Google 将 Antigravity 的 /teamwork 多智能体工作流开放给外部研究者
Google 在 Antigravity 中开放 /teamwork 多智能体工作流及 /boost、Deep Review 等工具,外部研究者现在可以用 Gemini 4 模型调用。
推荐理由:Google 公开了 /teamwork 多智能体工作流在数学证明、化学结构解析和内核优化上的具体结果,并开放给外部研究者使用。
Evidence-Guided Recovery for AI Agents with Ambiguous Tool Outcomes and Partial Execution
Genliang Zhu · Xiaobo Chen · Ziyuan Wang · Chu Wang
工具超时会使 AI 智能体面临模糊的工具结果与部分执行:某个动作可能已失败、已提交或仍在进行中,而其他工作流步骤已经完成。研究将证据引导的任务恢复形式化为在已批准义务、提供方能力以及与公开证据相容的状态上的恢复问题。共享的可接受性检查处理密钥过期、授权时序、依赖关系与残余效应;终止证书将实际目标满足与公开支持的安全完成区分开。已知模型实现将标准观测 contingent 规划与单独实现的效应历史裁决器结合。在 37 项分配的有限研究中,规划与三个主动控制各认证 28 次完成;节省四个合成费用单位却带来额外计算。随后一项预注册的分配留出比较,用两个本地模型包评估规划建议与证据提示。在 19 个先前开发任务族的 58 个配对单元中,建议认证 30 次完成,对照为 9 次,相差 36.2 个百分点(精确族符号翻转 p=0.0078),使用 272 个提议对 399 个。全部 116 条轨迹通过独立重放。两个模型均表现出正向完成差异。该比较在共同防护下测量所评估的建议接口;搜索与规则建议需要单独的匹配比较。未知与移交结果保持显式,保证与声明的提供方能力绑定,而非任意第三方的恰好一次执行。
尚无解读。
arXiv:2610.41453v1 Announce Type: new Abstract: Tool timeouts can leave AI agents facing ambiguous tool outcomes and partial execution: an action may have failed, committed or remained in flight while other workflow steps have already completed. We formulate evidence-guided task recovery over approved obligations, provider capabilities and states compatible with public evidence. A shared admissibility check handles key expiry, authorization timing, dependencies and residual effects; a terminal certificate separates actual goal satisfaction from publicly supported safe completion. The known-model implementation combines standard observation-contingent planning with a separately implemented effect-history adjudicator. In a finite study of 37 assignments, planning and three active controls each certify 28 completions; four saved synthetic fee units incur additional computation. A preregistered assignment-held-out comparison then evaluates planning advice against evidence prompting with two local model bundles. Across 58 paired units in 19 previously developed task families, advice certifies 30 completions versus 9, a 36.2-percentage-point difference (exact family sign-flip p=0.0078), using 272 proposals versus 399. All 116 trajectories pass independent replay. Both models exhibit a positive completion difference. The comparison measures the evaluated advice interface under a common shield; search-versus-rule advice requires a separate matched comparison. Unknown and handoff outcomes remain explicit, with guarantees tied to the declared provider capabilities rather than arbitrary third-party exactly-once execution.
Google 在 Antigravity 中开放 /teamwork 多智能体工作流及 /boost、Deep Review 等工具,外部研究者现在可以用 Gemini 4 模型调用。
推荐理由:Google 公开了 /teamwork 多智能体工作流在数学证明、化学结构解析和内核优化上的具体结果,并开放给外部研究者使用。