ReCode: Unify Plan and Action for Universal Granularity Control Paper • 2510.23564 • Published Oct 27 • 121
Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models Paper • 2510.04618 • Published Oct 6 • 125
AI-Slop to AI-Polish? Aligning Language Models through Edit-Based Writing Rewards and Test-time Computation Paper • 2504.07532 • Published Apr 10 • 1
A Survey of Context Engineering for Large Language Models Paper • 2507.13334 • Published Jul 17 • 259
Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination Paper • 2507.10532 • Published Jul 14 • 89