返回首页
arXiv AI··论文与技术

The Harness as the Only Mutable Surface: Compliance-Bounded Self-Evolution of LLM Agents in Credit Pipelines, with a Measured Admission Gate

中文摘要

提出一种受限的LLM代理自我演进方法,通过仅允许修改运行时配置而非模型权重,确保信贷流程中的变更可审计且可追溯。

English Summary

To ensure auditability in credit pipelines, LLM agents should evolve by modifying the runtime harness instead of weights, creating reviewable diffs for every adaptation.

原文节选

arXiv:2610.10629v1 Announce Type: new Abstract: Self-improving LLM agents can adapt a credit pipeline to a changed rule, but an agent that rewrites itself destroys the artefact a supervisor reviews: a named change, a recorded test, an approval. We argue that self-evolution is reviewable only if it is confined to the runtime harness (instruction text, tool-call logic and primitive composition) while model weights stay fixed, so that every adaptation is a diff with a cause and a test attached. We give a dual-loop engine built on that bound, with one admission gate that writes a hash-chained record before deployment, and we measure the gate in simulation, with a simulated agent and a seeded-search proposer rather than language models. Across three families of supervisory re-interpretation at three severities, 10 seeds each, the gated loop admitted 144 of 7,449 candidate changes, none of which worsened error on held-out history, and restored the false-positive rate to the oracle level without raising missed flags in every low- and mid-severity cell. With the gate replaced by the check an unbounded system applies (fewer errors visible in recent traces), the same loops admitted 309 harmf…