홈 › Papers

StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction

2026-05-07 · Xiangyuan Xue, Yifan Zhou, Zidong Wang, Shengji Tang, Philip Torr, Wanli Ouyang, Lei Bai, Zhenfei Yin arxiv

Large language models (LLMs) are increasingly used as interactive agents, but optimizing them for long-horizon decision making remains difficult because current methods are largely purely reactive, which weakens both exploration and credit assignment over extended trajectories. In this work, we present Strategic Trajectory Abstraction (StraTA), a simple framework that introduces an explicit trajectory-level strategy into agentic reinforcement learning (RL). StraTA samples a compact strategy from the initial task state, conditions subsequent actions on that strategy, and trains strategy generation and action execution jointly with a hierarchical GRPO-style rollout design, further enhanced by diverse strategy rollout and critical self-judgment. Experiments on ALFWorld, WebShop, and SciWorld show that StraTA consistently improves both sample efficiency and final performance over strong baselines. StraTA reaches success rates of 93.1% on ALFWorld and 84.2% on WebShop. On SciWorld, StraTA attains a 63.5% overall score, outperforming frontier closed-source models.

📄 PDF Abstract BibTeX arXiv:2605.06642

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning Decision Making

Stratagem: Learning Transferable Reasoning via Trajectory-Modulated Game Self-Play

2026-04-20 · Xiachong Feng, Deyi Yin, Xiaocheng Feng, Yi Jiang 외 arxiv

Games offer a compelling paradigm for developing general reasoning capabilities in language models, as they naturally demand strategic planning, probabilistic inference, and adaptive decision-making. However, existing se…

Mathematical Reasoning Code Generation

Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMs

2025-11-24 · Meng Lu, Ran Xu, Yi Fang, Wenxuan Zhang 외 arxiv

While recent vision-language models (VLMs) demonstrate strong image understanding, their ability to "think with images", i.e., to reason through multi-step visual interactions, remains limited. We introduce VISTA-Gym, a …

Reinforcement Learning Multimodal Reasoning Visual Reasoning

HLSMAC: A New StarCraft Multi-Agent Challenge for High-Level Strategic Decision-Making

2025-09-16 · Xingxing Hong, Yungong Wang, Dexin Jin, Ye Yuan 외 arxiv

Benchmarks are crucial for assessing multi-agent reinforcement learning (MARL) algorithms. While StarCraft II-related environments have driven significant advances in MARL, existing benchmarks like SMAC focus primarily o…

Multi-agent Reinforcement Learning Starcraft II

Signals: Trajectory Sampling and Triage for Agentic Interactions

2026-04-01 · Shuguang Chen, Adil Hafeez, Salman Paracha arxiv

Agentic applications based on large language models increasingly rely on multi-step interaction loops involving planning, action execution, and environment feedback. While such systems are now deployed at scale, improvin…

Incentivizing an Unknown Crowd

2021-09-09 · Jing Dong, Shuai Li, Baoxiang Wang

Motivated by the common strategic activities in crowdsourcing labeling, we study the problem of sequential eliciting information without verification (EIWV) for workers with a heterogeneous and unknown crowd. We propose …

reinforcement-learning Reinforcement Learning (RL)