Real-world tasks often stump LLM agents because environments are messy: files are scattered, evidence is mixed with misleading versions, and changes over time add noise. This paper introduces Env-Rethink, a system that prepares such environments by building collection maps to group related files and event logs to capture cross-data relationships. It also post-trains a 27B model on offline trajectories to identify noise and judge which evidence is valid. Finally, it evolves environments by generating virtual histories that create harder, but still solvable, tasks. On 30 tasks across nine downstream models, Env-Rethink raised the mean rubric pass rate from 57.6% to 72.7%, a 15.1 percentage-point gain, and improved held-out file-verification accuracy from 56.2% to 76.5%.
Structuring noisy file environments improves agents’ performance on complex tasks
Env-Rethink organizes fragmented evidence, learns to detect misleading files, and generates harder but verifiable environments for agent training.
Chinese Tech
Yukai Wu · Yuanjing Yang · Le Zhou · Shaokun Han · Haoyu Wang · Zirui Tang · +5 more
Shanghai Jiao Tong University · Theseus Labs · Tencent Hunyuan
Research Digest··2 min read
In one line
Env-Rethink prepares and evolves agent environments using collection maps and event logs, lifting mean rubric pass rate by 15.1 points across nine models.
Before you read this
Two ideas this paper builds onRead it as
Wu et al. developed Env-Rethink, a framework built around a post-trained 27-billion-parameter model that prepares persistent file environments for LLM agents.
The authors studied persistent environments containing documents, code, records, and conflicting file versions.
How it works
before and afterThe Daily Edition
The front page in your inbox each weekday morning: the lead, the picks, and why each one earned its place.