Skip to content

SINGED: Correct Outputs Do Not Certify Safe Execution in LLM Agents

Sep 2026 · arXiv.org · Vol abs/2609.35889 · 0 citations · 61 references
Computer Science

TL;DR

This work introduces SINGED (Source Integrity and the Nonidentifiability Gap in Execution Decisions for LLM Agents), a controlled benchmark covering five primary and two held-out task families and exposes a rank-, evidence-, and choice-sensitive outcome-to-execution gap.

Abstract

Tool-using language-model agents select and execute third-party artifacts. Different implementations can return the requested output while producing hidden execution effects that task-, attack-, or choice-based evaluations may miss. We study functional counterfeits: implementations that match benign alternatives on the requested output but add an effect forbidden by the task contract. We introduce SINGED (Source Integrity and the Nonidentifiability Gap in Execution Decisions for LLM Agents), a controlled benchmark covering five primary and two held-out task families. It varies displayed rank, evidence depth, decision policy, model release, and agent configuration, while task and process oracles verify the artifact and execution path. Across 7,549 audited trials, the randomized-rank study finds counterfeit execution in 45% (27/60) of rank-one trials and none at later ranks. Cross-candidate comparison eliminates shallow failures and reduces layered failures from 15.7% to 4.2%, but leaves dependency failures; its benefit is uncertain on unseen effects and public-package structures. Moreover, seven releases with no counterfeit executions when benign alternatives are available execute the counterfeit in 55/175 single-source cells after alternatives are removed. SINGED thus exposes a rank-, evidence-, and choice-sensitive outcome-to-execution gap: evaluation must connect correct outputs to execution paths.

View source

Similar papers

Preprint Aug 2026

When May an Agent Stop? Evidence-Carrying Termination for Tool-Using LLMs

Evidence-Carrying Termination (ECT): an agent may return COMPLETE only when a typed certificate binds every required answer claim to valid, in-scope trace evidence and a deterministic replay reconstructs the claimed value.

Jason Liu · 3 citations
Preprint Oct 2026

Compromise Is Not Consequence: Evaluating Task-Scoped Authorization in LLM Agents with Paired Replay

A tool-using model can follow a malicious instruction even when its credentials are valid. We study whether task-scoped authorization contains the resulting tool execution. Our paired-replay testbed samples a model request once and submits the same action, resource, and arguments to broad bearer, scoped JWT, sender-con...

Tural Hagverdiyev · 1 citation
Book Open access Oct 2026

Formal Runtime Verification for Tool-Using LLM Agents: An Offline Same-Benchmark Study on AgentDojo and STAC

Results show that formal temporal monitoring adds value exactly when the trace exposes trustworthy history, and quantify how far current benchmarks are from that point and propose a twelve-field enforcement-ready trace schema.

N. Kekatos, Stylianos Basagiannis, Marinelio Chintri et al. · 2 citations
#artificial intelligence Preprint Oct 2026

SpecGuard: Proving a Task Is Broken Before the Agent Cheats

As autonomous coding agents get increasingly deployed, the risk that accidental or adversarially injected misspecifications in tasks lead to dangerous agent behavior is critical to address. Prior work has shown that agents given such tasks rarely flag the conflict and instead cheat, editing tests or hard-coding expecte...

Param Biyani, K. Dvijotham · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.