AgentAssay: Token-Efficient Regression Testing for Non-Deterministic AI Agent Workflows
Fuente:
arXiv
Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908861685825536 |
|---|---|
| author | Bhardwaj, Varun Pratap |
| author_facet | Bhardwaj, Varun Pratap |
| contents | Autonomous AI agents are deployed at unprecedented scale, yet no principled methodology exists for
verifying that an agent has not regressed after changes to its prompts, tools, models, or
orchestration logic. We present AgentAssay, the first token-efficient framework for regression
testing non-deterministic AI agent workflows, achieving 78-100% cost reduction while maintaining
rigorous statistical guarantees. Our contributions include: (1) stochastic three-valued verdicts
(PASS/FAIL/INCONCLUSIVE) grounded in hypothesis testing; (2) five-dimensional agent coverage metrics;
(3) agent-specific mutation testing operators; (4) metamorphic relations for agent workflows; (5)
CI/CD deployment gates as statistical decision procedures; (6) behavioral fingerprinting that maps
execution traces to compact vectors, enabling multivariate regression detection; (7) adaptive budget
optimization calibrating trial counts to behavioral variance; and (8) trace-first offline analysis
enabling zero-cost testing on production traces. Experiments across 5 models (GPT-5.2, Claude Sonnet
4.6, Mistral-Large-3, Llama-4-Maverick, Phi-4), 3 scenarios, and 7,605 trials demonstrate that
behavioral fingerprinting achieves 86% detection power where binary testing has 0%, SPRT reduces
trials by 78%, and the full pipeline achieves 100% cost savings through trace-first analysis.
Implementation: 20,000+ lines of Python, 751 tests, 10 framework adapters. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_02601 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AgentAssay: Token-Efficient Regression Testing for Non-Deterministic AI Agent Workflows Bhardwaj, Varun Pratap Artificial Intelligence Software Engineering D.2.5; I.2.1 Autonomous AI agents are deployed at unprecedented scale, yet no principled methodology exists for verifying that an agent has not regressed after changes to its prompts, tools, models, or orchestration logic. We present AgentAssay, the first token-efficient framework for regression testing non-deterministic AI agent workflows, achieving 78-100% cost reduction while maintaining rigorous statistical guarantees. Our contributions include: (1) stochastic three-valued verdicts (PASS/FAIL/INCONCLUSIVE) grounded in hypothesis testing; (2) five-dimensional agent coverage metrics; (3) agent-specific mutation testing operators; (4) metamorphic relations for agent workflows; (5) CI/CD deployment gates as statistical decision procedures; (6) behavioral fingerprinting that maps execution traces to compact vectors, enabling multivariate regression detection; (7) adaptive budget optimization calibrating trial counts to behavioral variance; and (8) trace-first offline analysis enabling zero-cost testing on production traces. Experiments across 5 models (GPT-5.2, Claude Sonnet 4.6, Mistral-Large-3, Llama-4-Maverick, Phi-4), 3 scenarios, and 7,605 trials demonstrate that behavioral fingerprinting achieves 86% detection power where binary testing has 0%, SPRT reduces trials by 78%, and the full pipeline achieves 100% cost savings through trace-first analysis. Implementation: 20,000+ lines of Python, 751 tests, 10 framework adapters. |
| title | AgentAssay: Token-Efficient Regression Testing for Non-Deterministic AI Agent Workflows |
| topic | Artificial Intelligence Software Engineering D.2.5; I.2.1 |
| url | https://arxiv.org/abs/2603.02601 |