TSR Desk · science · 11 October 2026, 01:00 UTC
Safe, Persistent, and Evolving Agent Harness for Understanding Partially Observable Worlds
- What
- Safe, Persistent, and Evolving Agent Harness for Understanding Partially Observable Worlds
- Who
- arxiv.org
- When
- 10 October 2026, 04:00 UTC
- Category
- Science
- Primary source
- https://arxiv.org/abs/2610.11552
- What is not known
- This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.
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. It comes from a paper posted to arXiv on 10 October 2026. 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. 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.
Why it counts
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.
Sources
Primary source: primary source
What is not known
This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.
No clip. The article still stands.