Can your AI agent be cheaper? Investigating the effects of task specifications on token spend in agentic coding tasks

arXiv:2608.25399 · cs.AI · Submitted 2026-08-26 · Read on arXiv

cs.AI

Submitted: 2026-08-26

Updated: 2026-08-26

Code: https://github.com/github/spec-kit

Terminology

• Agentic Coding — 11× in this paper · explained in 1 episode
• Core — 6× in this paper · explained in 2 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Benchmark — 3× in this paper · explained in 2 episodes
• AI Agents — 2× in this paper · explained in 2 episodes
• Benchmarking — 2× in this paper · explained in 3 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Agent Skills — 1× in this paper · explained in 1 episode
• In International Conference on Learning Representations — 1× in this paper
• Sparsity — 1× in this paper · explained in 4 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• OptimalThinkingBench: Evaluating Over and Underthinking in LLMs
• When Prompt Under-Specification Improves Code Correctness: An Exploratory Study of Prompt Wording and Structure Effects on LLM-Based Code Generation
• Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs
• How Do AI Agents Spend Your Money? Analyzing and Predicting Token Consumption in Agentic Coding Tasks
• SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
• Value of Information: A Framework for Human-Agent Communication
• SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?
• AI Agents That Matter
• What Makes a Good Bug Report for an AI Agent?
• ClarEval: A Benchmark for Evaluating Clarification Skills of Code Agents under Ambiguous Instructions
• SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoning
• Re-Evaluating Code LLM Benchmarks Under Semantic Mutation
• Agentless: Demystifying LLM-based Software Engineering Agents
• SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
• Adaptive Test-Time Compute Allocation for Reasoning LLMs via Constrained Policy Optimization

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