# Measuring Weak-to-Strong Legibility of Reasoning Models

arXiv: https://arxiv.org/abs/2603.20508 · HTML: https://mlsanity.com/paper/2603.20508/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 39 of its 60 references that are in the map.
- First posted on arXiv 20 Mar 2026.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)

## Builds on (most cited first, 30 of 39)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [Tulu 3: Pushing Frontiers in Open Language Model Post-Training](https://mlsanity.com/paper/2411.15124/) (2024)
- [Kimi K2: Open Agentic Intelligence](https://mlsanity.com/paper/2507.20534/) (2025)
- [Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision](https://mlsanity.com/paper/2312.09390/) (2023)
- [Training Language Models to Self-Correct via Reinforcement Learning](https://mlsanity.com/paper/2409.12917/) (2024)
- [Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs](https://mlsanity.com/paper/2410.18451/) (2024)
- [TokenSkip: Controllable Chain-of-Thought Compression in LLMs](https://mlsanity.com/paper/2502.12067/) (2025)
- [Multi-Agent Risks from Advanced AI](https://mlsanity.com/paper/2502.14143/) (2025)
- [Llama-Nemotron: Efficient Reasoning Models](https://mlsanity.com/paper/2505.00949/) (2025)
- [Olmo 3](https://mlsanity.com/paper/2512.13961/) (2025)
- [Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost](https://mlsanity.com/paper/2407.19825/) (2024)
- [Prover-Verifier Games improve legibility of LLM outputs](https://mlsanity.com/paper/2407.13692/) (2024)
- [Evaluating Step-by-step Reasoning Traces: A Survey](https://mlsanity.com/paper/2502.12289/) (2025)
- [BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning](https://mlsanity.com/paper/2506.17211/) (2025)
- [Magistral](https://mlsanity.com/paper/2506.10910/) (2025)
- [Retro-Search: Exploring Untaken Paths for Deeper and Efficient Reasoning](https://mlsanity.com/paper/2504.04383/) (2025)
- [Metacognitive Reuse: Turning Recurring LLM Reasoning Into Concise Behaviors](https://mlsanity.com/paper/2509.13237/) (2025)
- [To Backtrack or Not to Backtrack: When Sequential Search Limits Model Reasoning](https://mlsanity.com/paper/2504.07052/) (2025)
- [An Empirical Study of LLM Reasoning Ability Under Strict Output Length Constraint](https://mlsanity.com/paper/2504.14350/) (2025)
- [Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2505.11827/) (2025)
- [How does information access affect LLM monitors' ability to detect sabotage?](https://mlsanity.com/paper/2601.21112/) (2026)

## Built on by (most cited first, 5 of 5)

- [How Much Does a Reasoning Summary Reveal? An Observability Ladder for Large Language Models](https://mlsanity.com/paper/2608.02089/) (2026)
- [Reasoning that Travels: Dissecting How Chain-of-Thought Transfers Across Models](https://mlsanity.com/paper/2605.28913/) (2026)
- [CLORE: Content-Level Optimization for Reasoning Efficiency](https://mlsanity.com/paper/2605.22211/) (2026)
- [Tandem Reinforcement Learning with Verifiable Rewards](https://mlsanity.com/paper/2606.28166/) (2026)
- [On Language Drift during RLVR Post-Training](https://mlsanity.com/paper/2610.02015/) (2026)

## Abstract (arXiv)

Reasoning language models (RLMs) and the intermediate chains of thought they emit play an increasingly central role in multi-agent setups such as inter-model monitoring or distillation into smaller models. When agents at different capability tiers must cooperate, strong models need to produce traces digestible by weaker ones. We refer to this goal as "weak-to-strong legibility". Trustworthiness of large models depends in part on this legibility property. For safety oversight in particular, adoption of weak monitors may become a standard for reliability scaffolds on a healthy budget. Legibility requires that the shape of these decision-making traces takes some form accessible to weaker monitors. Existing efficiency-based metrics for legibility fail to capture "thoroughness", instead focusing on conciseness.