Skip to content

T2SPO: Trajectory-to-Step Policy Optimization for Agentic Reinforcement Learning

Sep 2026 · 1 citation · 25 references
Computer Science

TL;DR

This work introduces Trajectory-to-Step Policy Optimization (T2SPO), a method that uses past interaction trajectories to provide step-level feedback for policy learning and shows that T2SPO consistently improves overall task success over GRPO.

Abstract

Reinforcement learning enables large language model (LLM) agents to learn multi-step behaviors through interaction with their environments. However, rewards in many interactive tasks reflect only the final outcome, providing limited guidance on which intermediate decisions advance the task. Successful training trajectories contain intermediate states that can provide supervision for subsequent interactions. We introduce Trajectory-to-Step Policy Optimization (T2SPO), a method that uses past interaction trajectories to provide step-level feedback for policy learning. T2SPO derives remaining-distance targets from successful trajectories and pairs them with representations of the states visited along the way. Conditioned on these examples, a pretrained TabPFN regressor estimates the remaining distance to success at each state of a new rollout. Changes in this distance estimate across consecutive states yield auxiliary credit for agent steps alongside task-level supervision. As training proceeds, newly completed trajectories refresh the estimator's context, incorporating new experience without updating its parameters. Experiments with 1.5B and 7B language models on ALFWorld and WebShop show that T2SPO consistently improves overall task success over GRPO.

View source

Similar papers

#artificial intelligence Preprint Oct 2026

Rollout-Time Intervention: Unlocking Agentic Reinforcement Learning Beyond Policy Limits

Rollout-Time Intervention is introduced, a technique designed to elicit successful trajectories beyond the policy's intrinsic exploration capacity, enabling the post-trained policy to approach the performance of substantially stronger contemporary LLMs and, more importantly, transcend its original capability boundary.

Xi Chen, Rui-Xue Ding, Zhigaoyuan Wang et al. · 0 citations
#artificial intelligence Preprint Nov 2026

AttnSR: Attention Step Reward for Long-Horizon Agentic RL

Long-horizon LLM agents make multi-step decisions, yet outcome-reward-only reinforcement learning provides little direct supervision for individual steps. We introduce AttnSR, a step-level reward augmentation method that derives reward allocations from policy attention extracted during training replay, without a separa...

Meng-Song Wu, Tian-Chen Zhou, Zhao-Chen Su et al. · 0 citations
#artificial intelligence Preprint Oct 2026

Co-Evolving Acting and Forecasting for Language Agents

Training language agents is bottlenecked by the high cost of long-horizon rollouts, yet standard agentic reinforcement learning (RL) learns only from a terminal scalar reward, leaving the supervision in intermediate steps largely unused. Prior work exploits this supervision through value targets that estimate per-step...

Hao-Fei Yu, Yi-Xin Chen, Yi-Ning Zhao et al. · 0 citations

Back to the Definition: Estimating Step-Level Advantages via Trajectory Graphs for Agentic Reinforcement Learning

A Graph-based Faithful sTep-level credit-assignment framework (GRAFT) that grafts all rollout trajectories into a trajectory graph, recovering node state-values via Bellman iteration on the graph, and assigning credit to each edge by the node value difference is proposed.

Xin-Cheng Yao, Haobo Fu, Wei-Ming Liu et al. · 0 citations
#natural language process... Preprint Oct 2026

RSIPO: Recursive Self-Improving Policy Optimization for Agentic Reinforcement Learning via Skill-Policy Co-Evolution

Recent focus in agentic reinforcement learning (RL) seeks to improve credit assignment in long-horizon tasks. One promising direction combines reinforcement learning with verifiable rewards (RLVR) and on-policy self-distillation (OPSD), integrating trajectory-level advantages with dense token-level supervision. This li...

Fan Zhang, Hao Wu, Jin-Yang Wu et al. · 1 citation

Related blog posts

MIT News · Artificial Intelligence Sep 29, 2026

Who we become when we talk to machines

Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.