Analyzing and Mitigating Cost-Inefficient Behaviors in Coding Agents

arXiv:2609.30725 · cs.AI, cs.SE · Submitted 2026-09-25 · Read on arXiv

cs.AI, cs.SE

Submitted: 2026-09-25

Updated: 2026-09-28

Code: https://github.com/colbymchenry/codegraph

Terminology

• Benchmark — 23× in this paper · explained in 2 episodes
• Verification — 20× in this paper · explained in 2 episodes
• Claude Code — 17× in this paper
• Trace — 14× in this paper · explained in 2 episodes
• Agent Skills — 8× in this paper · explained in 1 episode
• Benchmarking — 3× in this paper · explained in 3 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• AI Agents — 2× in this paper · explained in 2 episodes
• Abstraction — 2× in this paper · explained in 1 episode
• Accuracy — 2× in this paper · explained in 1 episode
• Agent Architectures — 2× in this paper · explained in 1 episode
• Agentic Coding — 2× in this paper · explained in 1 episode
• Multi-Agent System — 2× in this paper · explained in 5 episodes
• Agentic System — 1× in this paper · explained in 2 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Continual Learning — 1× in this paper · explained in 2 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• International Conference on Automated Software Engineering — 1× in this paper
• LLM judge — 1× in this paper · explained in 2 episodes
• Multi-objective Optimization — 1× in this paper · explained in 4 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Scaffolding — 1× in this paper · explained in 3 episodes

Sources

• EvoSkill: Automated Skill Discovery for Multi-Agent Systems
• Understanding Automated Program Repair Agents Through the Lens of Traceability: An Empirical Study
• SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
• More with Less: An Empirical Study of Turn-Control Strategies for Efficient Coding Agents
• SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering
• Compressing Code Context for LLM-based Issue Resolution
• AI Agents That Matter
• Coherence Collapse: Diagnosing Why Code Agents Fail After Reaching the Right Code
• Beyond the Final Answer: Evaluating the Reasoning Trajectories of Tool-Augmented Agents
• SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
• Budget-Aware Tool-Use Enables Effective Agent Scaling
• ContextSniper: AntTrail's Token-Efficient Code Memory for Repository-Level Program Repair
• SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
• Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations
• Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
• RouteLLM: Learning to Route LLMs with Preference Data
• The Hidden Cost of Readability: How Code Formatting Silently Consumes Your LLM Budget
• Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering
• ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration
• SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection