arXiv:2512.07850v1 Announce Type: new
Abstract: Despite rapid progress in LLM agents, performance on long-horizon, tool-using tasks remains fragile. To better understand this fragility, we ask a simple question: emph{do all actions contribute equally to failure?} Analyzing execution traces on $tau$-Bench (Airline/Retail) and SWE-Bench Verified, we decompose trajectories into emph{mutating} (environment-changing) vs. non-mutating steps and formalize emph{decisive deviations}, earliest action, level divergences that flip success to failure. A logistic regression reveals that each additional deviation in a mutating action reduces the odds of success by upto $92%$ on Airline and upto $96%$ on Retail for SoTA models. In contrast, deviations in non-mutating actions have little to no effect. Errors also grow with context length as agents drift from role and act on stale constraints. Motivated by these observations, we introduce cm{}, a model-agnostic, gradient-free, test-time safeguard that (i) adds mutation-gated verification, (ii) injects emph{Targeted Reflection} before mutating steps, and (iii) performs block-based context cleaning. cm{} delivers consistent gains, e.g., Qwen3-Thinking: +28% emph{relative} on Airline, +11% on Retail, and +7% on SWE-Bench Verified; Claude: +9%/+7%. We further identify ceiling effects in $tau$-Bench, where annotation errors and underspecified tasks artificially cap model performance. To address this, we release $tau$-Bench Verified, which restores benchmark headroom through targeted revisions. Our results argue for action-level analysis, targeted safeguards, and reliable evaluations as prerequisites for robust multi-turn agents.