arXiv cs.AI· Adri\'an Szlatincs\'an, Filippo Ziliotto, Bruno Lepri, Luciano Serafini, Massimiliano Luca, Tommaso Campari·· 3 天前AI 评分22
观察、共享还是预测？解耦具身多智能体协作中的伙伴信息
Observe, Share, or Predict? Disentangling Partner Information in Embodied Multi-Agent Collaboration
AI 导读
研究基于 Habitat 的 PARTNR 基准提出解耦部分可观测机制，在 1000 个验证任务上测试 OAS 观察、KE 知识交换与 OANA 预测对 LLM 具身智能体协作的影响。OAS 观察提升任务质量并减少无效动作，KE 主要提升执行效率、最多减少 25% 仿真步数；OANA 预测在 16 组模型×上下文组合中有 15 组降低成功率，协作收益主要来自对共享上下文的响应而非显式预测。
正文 · 原文
Abstract:LLMs are used as high-level controllers for embodied agents, but it remains unclear whether they support collaborative reasoning, such as anticipating a collaborator's actions in real-time teamwork without dialogue. We ask if observing the partner's state, exchanging object knowledge, and predicting the partner's next action, shape task outcomes and coordination when agents can share percepts but never intentions, plans, or task-level messages, and whether the two agents occupy symmetric roles. Using the Habitat-based PARTNR benchmark, we introduce a Decoupled Partial Observability regime that enforces strictly individual perception, and we augment decentralized zero-shot ReAct planners with Other Agent's State (OAS) observation, object Knowledge Exchange (KE) between co-located agents, and Other Agent's Next Action (OANA) prediction, evaluated on the full 2 x 2 x 2 grid with four planners on 1,000 validation tasks. OAS observation improves task quality, reducing extraneous effort for every planner, whereas KE primarily improves execution efficiency, cutting simulation steps by up to 25% with little change in success. The two are largely redundant for strong planners but complementary for the weakest, for which KE without the OAS is the worst configuration. OANA prediction lowers the success rate in 15 of 16 model x context pairs while raising explicit partner mentions to 55-100%, and its accuracy gains lie mainly in the coarse action type, partly because agents recognize the action the partner is already performing. The robot retrieves objects sooner and completes its tasks earlier than the simulated human. Shared context reduces total task time by shortening the remaining duration that the human works alone. Also, coordination benefits arise from responding to shared context, especially the OAS, rather than explicit anticipation, yielding shallow, planner-dependent partner modeling.
| Subjects: | Artificial Intelligence (cs.AI); Robotics (cs.RO) |
| Cite as: | arXiv:2610.16895 [cs.AI] |
| (or arXiv:2610.16895v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.16895 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Adrián Szlatincsán [view email]
[v1]
Mon, 12 Oct 2026 14:49:31 UTC (5,873 KB)
来源：arXiv cs.AI · arxiv.org