Evidence-Guided Recovery for AI Agents with Ambiguous Tool Outcomes and Partial Execution
Genliang Zhu, Xiaobo Chen, zwang, Chu Wang
Evidence-Guided Recovery for AI Agents with Ambiguous Tool Outcomes and Partial Execution: 4 upvotes on Hugging Face Daily Papers, #26 of 34 papers on 2026-11-13. Day-by-day upvote history.
Upvotes over time
It had 3 upvotes by its first day, 3 upvotes by the next day, 4 upvotes by day 3, 4 upvotes by day 7, and has 4 now. It ranked #117 of 167 papers in its week and #361 of 520 in its month.
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.
Paper page on Hugging Face · arXiv
Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.