agent/papers/items/2026-2607-05174-agentgym2-benchmarking-large-language-model-agents-in-de-idealized-real-world-en.md

Paper: AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments

---

type: paper title: "AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments" authors: Zhiheng Xi, Dingwen Yang, Jiaqi Liu, Jixuan Huang, Honglin Guo, Baodai Huang, Tinggang Chen, Qi Zhang, et al. year: 2026 venue: arXiv url: https://arxiv.org/abs/2607.05174 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2026-07-06 updated_at: 2026-07-06 status: queued relevance: high topics:

• agent-evaluation
• planning
• reasoning
• tool-use methods:

benchmarks:

models:

datasets:

• cs.AI related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 19 collection_queries: language-agent, llm-agent, planning-agent

One-line Takeaway

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

Why Collected

• matched queries: language-agent, llm-agent, planning-agent
• inferred topics: agent-evaluation, planning, reasoning, tool-use
• arXiv categories: cs.AI
• collection score: 19

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/2607.05174