# The Cost of Dynamic Reasoning: Demystifying AI Agents and Test-Time Scaling from an AI Infrastructure Perspective

arXiv: https://arxiv.org/abs/2506.04301 · HTML: https://mlsanity.com/paper/2506.04301/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 54 of its 104 references that are in the map.
- First posted on arXiv 4 Jun 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 54)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [Graph of Thoughts: Solving Elaborate Problems with Large Language Models](https://mlsanity.com/paper/2308.09687/) (2023)
- [Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads](https://mlsanity.com/paper/2401.10774/) (2024)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models](https://mlsanity.com/paper/2310.04406/) (2023)

## Built on by (most cited first, 30 of 39)

- [A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence](https://mlsanity.com/paper/2507.21046/) (2025)
- [A Survey of Context Engineering for Large Language Models](https://mlsanity.com/paper/2507.13334/) (2025)
- [What Is Your AI Agent Buying? Evaluation, Biases, Model Dependence, & Emerging Implications for Agentic E-Commerce](https://mlsanity.com/paper/2508.02630/) (2025)
- [Murakkab: Resource-Efficient Agentic Workflow Orchestration in Cloud Platforms](https://mlsanity.com/paper/2508.18298/) (2025)
- [AgentCgroup: Understanding and Controlling OS Resources of AI Agents](https://mlsanity.com/paper/2602.09345/) (2026)
- [AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent](https://mlsanity.com/paper/2602.03955/) (2026)
- [Inference-Time Budget Control for LLM Search Agents](https://mlsanity.com/paper/2605.05701/) (2026)
- [SWE-Replay: Efficient Test-Time Scaling for Software Engineering Agents](https://mlsanity.com/paper/2601.22129/) (2026)
- [AutoTool: Efficient Tool Selection for Large Language Model Agents](https://mlsanity.com/paper/2511.14650/) (2025)
- [Spend Less, Reason Better: Budget-Aware Value Tree Search for LLM Agents](https://mlsanity.com/paper/2603.12634/) (2026)
- [Routine: A Structural Planning Framework for LLM Agent System in Enterprise](https://mlsanity.com/paper/2507.14447/) (2025)
- [ICaRus: Identical Cache Reuse for Efficient Multi Model Inference](https://mlsanity.com/paper/2603.13281/) (2026)
- [SLR: Automated Synthesis for Scalable Logical Reasoning](https://mlsanity.com/paper/2506.15787/) (2025)
- [AgentStop: Terminating Local AI Agents Early to Save Energy in Consumer Devices](https://mlsanity.com/paper/2605.15206/) (2026)
- [EZBlender: Efficient 3D Editing with Plan-and-ReAct Agent](https://mlsanity.com/paper/2601.07143/) (2026)
- [From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems](https://mlsanity.com/paper/2608.15127/) (2026)
- [Towards Understanding, Analyzing, and Optimizing Agentic AI Execution: A CPU-Centric Perspective](https://mlsanity.com/paper/2511.00739/) (2025)
- [PrefillShare: A Shared Prefill Module for KV Reuse in Multi-LLM Disaggregated Serving](https://mlsanity.com/paper/2602.12029/) (2026)
- [From Logic Monopoly to Social Contract: Separation of Power and the Institutional Foundations for Autonomous Agent Economies](https://mlsanity.com/paper/2603.25100/) (2026)
- [Characterization of Multi-Model Agentic AI Systems on General Tasks via Trace-Driven Simulation](https://mlsanity.com/paper/2606.01725/) (2026)
- [Specialize Roles, Mix Deployments: Pushing the Cost-Accuracy Frontier of LLM Agent Teams](https://mlsanity.com/paper/2606.20629/) (2026)
- [Architectural Implications of Agentic AI Workflows](https://mlsanity.com/paper/2608.04458/) (2026)
- [Cost-Utility Alignment in LLM Agent Trajectories:Profiling,Attribution,Diagnosis,Adaptation,and Evaluation](https://mlsanity.com/paper/2608.26195/) (2026)
- [ORION: Teaching Language Models to Reason Efficiently in the Language of Thought](https://mlsanity.com/paper/2511.22891/) (2025)
- [KAIROS: Stateful, Context-Aware Power-Efficient Agentic Inference Serving](https://mlsanity.com/paper/2604.16682/) (2026)
- [The Sim-to-Real Gap of Foundation Model Agents: A Unified MDP Perspective](https://mlsanity.com/paper/2606.07017/) (2026)
- [WhiFlash: Accelerating Speculative Decoding with Token-Level Cross-Paradigm Routing](https://mlsanity.com/paper/2606.07710/) (2026)
- [DevNous: An LLM-Based Multi-Agent System for Grounding IT Project Management in Unstructured Conversation](https://mlsanity.com/paper/2508.08761/) (2025)
- [The Meta-Prompting Protocol: Orchestrating LLMs via Adversarial Feedback Loops](https://mlsanity.com/paper/2512.15053/) (2025)
- [Tessera: Unlocking Heterogeneous GPUs through Kernel-Granularity Disaggregation](https://mlsanity.com/paper/2604.10180/) (2026)

## Abstract (arXiv)

Large-language-model (LLM)-based AI agents have recently showcased impressive versatility by employing dynamic reasoning, an adaptive, multi-step process that coordinates with external tools. This shift from static, single-turn inference to agentic, multi-turn workflows broadens task generalization and behavioral flexibility, but it also introduces serious concerns about system-level cost, efficiency, and sustainability. This paper presents the first comprehensive system-level analysis of AI agents, quantifying their resource usage, latency behavior, energy consumption, and datacenter-wide power consumption demands across diverse agent designs and test-time scaling strategies. We further characterize how AI agent design choices, such as few-shot prompting, reflection depth, and parallel reasoning, impact accuracy-cost tradeoffs. Our findings reveal that while agents improve accuracy with increased compute, they suffer from rapidly diminishing returns, widening latency variance, and unsustainable infrastructure costs. Through detailed evaluation of representative agents, we highlight the profound computational demands introduced by AI agent workflows, uncovering a looming sustainability crisis. These results call for a paradigm shift in agent design toward compute-efficient reasoning, balancing performance with deployability under real-world constraints.