Tag
This paper proposes amortizing the high token cost of reasoning-mode LLMs by distilling domain-specific skills from existing trajectories into system prompts, recovering most of the reasoning gap on agentic benchmarks while emitting far fewer tokens.
This paper introduces CurveShift, an analysis method that separates overall ability gains from difficulty-specific improvements in LLM agents. Using METR time-horizon data and LiveCodeBench, it finds that most apparent shifts toward harder tasks are ceiling effects, though a genuine hard-task effect exists for reasoning models in competitive programming.