Measuring Weak-to-Strong Legibility of Reasoning Models
cs.MA, cs.AI, cs.CL
Submitted: 2026-03-20
Updated: 2026-11-06
Terminology
Sources
- Retrieval-of-Thought: Efficient Reasoning via Reusing Thoughts
- How does information access affect LLM monitors' ability to detect sabotage?
- Llama-Nemotron: Efficient Reasoning Models
- Training Verifiers to Solve Math Word Problems
- Metacognitive Reuse: Turning Recurring LLM Reasoning Into Concise Behaviors
- Gemma 3 Technical Report
- Multi-Agent Risks from Advanced AI
- Measuring Mathematical Problem Solving With the MATH Dataset
- Reconsidering Overthinking: Penalizing Internal and External Redundancy in CoT Reasoning
- Kimi K2: Open Agentic Intelligence
- Prover-Verifier Games improve legibility of LLM outputs
- Training Language Models to Self-Correct via Reinforcement Learning
- Tulu 3: Pushing Frontiers in Open Language Model Post-Training
- Beyond Correctness: Learning Robust Reasoning via Transfer
- Evaluating Step-by-step Reasoning Traces: A Survey
- Let's Verify Step by Step
- Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs
- The Llama 3 Herd of Models
- Retro-Search: Exploring Untaken Paths for Deeper and Efficient Reasoning
- Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
Related papers
- MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents
- Iterative Negotiation and Oversight: A Case Study in Decentralized Air Traffic Management
- Towards using Large Language Models for Risk Negotiation and Consensus-building in One Health contexts
- A-MapReduce: Executing Wide Search via Agentic MapReduce
- AgentCue: Statistical Summaries for Guiding Decentralized Multi-Agent Self-Organization
- Events as Triggers for Behavioral Diversity in Multi-Agent Reinforcement Learning