When Should an AI Workflow Release? Always-Valid Inference for Black-Box Generate-Verify Systems

• URL: http://arxiv.org/abs/2605.12947v1
• Date: Wed, 13 May 2026 03:30:39 GMT
• Title: When Should an AI Workflow Release? Always-Valid Inference for Black-Box Generate-Verify Systems
• Abstract summary: LLM-enabled AI increasingly produce outputs through iterative generate-evaluate-revise loops.<n>This raises a statistical challenge because deployment-time evaluator scores are adaptively generated and repeatedly monitored.<n>We propose an always-valid release wrapper for existing generator-evaluator pipelines.
• Score: 2.805986764620217
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LLM-enabled AI workflows increasingly produce outputs through iterative generate-evaluate-revise loops. Each iteration can improve the candidate, but it also creates a release decision: when to stop and output the current result? This raises a statistical challenge because deployment-time evaluator scores are adaptively generated and repeatedly monitored, yet the likelihood models or exchangeability assumptions typically used for calibration are unavailable. We propose an always-valid release wrapper for existing generator-evaluator pipelines. The wrapper builds a hard-negative reference pool of high-scoring failures, calibrates deployment-time evaluator scores against this pool, and accumulates the resulting evidence with an e-process. This separates two roles: the reference pool turns black-box scores into conservative evidence, while the e-process provides validity under optional stopping. In theory, we show that a conservative reference pool yields finite-sample control of the probability of releasing on infeasible tasks, that is, tasks for which the given workflow is not capable of producing a reliable solution. We also characterize conditions under which the same conservative rule still achieves nontrivial release on feasible tasks. In an MBPP+ coding-agent case study, the wrapper reduces premature incorrect release relative to baseline stopping rules while still releasing on tasks for which the workflow repeatedly accumulates moderate supporting evidence.

