paper-with-me

Papers

Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe

2026-03-23 · Xixi Wu, Qianguo Sun, Ruiyang Zhang, Chao Song, Junlong Wu, Yiyan Qi, Hong Cheng arxiv

Reinforcement Learning (RL) is essential for evolving Large Language Models (LLMs) into autonomous agents capable of long-horizon planning, yet a practical recipe for scaling RL in complex, multi-turn environments remains elusive. This paper presents a systematic empirical study using TravelPlanner, a challenging testbed requiring tool orchestration to satisfy multifaceted constraints. We decompose the agentic RL design space along 5 axes: reward shaping, model scaling, data composition, algorithm selection, and environmental stability. Our controlled experiments yield 7 key takeaways, e.g., (1) reward and algorithm choices are scale-dependent as smaller models benefit from staged rewards and enhanced exploration, whereas larger models converge efficiently with simpler dense rewards, (2) ~ 1K training samples with a balanced difficulty mixture mark a sweet spot for both in-domain and out-of-domain performance, and (3) environmental stability is critical to prevent policy degradation. Based on our distilled recipe, our RL-trained models achieve state-of-the-art performance on TravelPlanner, significantly outperforming leading LLMs.

📄 PDF Abstract BibTeX arXiv:2603.21972

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Reinforcement Learning for Long-Horizon Multi-Turn Search Agents

2025-10-28 · Vivek Kalyan, Martin Andrews arxiv

Large Language Model (LLM) agents can leverage multiple turns and tools to solve complex tasks, with prompt-based approaches achieving strong performance. This work demonstrates that Reinforcement Learning (RL) can push …

Reinforcement Learning

ToolVerse: Unlocking Massive Environments and Long-Horizon Tasks for Agentic Reinforcement Learning

2026-07-17 · Shuaiyu Zhou, Fengpeng Yue, Zengjie Hu, Yuanzhe Shen 외 arxiv

While LLM agents demonstrate strong reasoning abilities in compact and well-defined scenarios, they struggle to maintain robustness and effectiveness when faced with large-scale, diverse, and dynamic real-world environme…

Reinforcement Learning

TRIP-Bench: A Benchmark for Long-Horizon Interactive Agents in Real-World Scenarios

2026-02-02 · Yuanzhe Shen, Zisu Huang, Zhengyuan Wang, Muzhao Tian 외 arxiv

As LLM-based agents are deployed in increasingly complex real-world settings, existing benchmarks underrepresent key challenges such as enforcing global constraints, coordinating multi-tool reasoning, and adapting to evo…

Reinforcement Learning

Process-Supervised Reinforcement Learning for Interactive Multimodal Tool-Use Agents

2025-09-17 · Weiting Tan, Xinghua Qu, Ming Tu, Meng Ge 외 arxiv

Effective interactive tool use requires agents to master Tool Integrated Reasoning (TIR): a complex process involving multi-turn planning and long-context dialogue management. To train agents for this dynamic process, pa…

Reinforcement LearningMathematical Reasoning

Reducing Cognitive Overhead in Tool Use via Multi-Small-Agent Reinforcement Learning

2025-08-12 · Dayu Wang, Jiaye Yang, Weikang Li, Jiahui Liang 외 arxiv

Recent advances in multi-agent systems highlight the potential of specialized small agents that collaborate via division of labor. Existing tool-integrated reasoning systems, however, often follow a single-agent paradigm…

Reinforcement Learning