Jolt Atlas: Verifiable Inference via Lookup Arguments in Zero Knowledge · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2602.17452/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTJolt Atlas: Verifiable Inference via Lookup Arguments in Zero Knowledge — mentioned by wyattbennohttps://news.ycombinator.com/item?id=47275031urn:hackerpapers:mention:2602.17452:47275031Fri, 06 Mar 2026 14:04:03 GMT<p>Hi, AI Agents Can Move Money. Lobstar Wilde Proved They Can Lose It Too... So we made: (ARc + ZK) Neurosymbolic formal reasoning w/ zero knowledge proofs for cryptographically secure agentic guardrails. Our approach has two essential properties for agentic commerce: (1) succinct proofs and (2) optional privacy. The core idea is from the Automated Reasoning Checks (ARc) paper (https://arxiv.org/pdf/2511.09008) which converts natural language policies into SMT-LIB constraints and checks agent actions against an SMT solver rather than an LLM judge. The solver proofs are not succinctly verifiable…</p><p><a href="https://hackerpaper.kaipfister.de/p/2602.17452/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CR