arXiv CS
open access
Over-Defense in Coding Agents Begins at Silent Forks
Language models behind coding agents are post-trained with outcome rewards, and recent methods concentrate credit on the turns that decide the outcome. We find that defensive actions beyond what a task requires escape both. They begin at silent forks, the turns where every next action leads to the s
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
- Over-Defense in Coding Agents Begins at Silent Forks#1389895
- Preventing Premature Commitment in Coding Agents with an Evidence-Conditioned Execution Layer#422338
- AI Safety via Debate is Compromised by Cognitive Biases#1201474
- Dependency-Aware Reward Shaping for Agentic Reinforcement Learning#1156479
- BLINDSPOT: A Benchmark for Safety and Refusal Calibration in Long-Horizon Tool-Using Agents#1110671
Record · ID 1381317
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