相关论文: Pramana: A Protocol-Layer Treatment of Claim Verif…
Operating LLMs as coordinated multi-agent research systems over multi-hour runs surfaces failure modes that single-shot evaluation cannot: upstream providers throttle without warning, sub-agents drift the task to fit accessible tools,…
The integration of Formal Verification tools with Large Language Models (LLMs) offers a path to scale software verification beyond manual workflows. However, current methods remain unreliable: without a solid theoretical footing, the…
As autonomous AI agents increasingly call other agents to complete tasks on behalf of a human principal, a structural accountability gap has emerged: the calling agent accepts the terms of service of the callee without any protocol-level…
Large Language Models (LLMs) demonstrate potential in complex legal tasks like argument generation, yet their reliability remains a concern. Building upon pilot work assessing LLM generation of 3-ply legal arguments using human evaluation,…
The companion paper introduced a four-level verification lattice on agent-skill manifests (unverified, declared, tested, formal) and left the top level aspirational. This paper closes that gap. We give a precise semantics for skill…
Register-Transfer Level (RTL) verification is a primary bottleneck, consuming 60-70% of development time. While Large Language Models (LLMs) show promise for RTL automation, their performance and research focus have overwhelmingly centered…
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…
Since 2022, AI-powered coding assistants have produced contradictory evidence: controlled studies report 20-56% productivity gains on well-scoped tasks, while the most rigorous RCT documents a 19% slowdown for experienced developers, and…
Large language models produce fluent text but struggle with systematic reasoning, often hallucinating confident but unfounded claims. When Apple researchers added irrelevant context to mathematical problems, LLM performance degraded by 65%…
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…
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…
Verifying LLM-generated systems code is hard: bugs are prevalent, formal specifications are missing, and safety contracts are encoded implicitly at call sites rather than enforced at function boundaries. We propose agentic model checking, a…
The rapid adoption of Large Language Models (LLMs) in interactive systems has enabled the creation of dynamic, open-ended Role-Playing Agents (RPAs). However, evaluating these agents remains a significant challenge, as standard NLP metrics…
High-precision CNC machining of free-form aerospace components requires bounded compensations informed by inspection, simulation, and process knowledge. Off-the-shelf large language model (LLM) assistants can generate text, but they do not…
Large language models (LLMs) remain unreliable for high-stakes claim verification due to hallucinations and shallow reasoning. While retrieval-augmented generation (RAG) and multi-agent debate (MAD) address this, they are limited by…
Automated Program Repair (APR) agents leverage Large Language Models (LLMs) to autonomously diagnose and fix software bugs through reasoning, planning, and tool use. Despite impressive leaderboard gains on benchmarks such as SWE-bench,…
Large language models (LLMs) are increasingly used for automated tutoring, but their reliability in structured symbolic domains remains unclear. We study step-level feedback for propositional logic proofs, which require precise symbolic…
Multi-Agent Systems (MAS) built on Large Language Models (LLMs) often exhibit high variance in their reasoning trajectories. Process verification, which evaluates intermediate steps in trajectories, has shown promise in general reasoning…
Tool-using large language model (LLM) agents are increasingly deployed in settings where their reliable behavior is governed by strict procedural manuals. Ensuring that such agents comply with the rules from these manuals is challenging, as…
Verifiers--functions assigning rewards to agent behavior--have been key to AI progress in math, code, and games. However, extending gains to domains without clear-cut success criteria remains a challenge: while humans can recognize desired…