# Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs

arXiv: https://arxiv.org/abs/2505.19481 · HTML: https://mlsanity.com/paper/2505.19481/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use.
- Builds on 28 of its 40 references that are in the map.
- First posted on arXiv 26 May 2025.

## Placed in

- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 28 of 28)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [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)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [Phi-4 Technical Report](https://mlsanity.com/paper/2412.08905/) (2024)
- [The StarCraft Multi-Agent Challenge](https://mlsanity.com/paper/1902.04043/) (2019)
- [KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization](https://mlsanity.com/paper/2401.18079/) (2024)
- [BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions](https://mlsanity.com/paper/2406.15877/) (2024)
- [Atom: Low-bit Quantization for Efficient and Accurate LLM Serving](https://mlsanity.com/paper/2310.19102/) (2023)
- [QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving](https://mlsanity.com/paper/2405.04532/) (2024)
- [FP8 Formats for Deep Learning](https://mlsanity.com/paper/2209.05433/) (2022)
- [SCROLLS: Standardized CompaRison Over Long Language Sequences](https://mlsanity.com/paper/2201.03533/) (2022)
- [SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models](https://mlsanity.com/paper/2411.05007/) (2024)
- [FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design](https://mlsanity.com/paper/2311.13743/) (2023)
- [GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM](https://mlsanity.com/paper/2403.05527/) (2024)
- [A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist](https://mlsanity.com/paper/2402.18485/) (2024)
- [RecMind: Large Language Model Powered Agent For Recommendation](https://mlsanity.com/paper/2308.14296/) (2023)
- [OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models](https://mlsanity.com/paper/2306.02272/) (2023)
- [Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach](https://mlsanity.com/paper/2312.11865/) (2023)
- [Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance](https://mlsanity.com/paper/2203.08368/) (2022)
- [A Practical Mixed Precision Algorithm for Post-Training Quantization](https://mlsanity.com/paper/2302.05397/) (2023)
- [AI Metropolis: Scaling Large Language Model-based Multi-Agent Simulation with Out-of-order Execution](https://mlsanity.com/paper/2411.03519/) (2024)
- [DIAMBRA Arena: a New Reinforcement Learning Platform for Research and Experimentation](https://mlsanity.com/paper/2210.10595/) (2022)

## Built on by (most cited first, 9 of 9)

- [OckBench: Measuring the Efficiency of LLM Reasoning](https://mlsanity.com/paper/2511.05722/) (2025)
- [PrefIx: Understand and Adapt to User Preference in Human-Agent Interaction](https://mlsanity.com/paper/2602.06714/) (2026)
- [Learning Latency-Aware Orchestration for Multi-Agent Systems](https://mlsanity.com/paper/2601.10560/) (2026)
- [Accelerating Multi-modal LLM Gaming Performance via Input Prediction and Mishit Correction](https://mlsanity.com/paper/2512.17250/) (2025)
- [The Speedup Paradox: Rethinking Inference Speed-Quality Trade-off in Embodied Tasks](https://mlsanity.com/paper/2606.28529/) (2026)
- [From Performance to Purpose: A Sociotechnical Taxonomy for Evaluating Large Language Model Utility](https://mlsanity.com/paper/2602.20513/) (2026)
- [Memory in the Loop: In-Process Retrieval as Extended Working Memory for Language Agents](https://mlsanity.com/paper/2607.05690/) (2026)
- [Learning Latency-Aware Orchestration for Multi-Agent Systems](https://mlsanity.com/paper/2607.13359/) (2026)
- [StreamDecisionBench: Evaluating Decisions in Force on Evolving Language Streams](https://mlsanity.com/paper/2609.38612/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have shown remarkable performance across diverse reasoning and generation tasks, and are increasingly deployed as agents in dynamic environments such as code generation and recommendation systems. However, many real-world applications, such as high-frequency trading and real-time competitive gaming, require decisions under strict latency constraints, where faster responses directly translate into higher rewards. Despite the importance of this latency quality trade off, it remains underexplored in the context of LLM based agents. In this work, we present the first systematic study of this trade off in real time decision making tasks. To support our investigation, we introduce two new benchmarks: HFTBench, a high frequency trading simulation, and StreetFighter, a competitive gaming platform. Our analysis reveals that optimal latency quality balance varies by task, and that sacrificing quality for lower latency can significantly enhance downstream performance. To address this, we propose FPX, an adaptive framework that dynamically selects model size and quantization level based on real time demands. Our method achieves the best performance on both benchmarks, improving win rate by up to 80% in Street Fighter and boosting daily yield by up to 26.52% in trading, underscoring the need for latency aware evaluation and deployment strategies for LLM based agents. These results demonstrate the critical importance of latency aware evaluation and deployment strategies for real world LLM based agents. Our benchmarks are available at Latency Sensitive Benchmarks.