HeavySkill: Heavy Thinking as the Inner Skill in Agentic Harness
For LLM reasoning, this work reframes orchestration complexity as a learnable inner skill, offering a path to self-evolving models without brittle orchestration layers.
The paper proposes HeavySkill, a perspective that heavy thinking (parallel reasoning then summarization) is an inner skill internalized within LLM parameters, and shows it consistently outperforms Best-of-N strategies, with stronger LLMs approaching Pass@N performance, and can be scaled via reinforcement learning.
Recent advances in agentic harness with orchestration frameworks that coordinate multiple agents with memory, skills, and tool use have achieved remarkable success in complex reasoning tasks. However, the underlying mechanism that truly drives performance remains obscured behind intricate system designs. In this paper, we propose HeavySkill, a perspective that views heavy thinking not only as a minimal execution unit in orchestration harness but also as an inner skill internalized within the model's parameters that drives the orchestrator to solve complex tasks. We identify this skill as a two-stage pipeline, i.e., parallel reasoning then summarization, which can operate beneath any agentic harness. We present a systematic empirical study of HeavySkill across diverse domains. Our results show that this inner skill consistently outperforms traditional Best-of-N (BoN) strategies; notably, stronger LLMs can even approach Pass@N performance. Crucially, we demonstrate that the depth and width of heavy thinking, as a learnable skill, can be further scaled via reinforcement learning, offering a promising path toward self-evolving LLMs that internalize complex reasoning without relying on brittle orchestration layers.