arXiv (All)
open access
Where the Verifier Fails: A Category-Level Audit of Reward Signals in RLVR
Reinforcement learning with verifiable rewards (RLVR) and standard benchmark evaluation both rely on an automatic verifier that turns a free text answer into a binary reward. Prior work reports that one evaluation harness accepts only about 94% of its own ground truth answers, blaming LaTeX parsing.
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
- Learned Reporting Preferences in RLVR Can Conflict with the Current Request#1131788
- Same Reward, Different Skills: When Multimodal RL Learns to Look#1157179
- LSR-Ben: A Logical and Scientific Reasoning Benchmark for Evaluating Process Reward Models#1143744
- TRACE: Training Reasoning Agents for Causal Exploration with Synthesized Rewards#997207
Record · ID 821295
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