works on
empirical reasoning 1formal verification 1hallucination mitigation 1large language models 1tool calling 1

From the 1 of 3 linked papers with an AI index.

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2026

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

Junyu Ren

The paper presents EG-VAR, a system that integrates large language models with the Lean theorem prover so that every empirical claim is tied to an attested tool call and formally v…