Evidence-Grounded Verified Agentic Reasoning: A Path Toward Eliminating LLM Hallucination in Empirical Inference via Tool-Attested Kernel Proofs
Tool access alone does not make LLM empirical reasoning governable: accepted outputs need not descend from attested evidence, and accepted deductions need not hold up under formal scrutiny. We present EG-VAR (Evidence-Grounded Verified Agentic Reasoning), a Lean 4-based tool-calling architecture in which the Lean kernel is the sole minter of Verified claims via tool-attestation axioms and declared source lifts. Every verified output structurally descends from an attested tool call (Thm. 3.1) and a kernel-checked chain of valid inference (Thm. 3.2); residual outputs are honest Abstain with a replayable audit trail. On a subcollection of TableBench numerical reasoning (n=120), EG-VAR attains 120/120 versus a 95% same-tool baseline; on counterfactual stress tests (5 domains x 2 models), EG-VAR stays 100% source-faithful while same-tool drops to 80-90% (no-tool 50-80%). With the LLM as deployment-time formalizer, residual semantic-formalization error is 3.3% on Sonnet and 1.7% on Opus. We position EG-VAR as a technical-governance interface for high-stakes empirical claims: a formal sidecar makes the target proposition, source scope, evidence boundary, proof obligation, and abstention condition auditable, eliminating unsupported Verified outputs today while turning formalization errors, lift and source-authority disputes, ambiguities, and abstentions into explicit audit targets. Over time, typed sidecars in datasets, APIs, public records, and AI-generated documents can amortize this formalization burden into reusable infrastructure.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
MM-CondChain: A Programmatically Verified Benchmark for Visually Grounded Deep Compositional Reasoning
Multimodal Large Language Models (MLLMs) are increasingly used to carry out visual workflows such as navigating GUIs, where the next step depends on verified visual compositional conditions (e.g., "if a permission dialog…
A Multimodal Agentic Pathology Co-pilot via Evidence Grounded Reasoning
Pathology is the cornerstone of modern medicine, where accurate decision-making relies heavily on evidence-based practices. While artificial intelligence (AI) has the potential to transform clinical workflows, the inters…
ReflectFact: Self-Reflective Agents for Improving Comprehension and Reasoning in Multi-Hop Fact Verification
Multi-hop fact verification, which verifies claims by reasoning over multiple pieces of evidence, is critical for combating misinformation on social media yet remains highly challenging. Recent methods primarily rely on …
Fact VerificationAgentic Hybrid RAG for Evidence-Grounded Muon Collider Analysis
Muon collider research spans accelerator physics, detector instrumentation, and high-energy phenomenology, with relevant evidence scattered across a rapidly expanding and heterogeneous body of scientific literature. As h…
Semantic RetrievalQuestion AnsweringAnswer GenerationMC-Search: Evaluating and Enhancing Multimodal Agentic Search with Structured Long Reasoning Chains
With the increasing demand for step-wise, cross-modal, and knowledge-grounded reasoning, multimodal large language models (MLLMs) are evolving beyond the traditional fixed retrieve-then-generate paradigm toward more soph…
Multimodal Reasoning