paper-with-me

홈 › Papers

Evidence-Grounded Verified Agentic Reasoning: A Path Toward Eliminating LLM Hallucination in Empirical Inference via Tool-Attested Kernel Proofs

2026-07-14 · Junyu Ren arxiv

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.

📄 PDF Abstract BibTeX arXiv:2607.12650

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

MM-CondChain: A Programmatically Verified Benchmark for Visually Grounded Deep Compositional Reasoning

2026-03-12 · Haozhan Shen, Shilin Yan, Hongwei Xue, Shuaiqi Lu 외 arxiv

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

2026-06-06 · Zhe Xu, Zhengyu Zhang, Zhiyuan Cai, Jiahao Xu 외 arxiv

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

2026-08-13 · Runze Zhao, Zixin Tang, Xiaoshuai Hao, Leyuan Chang 외 arxiv

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 Verification

Agentic Hybrid RAG for Evidence-Grounded Muon Collider Analysis

2026-06-09 · Ruobing Jiang, Dawei Fu, Cheng Jiang, Tianyi Yang 외 arxiv

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 Generation

MC-Search: Evaluating and Enhancing Multimodal Agentic Search with Structured Long Reasoning Chains

2026-03-01 · Xuying Ning, Dongqi Fu, Tianxin Wei, Mengting Ai 외 arxiv

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