TSR: Trajectory-Search Rollouts for Multi-Turn RL of LLM Agents

• URL: http://arxiv.org/abs/2602.11767v1
• Date: Thu, 12 Feb 2026 09:49:24 GMT
• Title: TSR: Trajectory-Search Rollouts for Multi-Turn RL of LLM Agents
• Abstract summary: We propose TSR (Trajectory-Search Rollouts), a training-time approach that repurposes test-time scaling ideas for improved per-turn rollout generation.<n>We instantiate TSR with best-of-N, beam look search, and pair it with PPO and GRPO, achieving up to 15% performance gains and more stable learning on Sokoban, FrozenLake, and WebShop tasks at a one-time increase in training compute.
• Score: 31.795232330674413
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Advances in large language models (LLMs) are driving a shift toward using reinforcement learning (RL) to train agents from iterative, multi-turn interactions across tasks. However, multi-turn RL remains challenging as rewards are often sparse or delayed, and environments can be stochastic. In this regime, naive trajectory sampling can hinder exploitation and induce mode collapse. We propose TSR (Trajectory-Search Rollouts), a training-time approach that repurposes test-time scaling ideas for improved per-turn rollout generation. TSR performs lightweight tree-style search to construct high-quality trajectories by selecting high-scoring actions at each turn using task-specific feedback. This improves rollout quality and stabilizes learning while leaving the underlying optimization objective unchanged, making TSR optimizer-agnostic. We instantiate TSR with best-of-N, beam, and shallow lookahead search, and pair it with PPO and GRPO, achieving up to 15% performance gains and more stable learning on Sokoban, FrozenLake, and WebShop tasks at a one-time increase in training compute. By moving search from inference time to the rollout stage of training, TSR provides a simple and general mechanism for stronger multi-turn agent learning, complementary to existing frameworks and rejection-sampling-style selection methods.

