agent/papers/items/2026-2606-05558-autoregressive-diffusion-world-models-for-off-policy-evaluation-of-llm-agents.md

Paper: Autoregressive Diffusion World Models for Off-Policy Evaluation of LLM Agents

---

type: paper title: Autoregressive Diffusion World Models for Off-Policy Evaluation of LLM Agents authors: Kaixuan Liu, Guojun Xiong, Weinan Zhang, Shengpu Tang year: 2026 venue: arXiv url: https://arxiv.org/abs/2606.05558 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2026-06-04 updated_at: 2026-06-04 status: queued relevance: high topics:

• agent-evaluation
• agent-safety
• computer-use
• tool-use
• world-model methods:

benchmarks:

models:

datasets:

• cs.LG related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 18 collection_queries: agent-evaluation

One-line Takeaway

Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.

Why Collected

• matched queries: agent-evaluation
• inferred topics: agent-evaluation, agent-safety, computer-use, tool-use, world-model
• arXiv categories: cs.LG
• collection score: 18

Review Checklist

• Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
• Does it include a benchmark, dataset, code, or reproducible experimental setup?
• Should it be promoted from queued to skimmed or summarized?

Links

• arXiv: https://arxiv.org/abs/2606.05558