相关论文: Evidence-Bound Autonomous Research (EviBound): A G…

LLM applications are AI systems whose nondeterministic outputs and evolving model behavior make traditional testing insufficient for release governance. We present an automated self-testing framework that introduces quality gates with…

Financial AI systems must produce answers grounded in specific regulatory filings, yet current LLMs fabricate metrics, invent citations, and miscalculate derived quantities. These errors carry direct regulatory consequences as the EU AI…

Large Language Models (LLMs) frequently produce hallucinated statements that are assigned high likelihood by the model itself, exposing a fundamental limitation of probability-based verification. This suggests that hallucination is often…

Autonomous research agents produce competitive solutions and professional-looking manuscripts, yet their outputs contain verifiability failures undetectable by surface-level evaluation: fabricated citations, unreproducible scores, and…

Current AI-assisted engineering workflows lack a built-in mechanism to maintain task-level verification and regulatory traceability at machine-speed delivery. Agile V addresses this gap by embedding independent verification and audit…

As multi-agent systems move from short interactions to tool-using workflows with specialized roles and persistent state, completion becomes a runtime-control problem rather than a purely generative one. This preprint studies verify-gated…

Modern Large Language Model (LLM) systems are assembled from third-party artifacts such as pre-trained weights, fine-tuning adapters, datasets, dependency packages, and container images, fetched through automated pipelines. This speed comes…

Self-evolving agents should not train on examples they cannot justify. Data-free self-evolving search agents offer a scalable route to systems that generate their own questions, answer them, and improve from their own feedback without human…

Large language model agents increasingly operate through environment-facing scaffolds that expose files, web pages, APIs, and logs. These observations influence tool use, state tracking, and action sequencing, yet their reliability and…

While Large Language Models have transformed how we interact with AI systems, they suffer from a critical flaw: they confidently generate false information that sounds entirely plausible. This hallucination problem has become a major…

The development of LLM-based autonomous agents for end-to-end software development represents a significant paradigm shift in software engineering. However, the scientific evaluation of these systems is hampered by significant challenges,…

Multimodal agents increasingly choose tool calls from screenshots, documents, and webpages, where a false perceptual claim can turn hallucination from an answer-quality error into an authorization failure. We formalize this failure mode as…

Vision-language models (VLMs) frequently generate hallucinated content plausible but incorrect claims about image content. We propose a training-free self-correction framework enabling VLMs to iteratively refine responses through…

Formal verification is the next frontier for ensuring the correctness of code generated by Large Language Models (LLMs). While methods that co-generate code and formal specifications in formal languages, like Dafny, can, in principle, prove…

Large language models often produce unsupported claims. We frame this as a misclassification error at the output boundary, where internally generated completions are emitted as if they were grounded in evidence. This motivates a composite…

Autonomous GUI agents based on vision-language models (VLMs) often assume deterministic environment responses, generating actions without verifying whether previous operations succeeded. In real-world settings with network latency,…

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse applications, from open-domain question answering to scientific writing, medical decision support, and legal analysis. However, their tendency to generate…

Machine learning systems in fraud detection, credit scoring, and clinical risk assessment operate under delayed ground truth: outcome labels arrive days to months after the decision they evaluate. During this blind period, governance…

AI agents that execute tasks via tool calls frequently hallucinate results - fabricating tool executions, misstating output counts, or presenting inferences as facts. Recent approaches to verifiable AI inference rely on zero-knowledge…

We introduce ProofGrid, a benchmark suite for evaluating LLM reasoning through machine-checkable proofs rather than final answers alone. ProofGrid contains 15 tasks spanning proof writing, proof checking, proof masking, and proof…