Metraipolis › archive › dc_1271b87db82e
Verified Tool Calls Improve LLM Agent Reliability Under Non-Atomic Failures — arXiv:2608.02645
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.02645
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T12:17:30.507Z
- SHA-256 of the archived text
39e79bd866b765048fd4681ae09e6169c4fd99fef399c1de1962254d30dbb49a- Stable URL of this page
https://metraipolis.com/documento/dc_1271b87db82e
How to cite
Verified Tool Calls Improve LLM Agent Reliability Under Non-Atomic Failures — arXiv:2608.02645 — arXiv (en), https://arxiv.org/abs/2608.02645 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1271b87db82e (Metraipolis archive dc_1271b87db82e, sha256 39e79bd866b765048fd4681ae09e6169c4fd99fef399c1de1962254d30dbb49a)
BibTeX
@misc{dc1271b87db82e,
title = {Verified Tool Calls Improve LLM Agent Reliability Under Non-Atomic Failures — arXiv:2608.02645},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.02645},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1271b87db82e; sha256 39e79bd866b765048fd4681ae09e6169c4fd99fef399c1de1962254d30dbb49a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.02645. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large Language Model (LLM) agents rely on external tools to perform multistage tasks. Existing agent frameworks typically assume that tool calls are atomic and return binary success or failure signals. However, real-world systems exhibit non-atomic behaviors such as timeouts after dispatch, delayed visibility, and partial state updates. These mismatches lead to reliability issues including duplicate actions, task success, and unnecessary tool executions. A lightweight, verification-aware tool wrapper is introduced that augments tool calls with postcondition verification, verify-before-retry logic, and idempotency keys. The approach is evaluated in a controlled simulated environment with injected non-atomic failures across multiple task templates. The results demonstrate that the proposed method significantly reduces duplicate actions, while maintaining comparable task success rates. Overall, the findings suggest that strengthening tool interaction semantics is a promising direction for improving LLM agent reliability without requiring modifications to the underlying language model. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI). Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.02645 — 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 2026-10-31T12:05:52.906Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).