Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Interpreting Latent CoT Reasoning as Dynamical Systems
Sabari Iyyappan Duraipandian, Shreya Sanjay Boyane, Manju Nagesh +3
Recent latent reasoning methods, such as CODI and COCONUT, face a fundamental interpretability problem: they maintain multiple superimposed candidate traces in the hidden space at…
cs.AI2026
HumanMCP: A Human-Like Query Dataset for Evaluating MCP Tool Retrieval Performance
Shubh Laddha, Lucas Changbencharoen, Win Kuptivej +3
Model Context Protocol (MCP) servers contain a collection of thousands of open-source standardized tools, linking LLMs to external systems; however, existing datasets and benchmark…