Metraipolis › archive › dc_0a287d694bfa

Loud Failures, Quiet Failures: Fault Detection and Recovery in Tool-Using Language Model Agents — arXiv:2610.10062

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.10062
License (as archived): CC0-1.0
Archived: 2026-10-08T11:09:43.856Z
SHA-256 of the archived text: d230c1d32f157ec855fddee7f9feb610bd689a51009787b1c9478911c4724940
Stable URL of this page: https://metraipolis.com/documento/dc_0a287d694bfa

How to cite

Loud Failures, Quiet Failures: Fault Detection and Recovery in Tool-Using Language Model Agents — arXiv:2610.10062 — arXiv (en), https://arxiv.org/abs/2610.10062 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0a287d694bfa (Metraipolis archive dc_0a287d694bfa, sha256 d230c1d32f157ec855fddee7f9feb610bd689a51009787b1c9478911c4724940)

BibTeX

@misc{dc0a287d694bfa,
  title = {Loud Failures, Quiet Failures: Fault Detection and Recovery in Tool-Using Language Model Agents — arXiv:2610.10062},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10062},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0a287d694bfa; sha256 d230c1d32f157ec855fddee7f9feb610bd689a51009787b1c9478911c4724940},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10062. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Tool-using agents are usually scored on whether they finish a task while the tools work. Deployments are less forgiving: services time out, endpoints disappear, parameter names change, and results come back well formed but wrong. Prior work has shown that language models over-trust tool outputs that fail silently; we ask how that over-trust plays out across the stages of failure handling in multi-turn agents. Wrapping the executable environments of an established function-calling benchmark in a fault-injection layer, we inject one of four typed faults at a controlled point in the trajectory and record whether the agent notices, changes plan, recovers the task, or repeats itself. Six models from three families, half of them reasoning variants, ran 1,920 trials over 24 multi-step tasks. Agents treat a failure as a problem in 91.3% of trials when the tool returns an explicit error, but in 58.8% of trials when it returns a plausible wrong value, against a 26.8% rate of reporting problems when nothing was wrong. Reasoning models are not better placed: paired against instruct siblings, they notice less (-9.3 points, p < .001) and change plan more (+10.4 points, p < .001), and recovery is unchanged (p = .512). Because agents are stochastic, two fault-free runs of the same task end in the same state only 63.3% of the time; against that baseline, only a missing tool clearly lowers recovery (39.9%), while timeouts, schema drift, and corruption stay within run-to-run variation. After a fault, agents return to the same tool three or more times in a row in up to 22.2% of trials, though strictly identical repeats are rare. A prompt line asking the agent to check each result did not move detection. Agents respond to the error channel rather than to the content of what a tool returns, so failures that stay inside the expected format pass through.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.10062 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T10:14:05.972Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).