cs.AIAug 19, 2026

Outcome Monitors: Recovery Affordances for Silent Tool Failures

Authors: Sugam Panthi, Rabab Abdelfattah

Organizations: The University of Southern Mississippi

Abstract

When a tool call times out, the agent sees the failure and can route around it. A cached error page or negative price can instead arrive in the expected format and be consumed as fact. We introduce Outcome Monitors, which detect violations of outcome contracts mined from task-disjoint traces or derived from public schemas. On a violation, the monitor preserves the result and issues a nonbinding receipt naming the violated property and public recovery tools. In frozen, prespecified evaluations with injected failures, Outcome Monitors raise ToolMaze completion from 10.9% to 28.1% across four models in two provider families and replicate in a third. In tau-bench retail, completion improves by 14.0 and 12.0 points on two tiers. In separate ToolMaze controls, removing the recovery-tool list eliminates the measured gain and restoring it recovers the effect; diagnostic detail and timing produce no detectable differences. Gains concentrate where the fault blocks completion. On a suite transcribed from a published incident taxonomy, detection outside the mined vocabulary falls to 46%, though delivery continues and completion is unchanged. Recovery tools are the active receipt content in these controls; extending detection beyond the contract vocabulary remains open.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Loud Failures, Quiet Failures: Fault Detection and Recovery in Tool-Using Language Model Agents

    Oct 7, 2026Obada KraishanTool-Using AgentsLLM Agent Reliability

  2. Structural Baselines Matter for Agent Failure Detection and Attribution

    Oct 12, 2026Ramesh Arvind Naagarajan, Stefan StreifAgent Failure AnalysisFailure Attribution for LLM Agents