InferenceBench: A Benchmark for Open-Ended LLM Inference Optimization by AI Agents

• URL: http://arxiv.org/abs/2607.20468v1
• Date: Wed, 20 May 2026 15:55:21 GMT
• Title: InferenceBench: A Benchmark for Open-Ended LLM Inference Optimization by AI Agents
• Abstract summary: We introduce InferenceBench, where an agent must deploy an OpenAI-compatible inference server and optimize the speed of LLM inference.<n>Three optimization scenarios isolate distinct bottlenecks of inference.<n>Agents reliably improve over a naive PyTorch baseline.<n>Overall, InferenceBench reflects the ability of agents to operate in an open-ended AI engineering setting.
• Score: 15.892896819368751
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: AI agents are increasingly used to automate research and development tasks, yet existing benchmarks typically evaluate them on prescribed workflows or narrow action spaces. Even nominally open-ended tasks can often be solved by retrieving a well-known recipe and tuning a few hyperparameters, making it unclear whether strong results reflect genuine optimization or memorized solutions. We introduce InferenceBench, where an agent must deploy an OpenAI-compatible inference server and optimize the speed of LLM inference. Each agent receives a target LLM, one H100 GPU, an optimization scenario, and a wall-clock time budget of two hours. Three optimization scenarios isolate distinct bottlenecks of inference (prefill latency, decode latency, and concurrent request throughput) and a fourth balances all three at the same time. Across 15 frontier agent configurations, agents reliably improve over a naive PyTorch baseline (up to $8.08\times$) and often match or exceed serving engines with default settings ($4.05\times$ for vLLM), but still fall below a simple hyperparameter search under the same time budget (up to $11.53\times$). Qualitative analysis of agent trajectories shows that although agents enumerate many relevant optimization techniques, they overwhelmingly converge on a single inference framework. They test only a few distinct configurations and spend the remaining budget re-measuring, repairing, or optimizing hyperparameters rather than exploring substantially different strategies. This suggests the bottleneck is not domain knowledge, but the ability to propose diverse configurations, evaluate them systematically, and submit the best identified solution. Overall, InferenceBench reflects the ability of agents to operate in an open-ended AI engineering setting, where memorized solutions lead to limited improvements.

Related papers

• The Optimizer Is the Agent: Reasoning-Driven Search across Prompts, Programs, and ML Workflows [72.9051182568928]
  We present ReASearch, a unified framework for reasoning-driven optimization.<n>With a shared agent loop and domain-specific tools, ReASearch instantiates the exact same scaffold to optimize prompts, programs, and ML.<n>We observe that complex search behaviors emerge naturally from the agent's reasoning process.
  arXiv  Detail & Related papers  (2026-08-07T02:15:39Z)
• optimize_anything: A Universal API for Optimizing any Text Parameter [98.42497715725356]
  We show a single AI-based optimization system-supporting single-task search, multi-task search with cross-problem transfer, and generalization to unseen inputs.<n>We show for the first time that text optimization with LLM-based search is a general-purpose problem-solving paradigm.
  arXiv  Detail & Related papers  (2026-05-19T10:18:12Z)
• Multi-Agent Reasoning Improves Compute Efficiency: Pareto-Optimal Test-Time Scaling [11.219930588268433]
  computational efficiency is key for real-world applications with resource constraints.<n>We provide a systematic analysis of the inference scaling strategies self-consistency, self-refinement, multi-agent debate, and mixture-of-agents.<n>We identify a simple multi-agent design guideline: mixture-of-agents is most efficient when the number of parallel generations exceeds the number of sequential aggregations.
  arXiv  Detail & Related papers  (2026-05-02T18:31:02Z)
• AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation [59.964989458924585]
  AdaExplore is an agent framework that enables self-improvement via accumulated execution feedback for performance-critical kernel code generation.<n>In the adaptation stage, the agent synthesizes tasks and converts recurring failures into a reusable memory of validity rules.<n>In the search stage, the agent organizes candidate kernels as a tree and alternates between small local refinements and larger structural regeneration.
  arXiv  Detail & Related papers  (2026-04-17T18:25:03Z)
• Agent-GWO: Collaborative Agents for Dynamic Prompt Optimization in Large Language Models [69.55139736609367]
  Agent-GWO is a dynamic prompt optimization framework for complex reasoning.<n>We show that Agent-GWO consistently improves accuracy and stability over existing prompt optimization methods.
  arXiv  Detail & Related papers  (2026-04-14T07:35:37Z)
• AgentOpt v0.1 Technical Report: Client-Side Optimization for LLM-Based Agent [18.58248061903799]
  We introduce AgentOpt, the first framework-agnostic Python package for client-side AI optimization.<n>We first study model selection, a high-impact optimization lever in multi-step agent pipelines.<n>To efficiently explore the exponentially growing combination space, AgentOpt implements ten search algorithms.
  arXiv  Detail & Related papers  (2026-04-07T17:13:47Z)
• Efficient and Interpretable Multi-Agent LLM Routing via Ant Colony Optimization [58.59491516762626]
  We propose AMRO-S, an efficient and interpretable routing framework for Multi-Agent Systems (MAS)<n>AMRO-S models MAS routing as a semantic-conditioned path selection problem, enhancing routing performance through three key mechanisms.<n>Extensive experiments on five public benchmarks and high-concurrency stress tests demonstrate that AMRO-S consistently improves the quality--cost trade-off over strong routing baselines.
  arXiv  Detail & Related papers  (2026-03-13T12:26:05Z)
• Towards Efficient Agents: A Co-Design of Inference Architecture and System [66.59916327634639]
  This paper presents AgentInfer, a unified framework for end-to-end agent acceleration.<n>We decompose the problem into four synergistic components: AgentCollab, AgentSched, AgentSAM, and AgentCompress.<n>Experiments on the BrowseComp-zh and DeepDiver benchmarks demonstrate that through the synergistic collaboration of these methods, AgentInfer reduces ineffective token consumption by over 50%.
  arXiv  Detail & Related papers  (2025-12-20T12:06:13Z)
• syftr: Pareto-Optimal Generative AI [40.80352098169579]
  syftr is a framework that performs efficient multi-objective search over a broad space of agentic and non-agentic RAG configurations.<n>Syftr finds flows which are on average approximately 9 times cheaper while preserving most of the accuracy of the most accurate flows.
  arXiv  Detail & Related papers  (2025-05-26T17:43:13Z)
• Multi-Agent Reinforcement Learning for Microprocessor Design Space Exploration [71.95914457415624]
  Microprocessor architects are increasingly resorting to domain-specific customization in the quest for high-performance and energy-efficiency. We propose an alternative formulation that leverages Multi-Agent RL (MARL) to tackle this problem. Our evaluation shows that the MARL formulation consistently outperforms single-agent RL baselines.
  arXiv  Detail & Related papers  (2022-11-29T17:10:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.