arXiv (All)
open access
The Weakest Link: Distilling LLM Reasoning with Worst-Case Constrained Reinforcement Learning
Distilling the reasoning capabilities of large language models (LLMs) into smaller students is a central challenge for efficient deployment. Current approaches face a fundamental tension: optimizing purely for verifiable task rewards (e.g., via GRPO) leads to reward hacking, where students arrive at
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM#984715
- When is LLM-Based Program Reasoning Correct? A Completion Semantics for LLM-Based Code Inference#1084289
- "If You're Not Doing It, Somebody Else Is": Active Negotiation and the Invisible Labor of Sustained LLM Use#1105258
- An Incomplete Loop: Deductive, Inductive, and Abductive Reasoning in Language Models#1108898
- Verify to Amplify: Improving Reasoning via Learned Chain-of-Thought Verification#996884
Record · ID 1154955
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive