[
    {
        "id": "osp-15083",
        "type": "article-journal",
        "title": "Safe, Persistent, and Evolving Agent Harness for Understanding Partially Observable Worlds",
        "author": [
            {
                "family": "Gao",
                "given": "Yisen"
            },
            {
                "family": "Guo",
                "given": "Yue"
            },
            {
                "family": "Zong",
                "given": "Qing"
            },
            {
                "family": "Guo",
                "given": "Yiwen"
            },
            {
                "family": "Song",
                "given": "Yangqiu"
            }
        ],
        "URL": "https://omanscience.com/en/articles/safe-persistent-and-evolving-agent-harness-for-understanding-partially-observable-worlds",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "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 https://github.com/HKUST-KnowComp/E-LEDGER-WorldAbduct."
    }
]