arXiv (All)
open access
Fine Until Fine-Tuned: Repeated Solutions Make Reasoning Fragile
Recipes such as s1 and LIMO teach a model to reason with little data by showing it the same thousand or fewer worked solutions many times over. Judged when that training ends, the repetition looks harmless. But reasoning models are often trained again, and we find that repetition leaves their reason
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
- Revisiting Complete Reasoning Traces for Post-Training#975163
- Shockingly Simple Self-retrospection Improves Agentic Models Without RL#1130388
- Shockingly Simple Self-retrospection Improves Agentic Models Without RL#1108790
- Why Counterfactual Reasoning Requires a Minimal Structural Interval#102486
- Latent Recurrent Thoughts: Recurrent Refinement of Proposed Latents for Reasoning with Frozen LLMs#821090
Record · ID 1118271
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