TurnCost: Turns, Not Observations: Cache-Aware Loop Engineering for Coding Agents
cs.SE, cs.AI, cs.ET, cs.LG
Submitted: 2026-10-10
Updated: 2026-10-10
Sources
- Open-SWE-Traces: Advancing Dual-Mode Multilingual Distillation for Software Engineering Agents
- Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned
- Optimizing Model Selection for Compound AI Systems
- FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
- Uno-Orchestra: Parsimonious Agent Routing via Selective Delegation
- Dynamic Model Routing and Cascading for Efficient LLM Inference: A Survey
- xRouter: Training Cost-Aware LLMs Orchestration System via Reinforcement Learning
- ORACLE: Agentic AI Orchestrator Routing Via Adaptive Verifier Calibration Feedback
- Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering
- ReAct: Synergizing Reasoning and Acting in Language Models
- Budget-Aware Agentic Routing via Boundary-Guided Training
Related papers
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
- PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
- IntentCoding: Amplifying User Intent in Code Generation
- Incentives and Outcomes in Bug Bounties