Turn-PPO: Turn-Level Advantage Estimation with PPO for Improved Multi-Turn RL in Agentic LLMs

• URL: http://arxiv.org/abs/2512.17008v1
• Date: Thu, 18 Dec 2025 19:07:25 GMT
• Title: Turn-PPO: Turn-Level Advantage Estimation with PPO for Improved Multi-Turn RL in Agentic LLMs
• Abstract summary: We investigate more stable and effective advantage estimation strategies, especially for multi-turn settings.<n>We first explore Proximal Policy Optimization (PPO) as an alternative and find it to be more robust than GRPO.<n>To further enhance PPO in multi-turn scenarios, we introduce turn-PPO, a variant that operates on a turn-level MDP formulation.
• Score: 18.31183900162479
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning (RL) has re-emerged as a natural approach for training interactive LLM agents in real-world environments. However, directly applying the widely used Group Relative Policy Optimization (GRPO) algorithm to multi-turn tasks exposes notable limitations, particularly in scenarios requiring long-horizon reasoning. To address these challenges, we investigate more stable and effective advantage estimation strategies, especially for multi-turn settings. We first explore Proximal Policy Optimization (PPO) as an alternative and find it to be more robust than GRPO. To further enhance PPO in multi-turn scenarios, we introduce turn-PPO, a variant that operates on a turn-level MDP formulation, as opposed to the commonly used token-level MDP. Our results on the WebShop and Sokoban datasets demonstrate the effectiveness of turn-PPO, both with and without long reasoning components.

