用双重验证机制杜绝大模型研究代理的虚假声明。
Evidence-Bound Autonomous Research (EviBound): A Governance Framework for Eliminating False Claims
- 双层治理门控：执行前验证结构，执行后检查可查证成果。
- 0%虚假声明，8项任务中7项通过验证，仅1项在前期被拦截。
- 适合关注研究可信度与自动化系统安全的研究者和工程师。
基于大模型的自主研究代理常报告虚假声明：任务标记为“完成”却缺失成果、指标矛盾或执行失败。EviBound 是一种证据约束执行框架，通过双重治理门控消除虚假声明，要求机器可验证的证据。预执行审批门在代码运行前验证接受标准模板，主动发现结构性违规；后执行验证门通过 MLflow API 查询（含递归路径检查）验证成果，并按接受标准可选验证指标。只有具备可查询的运行ID、必要成果和已完成状态时，声明才可传播。有限次数的置信度门控重试（通常1-2次）可在不引发无限循环的情况下恢复瞬时失败。在8个涵盖基础设施验证、机器学习能力与治理压力测试的基准任务上评估：基线A（仅提示层）产生100%幻觉（8/8声称，0/8验证通过）；基线B（仅验证）将幻觉降至25%（2/8未通过验证）；EviBound（双门控）实现0%幻觉：7/8任务验证通过，1项在审批门被正确阻断，整体执行开销约8.3%。本包包含执行轨迹、所有验证任务的 MLflow 运行ID及四步验证协议。研究可靠性是架构属性，由治理门控实现，而非模型规模带来的涌现特性。
原文摘要 · Abstract (English)
LLM-based autonomous research agents report false claims: tasks marked "complete" despite missing artifacts, contradictory metrics, or failed executions. EviBound is an evidence-bound execution framework that eliminates false claims through dual governance gates requiring machine-checkable evidence. Two complementary gates enforce evidence requirements. The pre-execution Approval Gate validates acceptance criteria schemas before code runs, catching structural violations proactively. The post-execution Verification Gate validates artifacts via MLflow API queries (with recursive path checking) and optionally validates metrics when specified by acceptance criteria. Claims propagate only when backed by a queryable run ID, required artifacts, and FINISHED status. Bounded, confidence-gated retries (typically 1-2 attempts) recover from transient failures without unbounded loops. The framework was evaluated on 8 benchmark tasks spanning infrastructure validation, ML capabilities, and governance stress tests. Baseline A (Prompt-Level Only) yields 100% hallucination (8/8 claimed, 0/8 verified). Baseline B (Verification-Only) reduces hallucination to 25% (2/8 fail verification). EviBound (Dual Gates) achieves 0% hallucination: 7/8 tasks verified and 1 task correctly blocked at the approval gate, all with only approximately 8.3% execution overhead. This package includes execution trajectories, MLflow run IDs for all verified tasks, and a 4-step verification protocol. Research integrity is an architectural property, achieved through governance gates rather than emergent from model scale.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。