[2602.22302] Agent Behavioral Contracts: Formal Specification and Runtime Enforcement for Reliable Autonomous AI Agents

alpha (the natural drift rate) bound behavioral drift to D* = alpha/gamma in expectation, with Gaussian concentration in the stochastic setting. We establish sufficient conditions for safe contract composition in multi-agent chains and derive probabilistic degradation bounds. We implement ABC in AgentAssert, a runtime enforcement library, and evaluate on AgentContract-Bench, a benchmark of 200 scenarios across 7 models from 6 vendors. Results across 1,980 sessions show that contracted agents detect 5.2-6.8 soft violations per session that uncontracted baselines miss entirely (p

alpha (the natural drift rate) bound behavioral drift to D* = alpha/gamma in expectation, with Gaussian concentration in the stochastic setting. We establish sufficient conditions for safe contract composition in multi-agent chains and derive probabilistic degradation bounds. We implement ABC in AgentAssert, a runtime enforcement library, and evaluate on AgentContract-Bench, a benchmark of 200 scenarios across 7 models from 6 vendors. Results across 1,980 sessions show that contracted agents detect 5.2-6.8 soft violations per session that uncontracted baselines miss entirely (p

-->

Computer Science > Artificial Intelligence

arXiv:2602.22302 (cs)

[Submitted on 25 Feb 2026]

Title:Agent Behavioral Contracts: Formal Specification and Runtime Enforcement for Reliable Autonomous AI Agents

Authors:Varun Pratap Bhardwaj<br>View a PDF of the paper titled Agent Behavioral Contracts: Formal Specification and Runtime Enforcement for Reliable Autonomous AI Agents, by Varun Pratap Bhardwaj

View PDF<br>HTML (experimental)

Abstract:Traditional software relies on contracts -- APIs, type systems, assertions -- to specify and enforce correct behavior. AI agents, by contrast, operate on prompts and natural language instructions with no formal behavioral specification. This gap is the root cause of drift, governance failures, and frequent project failures in agentic AI deployments. We introduce Agent Behavioral Contracts (ABC), a formal framework that brings Design-by-Contract principles to autonomous AI agents. An ABC contract C = (P, I, G, R) specifies Preconditions, Invariants, Governance policies, and Recovery mechanisms as first-class, runtime-enforceable components. We define (p, delta, k)-satisfaction -- a probabilistic notion of contract compliance that accounts for LLM non-determinism and recovery -- and prove a Drift Bounds Theorem showing that contracts with recovery rate gamma > alpha (the natural drift rate) bound behavioral drift to D* = alpha/gamma in expectation, with Gaussian concentration in the stochastic setting. We establish sufficient conditions for safe contract composition in multi-agent chains and derive probabilistic degradation bounds. We implement ABC in AgentAssert, a runtime enforcement library, and evaluate on AgentContract-Bench, a benchmark of 200 scenarios across 7 models from 6 vendors. Results across 1,980 sessions show that contracted agents detect 5.2-6.8 soft violations per session that uncontracted baselines miss entirely (p

Comments:<br>71 pages, 7 figures, 14 tables. Patent pending. Also available on Zenodo: DOI https://doi.org/10.5281/zenodo.18775393

Subjects:

Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA); Software Engineering (cs.SE)

Cite as:<br>arXiv:2602.22302 [cs.AI]

(or<br>arXiv:2602.22302v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2602.22302

Focus to learn more

arXiv-issued DOI via DataCite

Related DOI:

https://doi.org/10.5281/zenodo.18775393

Focus to learn more

DOI(s) linking to related resources

Submission history<br>From: Varun Pratap Bhardwaj [view email]<br>[v1]<br>Wed, 25 Feb 2026 18:42:56 UTC (217 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Agent Behavioral Contracts: Formal Specification and Runtime Enforcement for Reliable Autonomous AI Agents, by Varun Pratap Bhardwaj<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.AI

next >

new<br>recent<br>| 2026-02

Change to browse by:

cs<br>cs.MA<br>cs.SE

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

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...