Renmin University researchers release the Agent-Editing World Model (AEWM)
Agent-Editing World Model (AEWM) released — instead of a conventional world model that predicts the environment's responses, it models "how reasoning and actions change the state of task progress". It consists of an Action Judge, which classifies decisions as critical, exploratory or noisy before they are executed, and State Revision, which rewrites problematic reasoning-action sequences using the same observation history. On the authors' own Action Judge benchmark it reached 70.5% macro-F1, 10.6 points ahead of the strongest frontier baseline; EditAct improved results by 3.2–6.7 points on 6 benchmarks, and AEWM-RFT by 2.2–2.6 points in 3 domains
Why it matters
It recasts why agents break down on long tasks — not "because they cannot read the environment" but "because stale state descriptions they wrote themselves linger". It means what a harness has to manage is not tool calls but the lifespan of task state, and it belongs to the same family of problems as last week's compaction-summary injection case
Source — Primary sources first; secondary reports are labelled “Press”
Officialhuggingface.cohttps://huggingface.co/papers/2609.28416Added in Week 40, 2026 · See that week