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 re
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 55%sileod/reasoning-core →
- PossiblePossibly related (embedding) · 52%mirror29/inalpha →
- PossiblePossibly related (embedding) · 52%Retrace-1.5B →
- PossiblePossibly related (embedding) · 52%kyegomez/Lets-Verify-Step-by-Step →
- PossiblePossibly related (embedding) · 52%agent-tools →
- LinkedLinked via arxiv author · 85%Junyu Ren →
“Evidence-Grounded Verified Agentic Reasoning: A Path Toward Eliminating LLM Hallucination in Empirical Inference via Too”
- PossiblePossibly related (embedding) · 45%dp-web4/SAGE →