Paper summary
Paper summary: A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents
A survey organising agentic reasoning into three layers (foundational single-agent skills, self-evolving agents, collective multi-agent reasoning), each split into in-context and post-training approaches.
- Three layers: plan/use tools/search; improve through feedback and memory; collaborate with other agents.
- Across all layers, it separates in-context orchestration from post-training (RL, SFT).