Related papers

• RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning [49.04912820721943]
  Group Prioritized Off-Policy Optimization (POPO) is a framework that exploits effective training batches without additional rollout overhead.<n>POPO comprises two key components: prioritized group replay and decoupled off-policy optimization.<n>POPO substantially accelerates RL finetuning and achieves strong reasoning performance with significantly fewer rollouts.
  arXiv  Detail & Related papers  (2026-05-31T15:06:38Z)
• TOPPO: Rethinking PPO for Multi-Task Reinforcement Learning with Critic Balancing [1.9552387050709823]
  We propose TOPPO, a set of modules that improve gradient conditioning and balance learning dynamics across tasks.<n> TOPPO achieves stronger mean and tail-task performance than published SAC-family and ARS-family baselines.<n>Our results demonstrate that, with proper optimization, on-policy methods can rival or exceed off-policy approaches in MTRL.
  arXiv  Detail & Related papers  (2026-05-12T03:40:28Z)
• HiPO: Hierarchical Preference Optimization for Adaptive Reasoning in LLMs [2.497936211748472]
  We propose HiPO, an extension of DPO that separates responses into segments and computes loss as a weighted sum of the DPO loss for each segment.<n>Our approach enables segment-specific training while maintaining DPO's computational efficiency and training stability.<n>We demonstrate that for multiple 7B LLMs fine-tuned using HiPO and DPO on the Math Stack Exchange preference dataset, the models trained with HiPO outperform the others on a variety of common math benchmarks.
  arXiv  Detail & Related papers  (2026-04-22T03:08:30Z)
• Bounded Ratio Reinforcement Learning [62.09379476369526]
  This paper introduces the Bounded Ratio Reinforcement Learning (BRRL) framework to solve on-policy reinforcement learning problems.<n>We develop a policy optimization algorithm called Bounded Policy Optimization (BPO) that minimizes an advantage-weighted divergence between the policy and the analytic optimal solution from BRRL.<n> Notably, our framework also provides a new theoretical lens to interpret the success of the PPO loss, and connects trust region policy optimization and the Cross-Entropy Method (CEM).
  arXiv  Detail & Related papers  (2026-04-20T17:59:01Z)
• Rethinking the Trust Region in LLM Reinforcement Learning [72.25890308541334]
  Proximal Policy Optimization (PPO) serves as the de facto standard algorithm for Large Language Models (LLMs)<n>We propose Divergence Proximal Policy Optimization (DPPO), which substitutes clipping with a more principled constraint.<n>DPPO achieves superior training and efficiency compared to existing methods, offering a more robust foundation for RL-based fine-tuning.
  arXiv  Detail & Related papers  (2026-02-04T18:59:04Z)
• GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization [133.27496265096445]
  We show how to apply Group Relative Policy Optimization under multi-reward setting without examining its suitability.<n>We then introduce Group reward-Decoupled Normalization Policy Optimization (GDPO), a new policy optimization method to resolve these issues.<n>GDPO consistently outperforms GRPO, demonstrating its effectiveness and generalizability for multi-reward reinforcement learning optimization.
  arXiv  Detail & Related papers  (2026-01-08T18:59:24Z)
• Learning Branching Policies for MILPs with Proximal Policy Optimization [0.0]
  Branch-and-Bound (B&B) is the dominant exact solution method for Mixed Linear Programs (MILP)<n>Current approaches rely on Imitation Learning (IL), which tends to overfit to expert demonstrations and struggles to generalize to structurally diverse or unseen instances.<n>In this work, we propose Tree-Gate Proximal Policy Optimization, a novel framework that employs Proximal Policy Optimization (PPO), a Reinforcement Learning (RL) algorithm, to train a branching policy.
  arXiv  Detail & Related papers  (2025-11-17T05:16:14Z)
• ACPO: Adaptive Curriculum Policy Optimization for Aligning Vision-Language Models in Complex Reasoning [17.928214942495412]
  ACPO employs a dynamic curriculum that orchestrates a principled transition from a stable, near on-policy exploration phase to an efficient, off-policy exploitation phase.<n>We conduct extensive experiments on a suite of challenging multimodal reasoning benchmarks, including MathVista, LogicVista, and MMMU-Pro.<n>Results demonstrate that ACPO consistently outperforms strong baselines such as DAPO and PAPO, achieving state-of-the-art performance, accelerated convergence, and superior training stability.
  arXiv  Detail & Related papers  (2025-10-01T09:11:27Z)
• PGPO: Enhancing Agent Reasoning via Pseudocode-style Planning Guided Preference Optimization [58.465778756331574]
  We propose a pseudocode-style Planning Guided Preference Optimization method called PGPO for effective agent learning.<n>With two planning-oriented rewards, PGPO further enhances LLM agents' ability to generate high-quality P-code Plans.<n>Experiments show that PGPO achieves superior performance on representative agent benchmarks and outperforms the current leading baselines.
  arXiv  Detail & Related papers  (2025-06-02T09:35:07Z)
• On-Policy RL with Optimal Reward Baseline [109.47676554514193]
  On-Policy RL with Optimal reward baseline (OPO) is a novel and simplified reinforcement learning algorithm.<n>OPO emphasizes the importance of exact on-policy training, which empirically stabilizes the training process and enhances exploration.<n>Results demonstrate OPO's superior performance and training stability without additional models or regularization terms.
  arXiv  Detail & Related papers  (2025-05-29T15:58:04Z)
• Reinforcing Multi-Turn Reasoning in LLM Agents via Turn-Level Reward Design [35.544075583073685]
  We present the first systematic study of textitturn-level reward design for multi-turn RL algorithms and agent applications.<n>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.<n>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.
  arXiv  Detail & Related papers  (2025-05-17T04:09:46Z)
• SDPO: Segment-Level Direct Preference Optimization for Social Agents [56.970902914217156]
  Social agents powered by large language models (LLMs) can simulate human social behaviors but fall short in handling complex social dialogues.<n>We propose Segment-Level Direct Preference Optimization (SDPO), which dynamically select key segments within interactions to optimize multi-turn agent behavior.
  arXiv  Detail & Related papers  (2025-01-03T14:09:46Z)
• A dynamical clipping approach with task feedback for Proximal Policy Optimization [29.855219523565786]
  There is no theoretical proof that the optimal PPO clipping bound remains consistent throughout the entire training process. Past studies have aimed to dynamically adjust PPO clipping bound to enhance PPO's performance. We propose Preference based Proximal Policy Optimization (Pb-PPO) to better reflect the preference (maximizing Return) of reinforcement learning tasks.
  arXiv  Detail & Related papers  (2023-12-12T06:35:56Z)
• Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning [139.53668999720605]
  We present a multi-agent PPO algorithm in which the local policy of each agent is updated similarly to vanilla PPO. We prove that with standard regularity conditions on the Markov game and problem-dependent quantities, our algorithm converges to the globally optimal policy at a sublinear rate.
  arXiv  Detail & Related papers  (2023-05-08T16:20:03Z)
• Permutation Invariant Policy Optimization for Mean-Field Multi-Agent Reinforcement Learning: A Principled Approach [128.62787284435007]
  We propose the mean-field proximal policy optimization (MF-PPO) algorithm, at the core of which is a permutation-invariant actor-critic neural architecture. We prove that MF-PPO attains the globally optimal policy at a sublinear rate of convergence. In particular, we show that the inductive bias introduced by the permutation-invariant neural architecture enables MF-PPO to outperform existing competitors.
  arXiv  Detail & Related papers  (2021-05-18T04:35:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.