arXiv cs.AI· Haofu Yang, Hongyang Yin, Ran Bi, Faguo Wu, Peng Xue, Feng Zhou, Han Zhang·· 1 天前AI 评分34
Ask on Demand（AOD）：面向并行智能体系统的按需定向同伴通信框架
Ask on Demand: Targeted Peer Communication for Parallel Agentic Systems
AI 导读
研究提出 Ask on Demand（AOD）通信框架，让并行 LLM 智能体在出现具体信息需求时向同伴发起定向求助，由框架从同伴执行历史中检索相关证据、选择合适同伴并生成针对性回复。团队用配对团队续跑训练轻量门控，以最终团队结果和推理成本作为监督信号，判断何时求助值得。在 AppWorld 和 WebShop 上，AOD 相比独立并行执行稳定提升任务表现，且推理成本低于现有信息共享基线。
正文 · 原文
Abstract:Parallel LLM agents tackle complex tasks by exploring multiple trajectories, yet useful discoveries remain isolated in individual execution histories. Existing sharing methods often select or summarize information before other agents' needs become clear, potentially overlooking details that become important later. We propose Ask on Demand (AOD), a communication framework that enables agents to seek targeted peer assistance when specific information needs arise. Upon an approved request, AOD retrieves relevant evidence from peer execution histories, selects a suitable peer, and generates a response tailored to the request. To determine when such assistance is worthwhile, we train a lightweight gate using paired team continuations, with supervision derived from final team outcomes and inference cost. Experiments on AppWorld and WebShop demonstrate that AOD consistently improves task performance over independent parallel execution while achieving lower inference cost than existing information-sharing baselines. These findings highlight the benefits of aligning peer communication with agents' evolving information needs to achieve more effective and efficient collaboration.
| Comments: | Equal contribution: Haofu Yang and Hongyang Yin. Corresponding authors: Ran Bi and Faguo Wu |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.41378 [cs.AI] |
| (or arXiv:2610.41378v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.41378 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Hongyang Yin [view email]
[v1]
Fri, 30 Oct 2026 07:43:03 UTC (2,595 KB)
来源：arXiv cs.AI · arxiv.org