Related papers

• Efficient Online LLM Watermark Detection via Rao-Blackwellized E-Processes [3.2639022787260266]
  We develop an efficient online watermark detection framework with anytime-valid inference based on Rao-Blackwellized e-processes.<n> Simulations and experiments on real-generated text demonstrate efficient online detection with rigorous anytime-valid guarantees.
  arXiv  Detail & Related papers  (2026-07-24T04:10:36Z)
• AEVAL: From Anecdotal to Deterministic Testing for Agentic Skill Workflows [1.6785141970297952]
  AEVAL (Agentic Evaluation) is a CI-integrated framework that replaces this practice with a deterministic, reproducible test pipeline for agentic skills.<n>Every skill change triggers a test event: the skill runs against a developer declared evaluation contract inside an automated executor.<n>A key ingredient is a structural separation between executor and grader, preventing a subtle but pervasive failure mode.
  arXiv  Detail & Related papers  (2026-07-16T21:33:05Z)
• TTHE: Test-Time Harness Evolution [50.26245555541721]
  Existing approaches optimize such harnesses before deployment, searching training or development data for a fixed agent workflow that is then frozen at test time.<n>We ask whether the harness can instead be optimized during evaluation itself, using only the unlabeled execution traces the agent produces on the test inputs.<n>During evaluation, TTHE maintains a population of candidate harnesses and refines them through an agentic proposer that reasons over their execution traces.<n>A judge then commits an improved harness from execution-derived proxy signals, and the selected program persists to govern subsequent inputs.
  arXiv  Detail & Related papers  (2026-07-09T05:53:39Z)
• LLM-as-a-Verifier: A General-Purpose Verification Framework [74.40111651545979]
  We introduce LLM-as-a-Verifier, a general-purpose verification framework.<n>It provides fine-grained feedback for agentic tasks without requiring additional training.<n>It achieves state-of-the-art performance on several benchmarks.
  arXiv  Detail & Related papers  (2026-07-06T17:59:35Z)
• What to Test Next: Interpretable Coverage Gap Discovery in Driving VLMs [52.50210189669399]
  Driving vision-language models (VLMs) must accurately understand scenes across diverse conditions defined by Operational Design Domains (ODDs)<n>We propose SliceScorer, a deterministic scoring rule for missing-slice recommendation.<n>We show that SliceNav surfaces high-risk coverage gaps more effectively than prior slice-discovery methods.
  arXiv  Detail & Related papers  (2026-06-01T03:18:01Z)
• PROTEA: Offline Evaluation and Iterative Refinement for Multi-Agent LLM Workflows [1.6429511119132734]
  Multi-agent LLMs often outperform single-prompt baselines, but they remain difficult to debug and refine.<n>We present PROTEA, a unified interface for offline, test-driven improvement of multi-agent systems.
  arXiv  Detail & Related papers  (2026-05-18T08:22:14Z)
• Interactive Critique-Revision Training for Reliable Structured LLM Generation [18.00222080273147]
  We propose DPA-GRPO, a paired-action training method for a two-player generator--verifier game with structured verifier interventions.<n>We analyze the unregularized game and show that positive probability on strictly lower-reward intervention or revision actions creates a profitable unilateral deviation.<n>Experiments on TaxCalc TY24 show that DPA-GRPO improves structured decision accuracy over zero-shot generation and generator-only RL baselines.
  arXiv  Detail & Related papers  (2026-05-08T17:00:38Z)
• CITE: Anytime-Valid Statistical Inference in LLM Self-Consistency [10.34950275095264]
  We study anytime-valid certification of a prespecified target answer as unique mode of the model's response distribution.<n>We propose the Certification by Intersection-union Testing with E-processes (CITE) algorithm, which provably controls false certification at any prescribed level.<n>We also prove an category-set-size-free stopping-time rate, establish matching minimax lower bounds up to constants in the main regime, and extend the construction to confidence-weighted voting.
  arXiv  Detail & Related papers  (2026-05-07T08:41:51Z)
• LiveFMBench: Unveiling the Power and Limits of Agentic Workflows in Specification Generation [75.05397479715576]
  Large language models (LLMs) and agents have shown promising progress, but their true capabilities and failure modes remain unclear.<n>We present the first systematic and contamination-aware study of LLM- and agent-based formal specification generation for C programs.
  arXiv  Detail & Related papers  (2026-05-02T11:31:33Z)
• IMPACT-CYCLE: A Contract-Based Multi-Agent System for Claim-Level Supervisory Correction of Long-Video Semantic Memory [73.22944697933603]
  Existing pipelines produce opaque, end-to-end outputs that expose no intermediate state for inspection.<n>We present IMPACT-Cycle, a supervisory multi-agent system that reformulates long-video understanding as a multimodal iterative claim-level maintenance.
  arXiv  Detail & Related papers  (2026-04-22T03:03:33Z)
• Runtime Execution Traces Guided Automated Program Repair with Multi-Agent Debate [8.424102114588559]
  Automated Program Repair (APR) struggles with complex logic errors and silent failures.<n>Current LLM-based APR methods are mostly static, relying on source code and basic test outputs.<n>We propose TraceRepair, a multi-agent framework that leverages runtime facts as shared constraints for patch validation.
  arXiv  Detail & Related papers  (2026-04-03T02:23:25Z)
• Probabilistic Guarantees for Reducing Contextual Hallucinations in LLMs [0.0]
  Large language models (LLMs) frequently produce contextual hallucinations, where generated content contradicts or ignores information explicitly stated in the prompt.<n>We introduce a model-agnostic framework that provides explicit probabilistic guarantees for reducing hallucinations in this setting.<n>We prove that the probability that the judged pipeline fails decays at a rate determined by the judge's true and false-positive probabilities.
  arXiv  Detail & Related papers  (2026-01-02T10:52:33Z)
• CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal [84.71254539482369]
  Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures.<n>We present CARE, a failure-centric post-training framework for multimodal reasoning that turns errors into supervision.<n> CARE improves accuracy and training smoothness while explicitly increasing the share of learning signal that comes from failures.
  arXiv  Detail & Related papers  (2025-12-22T16:34:21Z)
• Eliminating Hallucination-Induced Errors in LLM Code Generation with Functional Clustering [0.0]
  We present functional clustering, a black-box wrapper that eliminates nearly all hallucination-induced errors while providing a tunable confidence score.<n>Our verifier preserves baseline pass@1 on solvable tasks yet slashes the error rate of returned answers from 65% to 2%.<n>Because the method requires only sampling and sandbox execution, it applies unchanged to closed-source APIs and future models.
  arXiv  Detail & Related papers  (2025-05-16T18:19:38Z)
• Sequential Kernelized Independence Testing [77.237958592189]
  We design sequential kernelized independence tests inspired by kernelized dependence measures.<n>We demonstrate the power of our approaches on both simulated and real data.
  arXiv  Detail & Related papers  (2022-12-14T18:08:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.