# Verified Tool Calls Improve LLM Agent Reliability Under Non-Atomic Failures

arXiv: https://arxiv.org/abs/2608.02645 · HTML: https://mlsanity.com/paper/2608.02645/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use.
- Builds on 4 of its 16 references that are in the map.
- First posted on arXiv 31 Jul 2026.

## Placed in

- LLM agents and tool use / [Tool learning and function calling](https://mlsanity.com/agents/tool-learning-and-function-calling/)

## Builds on (most cited first, 4 of 4)

- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [On the Tool Manipulation Capability of Open-source Large Language Models](https://mlsanity.com/paper/2305.16504/) (2023)
- [When Agents Fail to Act: A Diagnostic Framework for Tool Invocation Reliability in Multi-Agent LLM Systems](https://mlsanity.com/paper/2601.16280/) (2026)
- [Recoverability Has a Law: The ERR Measure for Tool-Augmented Agents](https://mlsanity.com/paper/2601.22352/) (2026)

## Built on by (most cited first, 8 of 8)

- [Where Does Exactly-Once Live? Model, Harness, and Tool-Contract Effects on Duplicate Side Effects in LLM Agents](https://mlsanity.com/paper/2609.29095/) (2026)
- [Callability Is Not Operability: Controlled Interface Interventions for LLM Agents](https://mlsanity.com/paper/2608.23628/) (2026)
- [FinalityBench: An Effect-Level Benchmark for Agent Decisions Under Delayed and Conflicting Financial Finality](https://mlsanity.com/paper/2609.04706/) (2026)
- [UndoBench: Separating Task Competence from Recovery Capability in Tool-Using AI Agents](https://mlsanity.com/paper/2610.05622/) (2026)
- [Toolcompass: Guiding Tool Trialing, Not Suppressing It](https://mlsanity.com/paper/2609.25678/) (2026)
- [Stale Does Not Mean Unsafe: Guard Precision for Tool-Using LLM Agents under Infrastructure State Races](https://mlsanity.com/paper/2609.29522/) (2026)
- [Beyond Approved Actions: Runtime Validation of Persistent Outcomes in Agent Workflows](https://mlsanity.com/paper/2609.31301/) (2026)
- [RSure-Agent: Reliable Use of Tool Observations for Remote Sensing Agents](https://mlsanity.com/paper/2610.04836/) (2026)

## Abstract (arXiv)

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.