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

arXiv: https://arxiv.org/abs/2608.25399 · HTML: https://mlsanity.com/paper/2608.25399/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 18 of its 22 references that are in the map.
- First posted on arXiv 26 Aug 2026.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 18 of 18)

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024)
- [SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?](https://mlsanity.com/paper/2509.16941/) (2025)
- [AI Agents That Matter](https://mlsanity.com/paper/2407.01502/) (2024)
- [SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?](https://mlsanity.com/paper/2603.15401/) (2026)
- [Efficient multi-prompt evaluation of LLMs](https://mlsanity.com/paper/2405.17202/) (2024)
- [SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoning](https://mlsanity.com/paper/2505.11274/) (2025)
- [Ambig-SWE: Interactive Agents to Overcome Underspecificity in Software Engineering](https://mlsanity.com/paper/2502.13069/) (2025)
- [OptimalThinkingBench: Evaluating Over and Underthinking in LLMs](https://mlsanity.com/paper/2508.13141/) (2025)
- [How Do AI Agents Spend Your Money? Analyzing and Predicting Token Consumption in Agentic Coding Tasks](https://mlsanity.com/paper/2604.22750/) (2026)
- [Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs](https://mlsanity.com/paper/2507.02076/) (2025)
- [Value of Information: A Framework for Human-Agent Communication](https://mlsanity.com/paper/2601.06407/) (2026)
- [Adaptive Test-Time Compute Allocation for Reasoning LLMs via Constrained Policy Optimization](https://mlsanity.com/paper/2604.14853/) (2026)
- [ClarEval: A Benchmark for Evaluating Clarification Skills of Code Agents under Ambiguous Instructions](https://mlsanity.com/paper/2603.00187/) (2026)
- [When Prompt Under-Specification Improves Code Correctness: An Exploratory Study of Prompt Wording and Structure Effects on LLM-Based Code Generation](https://mlsanity.com/paper/2604.24712/) (2026)
- [Re-Evaluating Code LLM Benchmarks Under Semantic Mutation](https://mlsanity.com/paper/2506.17369/) (2025)
- [What Makes a Good Bug Report for an AI Agent?](https://mlsanity.com/paper/2607.07593/) (2026)

## Built on by (most cited first, 1 of 1)

- [Enterprise Representation Simplification (ERS): Reducing Representational Complexity for Enterprise AI](https://mlsanity.com/paper/2610.00791/) (2026)

## Abstract (arXiv)

Agentic coding workflows are now widely deployed in real-world systems. With long-horizon reasoning and tool use, token usage has become an important consideration for both cost and efficiency. Two engineers using AI will solve the same problem differently. How the specification of a task shapes an agent's token spend, and whether that spend can be predicted in advance, are open questions. Here, we study the effects of different task specifications on agentic token spend with the Kimi K3 model at three thinking efforts. Across 2,700 runs, we show that reducing a full task specification to a bare user story raises token spend by 29.7%, while run-to-run variance remains unaffected by any prompt changes. We show that prompt-sensitivity is task-dependent, running from 13% to 115%. We fit a simple predictor that can price a full distribution of task specifications and thinking effort configurations from a single cheap probe on an unseen task within 36%, improving over prior work in predicting token spend. Our work provides initial results quantifying the effects of task specification on agentic token spend and introduces a method that can be used to systematically evaluate the cost of AI coding workflows.