发表机构
The Hong Kong University of Science and Technology; LIGHTSPEED（香港科技大学; 光速公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对大型语言模型智能体在企业工作流中面临的策略合规、部分可观测性及长周期状态跟踪问题，提出E-Ledger管控框架，结合WorldAbduct实现规则演进，在多基准测试中提升安全任务完成率。
AI 中文摘要
大型语言模型智能体能够流畅调用工具，但企业工作流的需求不止于选择合适的工具：行动必须严格符合组织策略，工具反馈常因部分可观测性隐藏潜在副作用，长周期任务需要跨多条记录的持久状态跟踪。为应对这些挑战，我们提出E-Ledger，一种用于安全持久执行的多智能体管控框架。E-Ledger采用代码审批层，在执行前对照策略检查每一个拟执行的行动，并维护一个经验证的隐藏规则世界账本，以及基于证据的动态状态。由于隐藏规则通常先验未知，我们进一步提出WorldAbduct，一种基于溯因推理、由世界模型驱动的管控框架演进框架。WorldAbduct通过四个互补视角（状态一致性、世界-观测差距、策略门正确性、目标判断）诊断执行轨迹，以假设潜在规则，并通过针对性的溯因交互验证这些规则，再将其整合入账本。在企业基准测试环境World of Workflows中，配备WorldAbduct的E-Ledger在四个大语言模型主干上提升了安全任务完成率，比最强的演进基线高出5至15个百分点。在ScienceWorld和DiscoveryWorld中的实验进一步表明，溯因式管控框架演进可迁移至科学环境。我们的代码可在此https URL获取。
英文摘要
Large language model agents can invoke tools fluently, but enterprise workflows demand more than selecting the right tools: actions must strictly comply with organizational policies, tool feedback often conceals hidden side effects under partial observability, and long-horizon tasks require persistent state tracking across multiple records. To address these challenges, we introduce E-Ledger, a multi-agent harness for safe and persistent execution. E-Ledger employs a code approval layer that checks every proposed action against policy before execution, and maintains a world ledger of verified hidden rules alongside evidence-backed dynamic state. Because hidden rules are typically unknown a priori, we further propose WorldAbduct, an abductive, world-model-driven harness evolution framework. WorldAbduct diagnoses execution trajectories across four complementary views (state consistency, world-observation gap, policy-gate correctness, and goal judgment) to hypothesize latent rules, and verifies them through targeted abductive interactions before integrating them into the ledger. On the enterprise benchmark World of Workflows, E-Ledger with WorldAbduct improves safe task completion across four LLM backbones, outperforming the strongest evolution baseline by 5--15 percentage points. Experiments in ScienceWorld and DiscoveryWorld further show that abductive harness evolution carries over to scientific environments. Our code is available at https://github.com/HKUST-KnowComp/E-LEDGER-WorldAbduct.
