arXiv：cs.AI· Yisen Gao, Yue Guo, Qing Zong, Yiwen Guo, Yangqiu Song·· 3 小时前
E-Ledger：面向部分可观测世界的安全持久演进式智能体执行框架
Safe, Persistent, and Evolving Agent Harness for Understanding Partially Observable Worlds
AI 导读
研究团队提出多智能体执行框架 E-Ledger，通过代码审批层在执行前校验每个动作是否符合策略，并维护记录已验证隐藏规则与动态状态的世界账本。配套的 WorldAbduct 框架从状态一致性、世界-观测差距、策略门正确性和目标判定四个视角诊断执行轨迹，验证潜在规则后写入账本。
正文
Abstract: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 this https URL.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.11552 [cs.AI] |
| (or arXiv:2610.11552v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.11552 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yisen Gao [view email]
[v1]
Thu, 8 Oct 2026 09:15:28 UTC (2,825 KB)
来源：arXiv：cs.AI · arxiv.org