arXiv (All)
open access
Continue or Restart? The Limits of Early Failure Prediction in Coding Agents
Early stopping promises to reduce compute costs for autonomous coding agents by terminating unpromising runs early. Deciding when to abandon a run requires separating baseline issue difficulty from the trajectory of an individual attempt. We study the distinction in 147,002 execution traces from two
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
- SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science?#820620
- COCA: Generative Root Cause Analysis for Distributed Systems with Code Knowledge#1317986
- Resilience of the surface code to error bursts#1330529
- ChurnBench: A Drift-Aware Benchmark Demonstrating That Refresh Scheduling, Not Cache Age, Governs Staleness in Agentic AI#673571
- Beyond the Traceback: Using LLMs for Adaptive Explanations of Programming Errors#662088
Record · ID 1467295
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