English(EN) ContractEval: Query-Conditioned Execution Matching for Procedural Instruction Conformance

新框架ContractEval审计LLM代理的程序一致性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-11 04:00

研究人员开发了ContractEval，一个旨在评估LLM代理程序指令一致性的新诊断框架。该系统明确识别代理未能满足特定义务的情况，例如跳过检查或违反不变式，这可能导致看似正确但无根据的输出。ContractEval将这些程序指令表示为查询活跃义务，并将其与响应或跟踪证据进行匹配，区分各种类型的一致性失败。在对审计的程序合同进行的测试中，ContractEval成功检测并定位了所有被传统仅输出和跟踪感知裁判所遗漏的注入结构性失败。 AI

影响增强了LLM代理程序的审计能力，提高了复杂任务执行的可靠性。

排序理由该集群包含一篇详细介绍LLM代理评估新框架的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 13 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍LLM代理评估新框架的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Praphul Singh, Shanu Kumar, Akshat Agarwal, Ganesh Kumar · 2026-09-11 04:00

ContractEval：面向程序指令一致性的查询条件执行匹配

arXiv:2609.09458v1 Announce Type: new Abstract: As LLM agents move from answering questions to carrying out procedures, failures can be unwarranted rather than visibly wrong: the final response looks acceptable even though the system skipped the check, branch, dependency, or inva…

本文如何被排名

报道来源 [1]

ContractEval：面向程序指令一致性的查询条件执行匹配

相关实体

相关话题