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 compute, and when should it escalate? We formulate this post-failure decision as recovery routing over h
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 50%Pluggable by design: An agent mesh for software modernization that adopts the next model release →
- FuzzySimilar title/name (fuzzy) · 87%NirDiamant/GenAI_Agents →
“Fuzzy title match (0.94): “CodeRescue: Budget-Calibrated Recovery Routing for Coding Ag” ≈ “NirDiamant/GenAI_Agents””
- FuzzySimilar title/name (fuzzy) · 84%Unity-Technologies/ml-agents →
“Fuzzy title match (0.92): “CodeRescue: Budget-Calibrated Recovery Routing for Coding Ag” ≈ “Unity-Technologies/ml-agents””
- FuzzyOverlapping authors or contributors · 62%modular/modular →
“Shared author/contributor keys: liu”
- FuzzyOverlapping authors or contributors · 62%DietrichGebert/ponytail →
“Shared author/contributor keys: cheng”
- FuzzyOverlapping authors or contributors · 62%bytedance/deer-flow →
“Shared author/contributor keys: wang”
- LinkedLinked via arxiv author · 85%Qijia He →
“CodeRescue: Budget-Calibrated Recovery Routing for Coding Agents”
- LinkedLinked via arxiv author · 85%Jiayi Cheng →
“CodeRescue: Budget-Calibrated Recovery Routing for Coding Agents”