arXiv (All)
open access
Learning to Solve, Forgetting to Retain: Correct-Set Turnover in RLVR
Reinforcement learning with verifiable rewards (RLVR) improves the ability of large language model, yet headline accuracy gains often conceal a hidden cost: previously solved problems quietly become unsolvable as training proceeds. We frame this phenomenon as \emph{correct-set turnover}, representin
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
- Beyond Verbalized Confidence: Calibrating Reasoners with Differentiable Readouts#1129470
- Visual sensitivity is not claim retractability: persistence-aware credit assignment for multimodal reinforcement learning#1131773
- TGRL: Temperature-Grouped Reinforcement Learning for Efficient Exploration in LLMs#1118301
- Surprising Success, Repeated Failure: Entropy-Guided Credit Assignment for Exploration in LLM Reasoning#1118854
- Learning to Steer, Steering to See: Unveiling the Geometry of RLVR in Large Language Models via Trainable Vectors#1119417
Record · ID 1131563
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