arXiv CS
open access
Beyond Binary Verifiable Rewards: Behavioral Self-Rewarding for SWE Agents
Reinforcement learning with verifiable rewards (RLVR) provides reliable supervision for software engineering agents through executable tests, but binary rewards fail to distinguish trajectories with substantially different debugging quality. We investigate whether the current policy can judge its ow
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 Binary Verifiable Rewards: Behavioral Self-Rewarding for SWE Agents#1296605
- LatentSift: Policy-State Filtering for Token-Efficient Verification of Software Engineering Agents#1131213
- LatentSift: Policy-State Filtering for Token-Efficient Verification of Software Engineering Agents#1122375
- OpenComputer: Verifiable Software Worlds for Computer-Use Agents#204842
- RAWR: Reward Assignment Without Rollouts in Verifiable Domains#1141246
Record · ID 1291882
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