Kang Liu

Current LLMs falter in complex rule-centered reasoning, with top models only reaching half of the potential performance on a new benchmark.

Simply adding more multimodal environments can hinder agent performance, but targeted diversity and structured difficulty can transform training outcomes.

SFT leads to task conflicts that can cripple multi-task learning, while RL's variance-limited updates enable seamless task coexistence.

Suboptimal trajectories can amplify errors in long-horizon planning, revealing critical insights into the limitations of current training methods.

AREX achieves superior performance in deep research tasks by recursively refining answers through a novel self-improvement mechanism that outpaces traditional search methods.

MemTools transforms agent memory research by enabling seamless integration and evaluation of diverse memory types across architectures.

Models fine-tuned with LongCrafter data achieve unprecedented performance on long-context tasks, particularly in high-difficulty scenarios.