Env-Rethink：用27B模型改造LLM智能体环境实现递归自我提升
Breaking the Environment Wall: Evolving LLM Agent Environments for Recursive Self-Improvement
一篇讲怎么给智能体造更难环境的论文，27B 模型自动改环境，9 个模型平均涨 15% 通过率，做 Agent 训练的可以看看。
arXiv 论文提出 Env-Rethink，一个基于 27B 后训练模型的系统，解决真实任务环境中信息碎片化、噪声混杂、环境随时间演化三类问题。这些问题会让 SOTA 智能体成绩从 83.9% 降到 57.6%。系统通过构建 Collection Maps 和 Event Logs 补充上下文，用离线轨迹学习识别环境噪声，再通过虚拟事件历史改变环境状态生成更难的任务。在 30 个任务、9 个模型上，Env-Rethink 带来超过 15.1% 的 rubric 通过率提升。
Breaking the Environment Wall: Evolving LLM Agent Environments for Recursive Self-Improvement
Many real-world tasks (e.g., office workflows, scientific experimentation) require LLM agents to interact repeatedly with their environments for context-dependent operations. However, such environments are often not agent-ready. First, information is often scattered and fragmented across the environment. Second, relevant evidence in the environment is often mixed with misleading information and conflicting versions. Third, environments evolve over time, introducing new noise and more challenging tasks. These challenges can substantially degrade performance for state-of-the-art AI agents (e.g., from 83.9% to 57.6%). To address these challenges, we propose Env-Rethink (a system with 27B post-trained model) that supports three main capabilities: (1) It adaptively builds Collection Maps (for organizing related files) and Event Logs (for contextualizing cross-data relationships) to supplement necessary context; (2) It further leverages the post-trained model (through offline trajectory learning) to identify underlying noise issues in the environment; (3) It ultimately evolves environments through virtual event histories that alter environmental states and evidence relationships, producing more tricky ones for further agent improvement. Experiments show that Env-Rethink can effectively improve downstream task performance (with over 15.1% rubric pass rate improvement across nine models on 30 tasks).
