Replayable Financial Agents: A Determinism-Faithfulness Assurance Harness for Tool-Using LLM Agents · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2601.15322/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTReplayable Financial Agents: A Determinism-Faithfulness Assurance Harness for Tool-Using LLM Agents — mentioned by raffiskhttps://news.ycombinator.com/item?id=46733783urn:hackerpapers:mention:2601.15322:46733783Fri, 23 Jan 2026 15:39:45 GMT<p>Introed Determinism-Faithfulness assurance harness (DFAH) in new paper &quot;Replayable Financial Agents&quot; along with the open-source code A few findings: - Determinism and faithfulness are positively correlated (r = 0.45) for the tasks in my experiments - Schema-first Tier 1 (7–20B) stays near the 95% compliance threshold under stress. - Frontier models performed well on some tasks (e.g., strong action determinism in agentic triage), but the matrix helps define when HITL is still needed. note: I didn&#x27;t have control of inferencing engines, or infra for these experiments, leveraged local…</p><p><a href="https://hackerpaper.kaipfister.de/p/2601.15322/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.AI