Zhan Shi
6 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper distinguishes between a model's ability to generate useful updates for external agent components (harness-updating) and its ability to benefit from those updates (harness-benefit), finding that updating capabilities are surprisingly uniform while benefit is maximized in mid-tier models.
The paper distinguishes between a model's ability to generate useful updates for external agent components (harness-updating) and its ability to benefit from those updates (harness-benefit), finding that updating capabilities are surprisingly uniform while benefit is maximized in mid-tier models.
Adaptive Auto-Harness introduces a framework that enables LLM agents to sustain self-improvement and maintain high performance over open-ended, shifting task streams, outperforming existing fixed-benchmark auto-harness systems.
Adaptive Auto-Harness introduces a framework that enables LLM agents to sustain self-improvement and maintain high performance over open-ended, shifting task streams, outperforming existing fixed-benchmark auto-harness systems.
This paper introduces MM-IssueLoc, a benchmark and evaluation protocol for repository-level issue localization with visual evidence.
This paper proposes a method, LM2LM, to train large language models to generate effective improvement proposals using reinforcement learning and a research world model.
Papers
Language Models Learn to Improve Language Models
Minhua Lin, Zijun Wang, Zewen Liu, Zhaotian Weng +6 more
This paper proposes a method, LM2LM, to train large language models to generate effective improvement proposals using reinforcement learning and a research world model.