Posts

Showing posts with the label paper brief

When Do Tools Help LLM Agents, and When Do They Backfire?

Two Ways to Stabilize LLM Agents on Complex Tasks: Hierarchical Planning and CAP-CoT

When Does LLM Self-Correction Actually Help? Papers on Iterative Refinement, Evaluation, and Reliability

Is LLM Reasoning Really a Chain of Thought? What a New Paper Questions

Rethinking LLM Reasoning as Internal State Change, Not Visible Chain-of-Thought