Skip to content
AI News HubLIVE
Original source2 min read

TwinCheck: Evidence-Grounded Negative-Twin Verification for Stateful Tool Agents

Summary

arXiv:2609.26911v1 Announce Type: new Abstract: A single locally plausible tool call can derail an otherwise successful agent trajectory. Suspicion alone does not justify intervention, because the replacement itself can introduce the very failure verification is meant to prevent. We introduce TwinCheck, an inference-time verification policy that considers replacement only when the trace satisfies an evidence condition tied to a trace-local failure hypothesis. It constructs a trace-grounded counterfactual alternative, a negative twin, and replaces the agent's proposal only if the twin passes structural checks and the pairwise verifier prefers it in both candidate orders. For paired evaluation, exact replay holds the agent's parsed responses and actions fixed until the first accepted replac…

SourcearXiv AIAuthor: Jiaxuan Dai, Tianyi Huang
TwinCheck: Evidence-Grounded Negative-Twin Verification for Stateful Tool Agents
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 22 Sep 2026]

Title:TwinCheck: Evidence-Grounded Negative-Twin Verification for Stateful Tool Agents

View a PDF of the paper titled TwinCheck: Evidence-Grounded Negative-Twin Verification for Stateful Tool Agents, by Jiaxuan Dai and 1 other authors

View PDF HTML (experimental)

Abstract:A single locally plausible tool call can derail an otherwise successful agent trajectory. Suspicion alone does not justify intervention, because the replacement itself can introduce the very failure verification is meant to prevent. We introduce TwinCheck, an inference-time verification policy that considers replacement only when the trace satisfies an evidence condition tied to a trace-local failure hypothesis. It constructs a trace-grounded counterfactual alternative, a negative twin, and replaces the agent's proposal only if the twin passes structural checks and the pairwise verifier prefers it in both candidate orders. For paired evaluation, exact replay holds the agent's parsed responses and actions fixed until the first accepted replacement, separating intervention effects from resampling. In the primary analysis of 159 multi-turn BFCL V4 tasks with complete exact-replay pairs, the complete policy raises task success for GPT-5.6 Sol from 45.3% to 58.5% (95% task-bootstrap CI [8.2, 18.8]), with no observed success-to-failure regressions. Together, these findings recast execution-boundary repair as a constrained comparison, making the counterfactual action itself the object of verification.

Subjects:

Artificial Intelligence (cs.AI)

Cite as: arXiv:2609.26911 [cs.AI]

(or arXiv:2609.26911v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2609.26911

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Tianyi Huang [view email] [v1] Tue, 22 Sep 2026 18:09:40 UTC (1,647 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled TwinCheck: Evidence-Grounded Negative-Twin Verification for Stateful Tool Agents, by Jiaxuan Dai and 1 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.AI

new | recent | 2026-09

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
  • arXiv:2609.26911v1 Announce Type: new Abstract: A single locally plausible tool call can derail an otherwise successful agent trajectory. Suspicion alone does not justify interven…

Highlights and analysis are generated automatically and may contain errors. Check the original source.