AI News HubLIVE
原文2 min read

MAVEN: Improving Generalization in Agentic Tool Calling

MAVEN (Modular Agentic Verification and Execution Network) is a lightweight symbolic reasoning scaffold designed to enhance generalization in tool-calling environments through structured decomposition, adaptive tool orchestration, and intermediate verification. On the MAVEN-Bench stress test, MAVEN improves the GPT-OSS-120b base model from 48% to 71% accuracy without additional training, using an open-weight backbone at roughly 1/10 the cost of proprietary baselines.

SourcearXiv AIAuthor: Omkar Ghugarkar, Vishvesh Bhat, Muhammad Ahmed Mohsin, Asad Aali

[2605.30738] MAVEN: Improving Generalization in Agentic Tool Calling

[Submitted on 29 May 2026]

Title:MAVEN: Improving Generalization in Agentic Tool Calling

View a PDF of the paper titled MAVEN: Improving Generalization in Agentic Tool Calling, by Omkar Ghugarkar and 3 other authors

View PDF HTML (experimental)

Abstract:Generalization across agentic tool-calling environments remains a central challenge for reliable agentic reasoning systems. Although large language models achieve strong results on individual benchmarks, their ability to compose reasoning strategies, preserve intermediate states, and coordinate tools across domains remains underexplored. We present MAVEN (Modular Agentic Verification and Execution Network), a lightweight symbolic reasoning scaffold for structured decomposition, adaptive tool orchestration, and intermediate verification. We evaluate MAVEN across established tool-calling benchmarks, including BFCL v3, TauBench, Tau2Bench, AceBench, and introduce MAVEN-Bench, a stress-test benchmark for multi-step mathematical and physical reasoning with explicit verification and adversarial task composition. MAVEN-Bench exposes a substantial gap between partial reasoning quality and end-to-end task success; in direct MAVEN-Bench runs, MAVEN improves its GPT-OSS-120b base model from 48% to 71% accuracy without additional training. It also remains competitive with frontier proprietary baselines while using an open-weight backbone with an estimated cost ratio of roughly 1/10, suggesting that lightweight verification-centered scaffolds can strengthen compositional reasoning and motivate more process-aware evaluation of agents in the wild.

Subjects:

Artificial Intelligence (cs.AI)

Cite as: arXiv:2605.30738 [cs.AI]

(or arXiv:2605.30738v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2605.30738

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Vishvesh Bhat [view email] [v1] Fri, 29 May 2026 02:02:31 UTC (319 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled MAVEN: Improving Generalization in Agentic Tool Calling, by Omkar Ghugarkar and 3 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.AI

new | recent | 2026-05

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?)