4 papers
Scaling Test-Time Compute for Agentic Coding
Joongwon Kim, Wannan Yang, Kelvin Niu +13
Test-time scaling has become a powerful way to improve large language models. However, existing methods are best suited to short, bounded outputs that can be directly compared, ran…
Hyperagents
Jenny Zhang, Bingchen Zhao, Wannan Yang +5
Self-improving AI systems aim to reduce reliance on human engineering by learning to improve their own learning and problem-solving processes. Existing approaches to self-improveme…
Hallucination reduction with CASAL: Contrastive Activation Steering For Amortized Learning
Wannan, Yang, Xinchi Qiu +6
Large Language Models (LLMs) exhibit impressive capabilities but often hallucinate, confidently providing incorrect answers instead of admitting ignorance. Prior work has shown tha…
Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RL
Chen Sun, Wannan Yang, Thomas Jiralerspong +4
In real life, success is often contingent upon multiple critical steps that are distant in time from each other and from the final reward. These critical steps are challenging to i…