Related papers

• ARISE-RL: Agentic Rubric-Grounded Iterative Self-Evolution with Reinforcement Learning [74.19730275669227]
  ARISE-RL is a novel full-cycle self-evolution framework for training open-ended agents.<n>We present Reward-Gated Self-Evolution Distillation (RG-SED), which distills a memory-augmented variant of the same policy back into itself.<n>We also present ECR-Bench, an expert-calibrated rubric benchmark suite covering single-tool deep research and multi-tool travel planning.
  arXiv  Detail & Related papers  (2026-09-01T10:54:13Z)
• Reinforcement Learning Enhanced LLM Agents for Complex Vehicle Routing Problems [22.538946344456857]
  Vehicle Routing Problems (VRPs) are fundamental optimization problems with widespread applications in various scenarios.<n>We propose Reinforcement Learning Enhanced LLMAgents(RLEA), a multi-agent framework designed to automate the modeling of complex VRPs.
  arXiv  Detail & Related papers  (2026-09-01T07:56:15Z)
• HiDiffTIR: Hierarchical Difficulty-Aware Policy Optimization for Multi-Turn Tool-Integrated Reasoning [95.29291773706224]
  Tool-Integrated Reasoning is a capability for LLM agents to solve complex tasks by interacting with external tools iteratively.<n>Existing approaches typically assign uniform trajectory-level advantages and treat all correct tool calls equally.<n>This can lead to imprecise learning signals that do not adequately distinguish between trivial and challenging tool-use patterns.
  arXiv  Detail & Related papers  (2026-08-22T09:14:15Z)
• Process Reward Informed Tree Rollout for Effective Multi-Turn RL [58.392997761968566]
  In long-horizon agentic tasks, a uniform rollout strategy can waste budget on uninformative dead-end attempts.<n>We propose Process-Scorer Guided Adaptive Tree Rollout (PATR), a quality-aware rollout framework for multi-turn agent RL.<n>PATR uses task-appropriate process feedback to score partial trajectories, selectively branches from promising states, reuses shared prefixes, and conservatively stops paths to reduce wasted sampling.
  arXiv  Detail & Related papers  (2026-07-17T04:16:58Z)
• Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning [47.00572734047258]
  We present Single-rollout Asynchronous Optimization (SAO) to address the stability and off-policy challenges in asynchronous RL.<n>SAO replaces group-wise sampling with single-rollout sampling, that is, using one rollout per prompt.<n>SAO is successfully deployed in the agentic RL pipeline for training the open GLM-5.2 model.
  arXiv  Detail & Related papers  (2026-07-08T15:02:19Z)
• Guided by Trajectories: Repairing and Rewarding Tool-Use Trajectories for Tool-Integrated Reasoning [65.10602992874787]
  AutoTraj is a framework that automatically learns TIR by repairing and rewarding tool-use trajectories.<n> Experiments on real-world benchmarks demonstrate the effectiveness of AutoTraj.
  arXiv  Detail & Related papers  (2026-01-30T14:42:04Z)
• PROPA: Toward Process-level Optimization in Visual Reasoning via Reinforcement Learning [30.44007644340425]
  We introduce PROPA, a novel framework that integrates Monte Carlo Tree Search (MCTS) with GRPO to generate dense, process-level rewards and optimize reasoning at each intermediate step without human annotations.<n>Across seven benchmarks and four VLM backbones, PROPA consistently outperforms both SFT- and RLVR-based baselines.<n>It achieves up to 17.0% gains on in-domain tasks and 21.0% gains on out-of-domain tasks compared to existing state-of-the-art.
  arXiv  Detail & Related papers  (2025-11-13T13:06:12Z)
• Agentic Reinforcement Learning with Implicit Step Rewards [92.26560379363492]
  Large language models (LLMs) are increasingly developed as autonomous agents using reinforcement learning (agentic RL)<n>We introduce implicit step rewards for agentic RL (iStar), a general credit-assignment strategy that integrates seamlessly with standard RL algorithms.<n>We evaluate our method on three challenging agent benchmarks, including WebShop and VisualSokoban, as well as open-ended social interactions with unverifiable rewards in SOTOPIA.
  arXiv  Detail & Related papers  (2025-09-23T16:15:42Z)
• ActiveVLN: Towards Active Exploration via Multi-Turn RL in Vision-and-Language Navigation [57.399685080574756]
  Existing MLLM-based VLN methods rely on imitation learning (IL) and often use DAgger for post-training.<n>We propose ActiveVLN, a VLN framework that explicitly enables active exploration through multi-turn RL.<n>Experiments show that ActiveVLN achieves the largest performance gains over IL baselines compared to both DAgger-based and prior RL-based post-training methods.
  arXiv  Detail & Related papers  (2025-09-16T03:31:46Z)
• Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic Shuffle [65.14124923451077]
  Reinforcement learning (RL) has emerged as an effective post-training paradigm for enhancing the reasoning capabilities of multimodal large language model (MLLM)<n>However, current RL pipelines often suffer from training inefficiencies caused by two underexplored issues: Advantage Collapsing and Rollout Silencing.<n>We propose Shuffle-R1, a simple yet principled framework that improves RL fine-tuning efficiency by dynamically restructuring trajectory sampling and batch composition.
  arXiv  Detail & Related papers  (2025-08-07T17:53:47Z)
• Agentic Reinforced Policy Optimization [66.96989268893932]
  Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks.<n>Current RL algorithms inadequately balance the models' intrinsic long-horizon reasoning capabilities and their proficiency in multi-turn tool interactions.<n>We propose Agentic Reinforced Policy Optimization (ARPO), a novel agentic RL algorithm tailored for training multi-turn LLM-based agents.
  arXiv  Detail & Related papers  (2025-07-26T07:53:11Z)
• TGRPO :Fine-tuning Vision-Language-Action Model via Trajectory-wise Group Relative Policy Optimization [12.061547251822326]
  Trajectory-based Group Relative Policy Optimization (TGRPO) is an online RL-based training framework for Visual-Language-Action (VLA) models.<n>We show that TGRPO achieves an average success rate of 80.7%, which is 4.2% higher than that of Supervised Fine-Tuning (SFT) and outperforms other representative RL-based post-training methods.
  arXiv  Detail & Related papers  (2025-06-10T04:27:49Z)
• ViaRL: Adaptive Temporal Grounding via Visual Iterated Amplification Reinforcement Learning [68.76048244253582]
  We introduce ViaRL, the first framework to leverage rule-based reinforcement learning (RL) for optimizing frame selection in video understanding.<n>ViaRL utilizes the answer accuracy of a downstream model as a reward signal to train a frame selector through trial-and-error.<n>ViaRL consistently delivers superior temporal grounding performance and robust generalization across diverse video understanding tasks.
  arXiv  Detail & Related papers  (2025-05-21T12:29:40Z)
• RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning [125.96848846966087]
  Training large language models (LLMs) as interactive agents presents unique challenges.<n>While reinforcement learning has enabled progress in static tasks, multi-turn agent RL training remains underexplored.<n>We propose StarPO, a general framework for trajectory-level agent RL, and introduce RAGEN, a modular system for training and evaluating LLM agents.
  arXiv  Detail & Related papers  (2025-04-24T17:57:08Z)
• Dynamic Learning Rate for Deep Reinforcement Learning: A Bandit Approach [2.743898388459522]
  In deep Reinforcement Learning (RL), the learning rate critically influences both stability and performance, yet its optimal value shifts during training as the environment and policy evolve.<n>Standard decay schedulers assume monotonic convergence and often misalign with these dynamics, leading to premature or delayed adjustments.<n>We introduce LRRL, a meta-learning approach that dynamically selects the learning rate based on policy performance rather than training steps.
  arXiv  Detail & Related papers  (2024-10-16T14:15:28Z)
• Robust Reinforcement Learning as a Stackelberg Game via Adaptively-Regularized Adversarial Training [43.97565851415018]
  Robust Reinforcement Learning (RL) focuses on improving performances under model errors or adversarial attacks. Most of the existing literature models RARL as a zero-sum simultaneous game with Nash equilibrium as the solution concept. We introduce a novel hierarchical formulation of robust RL - a general-sum Stackelberg game model called RRL-Stack.
  arXiv  Detail & Related papers  (2022-02-19T03:44:05Z)

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.