Study Tracks How LLM Reasoning Traces Represent Iterated Games
A new arXiv paper examines tracking representations in large language model chain-of-thought reasoning traces during iterated games, noting LLM agents achieve state-of-the-art performance via CoT reasoning.
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-11-19 05:00 · arXiv cs.CL
Tracking Representations in LLM Reasoning Traces for Iterated Games