Tianxin Wei
3 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.
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 proposes RECONTEXT, a training-free inference method for improving long-context reasoning in large language models using model-internal relevance signals and recursive evidence replay.
Papers
ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning
Yanjun Zhao, Ruizhong Qiu, Tianxin Wei, Yuanchen Bei +5 more
This paper proposes RECONTEXT, a training-free inference method for improving long-context reasoning in large language models using model-internal relevance signals and recursive evidence replay.