CodeRescue: Budget-Calibrated Recovery Routing for Coding Agents
Coding agents increasingly operate in executable environments where a failed attempt produces actionable feedback rather than merely an incorrect answer. Existing cost-aware systems typically treat such failures as cascade decisions: try a cheap model first, then escalate hard cases to a stronger and more expensive model. In coding, however, execution feedback can also make further cheap-model recovery worthwhile, raising a budgeted deployment question: when should an agent spend more cheap comp
Record details
Published: 21 July 2026
Source: arXiv cs.AI
Category: Research
Topics: Agents & autonomy · Environment
Retrieved: 22 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
From Distances to Trajectories: Real-Time Signed Distance Function Mapping and Distance-Accelerated Motion Planning for UAVs
arXiv cs.AI · 21 July 2026
Progress Reward Modeling for Robotic Learning: A Comprehensive Survey
HuggingFace Daily Papers · 21 July 2026
Comparative Study of Multi-Agent Actor-Critic Algorithms in Parameterized Action Reinforcement Learning
arXiv cs.AI · 21 July 2026
AI Contagion in Social Networks
arXiv cs.CY · 21 July 2026
Coordinating from Memory: Graph-Structured Experience Reuse for Multi-Agent Adaptation in Dynamic Manufacturing
arXiv cs.AI · 22 July 2026
PRO-LONG: Programmatic Memory Enables Long-Horizon Reasoning
arXiv cs.AI · 22 July 2026
How to cite this record
ethics.ai (21 July 2026), “CodeRescue: Budget-Calibrated Recovery Routing for Coding Agents,” evidence record 12585, https://ethics.ai/record/12585 (originally published by arXiv cs.AI).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.