arXiv (All)
open access
Selecting Diverse SFT Traces Improves Post-RL Generalization
Verified solutions are not equally useful for preparing reasoning models for reinforcement learning (RL). We present a comprehensive study of route diversity, the variation in the sequences of reasoning steps in supervised fine-tuning (SFT) data, and propose a lightweight, rule-based fingerprint to
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
- Reasoning-Preserving Fine-Tuning of Post-RL LLMs with Null-Basis LoRA#1061255
- DSPO: Diversity-aware Subjective Policy Optimization for Robust Emotional Reasoning#1131976
- TOUR: A Trajectory-Level Unlearning Benchmark for Offline Reinforcement Learning#394431
- Control-Geometry Straightening for Sampling-Based Latent Planning#1130257
- Control-Geometry Straightening for Sampling-Based Latent Planning#1108773
Record · ID 1118853
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