让智能体在信息不全时仍能可靠协作,通过可执行的任务承诺达成默契。
GenCoord: Skill-Path Commitments under Private Information

- 基于局部信息生成多步计划与请求,通过反馈闭环修正决策。
- 信息对齐后协作成功率从50%提升至100%,任务成功率提高6.9点。
- 使用简化的指令语言减少92.8%通信量,加速68.2%任务承诺速度。
当一个具身智能体知道目标是什么,而其队友仅了解工作台的变换能力时,双方都无法独立判断谁该行动、交接什么或如何推进任务。我们提出GenCoord,将这种私有信息导致的任务后果转化为可执行的技能路径承诺。本地Qwen3.5-0.8B模型生成多步自我计划(SELF)与同伴请求(REQ),在决定能力为同伴本地时,受限反馈引导修正。最终承诺被解析、校验、规范化并编译为Mineflayer技能,通过交接与终态验证。反事实干预保持世界状态、调度和执行者不变,使请求方修正与接收方执行均按注入的任务后果双向一致。在三个独立训练种子下,正确能力反馈将局部信息差距的解决率从50%提升至100%。多步承诺使未见模板的成功率提升6.9分,同时减少32%模型决策。在128个未见语义簇上达到相同闭环质量时,短指令语言(Short DSL)相比自由沟通,减少92.8%同伴通信量,将中位承诺时间缩短68.2%。结果表明,可执行的任务后果是连接分布式局部推理与可验证联合行动的核心协调单元。
原文摘要 · Abstract (English)
Suppose one embodied agent knows what must be built, while its teammate alone knows which transformation its workcell can perform. Neither local view determines who should act, what should be handed off, or how the joint task should continue. We introduce GenCoord, which turns the task consequence of such private facts into an executable skill-path commitment. A local Qwen3.5-0.8B model emits a multi-step SELF plan and peer REQ; bounded feedback conditions route revision when the deciding capability is peer-local. The resolved commitment is parsed, checked, canonically materialized, compiled to Mineflayer skills, and verified by handoff and terminal state. Counterfactual interventions that hold the world, call schedule, and executor unchanged make requester revision and receiver execution follow the injected task consequence in both directions. Across three independently trained seeds, correct capability feedback closes the paired local-information gap from 50% to 100%. Multi-step commitments improve held-out-template success by 6.9 points while reducing model decisions by 32%. At matched closed-loop quality on 128 held-out semantic clusters, Short DSL reduces peer traffic by 92.8% and median time-to-commitment by 68.2% relative to controlled free-form communication. These results identify executable task consequences as the coordination unit connecting distributed local reasoning to verified joint action.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。