agent/papers/items/2026-2605-11928-when-simulation-lies-a-sim-to-real-benchmark-and-domain-randomized-rl-recipe-for.md

Paper: When Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use Agents

---

type: paper title: "When Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use Agents" authors: Xiaolin Zhou, Aojie Yuan, Zheng Luo, Zipeng Ling, Xixiao Pan, Yicheng Gao, Haiyue Zhang, Jiate Li, et al. year: 2026 venue: arXiv url: https://arxiv.org/abs/2605.11928 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2026-05-12 updated_at: 2026-05-12 status: queued relevance: high topics:

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

benchmarks:

models:

datasets:

• cs.AI related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 13 collection_queries: function-calling, language-agent

One-line Takeaway

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

Why Collected

• matched queries: function-calling, language-agent
• inferred topics: agent-evaluation, tool-use, world-model
• arXiv categories: cs.AI
• collection score: 13

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/2605.11928