Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

  • Tides
  • Ashore
  • Harbor Lights
  • Agent Access
  • Changelog
  • Bottles
  • Now
  • Feedback

External links

GitHubCloudborne ↗

© 2026 Pier.

WatchingResearchWatching0 independent reports0

CodeRescue: Budget-Calibrated Recovery Routing for Coding Agents

First seen · 7/22/2026, 01:56 AMLatest activity · 7/22/2026, 01:56 AM

CodeRescue treats a coding agent’s post-failure choice as a recovery-routing problem over heterogeneous actions: continue with a cheap model, spend more cheap compute, or escalate to a stronger model. The authors train a supervised router from execution rollouts and add a Conformal Risk Control (CRC) layer that chooses a deployment-time cost penalty without retraining. On held-out failures from five coding benchmarks, cheap recovery and escalation show complementary success patterns. In the main GPT-5.4-nano/GPT-5.4 experiment, one CRC-calibrated frontier point reportedly exceeds always-escalate solve rate while using 35% of its mean recovery cost.

Event heat · last 24 hours

No heat snapshots are available in the last 24 hours.

No heat snapshots are available in the last 24 hours.

Reporting Timeline

  1. AggregatorarXiv7/22, 01:56 AMnot independentRepresentative
    CodeRescue: Budget-Calibrated Recovery Routing for Coding Agents