li, Adel Elmahdy, Alex Boyd et al.

Reinforcement learning (RL) algorithms such as PPO and GRPO are widely used to train large language models (LLMs) for multi-turn agentic tasks. However, in off-policy training pipelines, these methods often exhibit unstable optimization dynamics and are prone to performance collapse. Through empirical analysis, we identify two fundamental sources of instability in this setting: (1)~a granularity mismatch between token-level policy optimization and turn-structured interactions, and (2) high-variance and unreliable gradient updates induced by off-policy importance sampling and inaccurate advantage estimation. To address these challenges, we propose SORL, \underline{S}tabilizing \underline{O}ff-Policy \underline{R}einforcement \underline{L}earning for Long-Horizon Agent Training. SORL introduces principled mechanisms that align policy optimization with the structure of multi-turn interactions and adaptively suppress unreliable off-policy updates, yielding more conservative and robust learning dynamics. Within this framework, we instantiate two stabilized algorithms: SO-PPO and SO-GRPO. Both algorithms are designed to mitigate gradient variance and prevent optimization collapse without requiring careful early stopping or heuristic tuning. We evaluate SO-PPO and SO-GRPO on a range of multi-turn search benchmarks, including general question answering, multi-hop question answering, and medical multiple-choice QA tasks. Experimental results show that both methods consistently prevent training instabilities and performance collapses observed in standard PPO and GRPO, maintain lower clipping ratios and more stable optimization trajectories, and achieve superior or comparable task performance. These results demonstrate that the proposed algorithm provides a practical, scalable, and general framework for stabilizing reinforcement learning in multi-turn LLM agent training.