paper-with-me

홈 › Papers

BrowseMaster: Towards Scalable Web Browsing via Tool-Augmented Programmatic Agent Pair

2025-08-12 · Xianghe Pang, Shuo Tang, Rui Ye, Yuwen Du, Yaxin Du, Siheng Chen arxiv

Effective information seeking in the vast and ever-growing digital landscape requires balancing expansive search with strategic reasoning. Current large language model (LLM)-based agents struggle to achieve this balance due to limitations in search breadth and reasoning depth, where slow, serial querying restricts coverage of relevant sources and noisy raw inputs disrupt the continuity of multi-step reasoning. To address these challenges, we propose BrowseMaster, a scalable framework built around a programmatically augmented planner-executor agent pair. The planner formulates and adapts search strategies based on task constraints, while the executor conducts efficient, targeted retrieval to supply the planner with concise, relevant evidence. This division of labor preserves coherent, long-horizon reasoning while sustaining broad and systematic exploration, overcoming the trade-off that limits existing agents. Extensive experiments on challenging English and Chinese benchmarks show that BrowseMaster consistently outperforms open-source and proprietary baselines, achieving scores of 30.0 on BrowseComp-en and 46.5 on BrowseComp-zh, which demonstrates its strong capability in complex, reasoning-heavy information-seeking tasks at scale.

📄 PDF Abstract BibTeX arXiv:2508.09129

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

The Bitter Lesson of Tool Calling

2026-08-06 · Ishan Patel, Sahil Sen, Elias Lumer, Vamse Kumar Subbiah arxiv

Tool use transforms LLMs into agents that act beyond their training data, and for code-capable models, programmatic tool calling extends this further by replacing rigid JSON calls with scripts that chain and parallelize …

EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis

2026-01-09 · Xiaoshuai Song, Haofei Chang, Guanting Dong, Yutao Zhu 외 arxiv

Large language models (LLMs) are expected to be trained to act as agents in various real-world environments, but this process relies on rich and varied tool-interaction sandboxes. However, access to real systems is often…

Reinforcement Learning

METU Turkish Discourse Bank Browser

2012-05-01 · LREC 2012 5 · Utku {\c{S}}irin, Ruket {\c{C}}ak{\i}c{\i}, Deniz Zeyrek

In this paper, the METU Turkish Discourse Bank Browser, a tool developed for browsing the annotated annotated discourse relations in Middle East Technical University (METU) Turkish Discourse Bank (TDB) project is present…

Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agents

2025-10-28 · Yueqi Song, Ketan Ramaneti, Zaid Sheikh, Ziru Chen 외 arxiv

Public research results on large-scale supervised finetuning of AI agents remain relatively rare, since the collection of agent training data presents unique challenges. In this work, we argue that the bottleneck is not …

Natural Language Actor-Critic: Scalable Off-Policy Learning in Language Space

2025-12-04 · Joey Hong, Kang Liu, Zhan Ling, Jiecao Chen 외 arxiv

Large language model (LLM) agents -- LLMs that dynamically interact with an environment over long horizons -- have become an increasingly important area of research, enabling automation in complex tasks involving tool-us…