# Scaling Small Agents Through Strategy Auctions arXiv: https://arxiv.org/abs/2602.02751 ยท HTML: https://mlsanity.com/paper/2602.02751/ ## Key facts - Cited by 3 papers in the map (data through 14 Oct 2026). - Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. - Builds on 30 of its 78 references that are in the map. - First posted on arXiv 2 Feb 2026. ## Placed in - 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 30) - [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025) - [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021) - [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025) - [Measuring short-form factuality in large language models](https://mlsanity.com/paper/2411.04368/) (2024) - [Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models](https://mlsanity.com/paper/2404.18796/) (2024) - [Small Language Models are the Future of Agentic AI](https://mlsanity.com/paper/2506.02153/) (2025) - [RouterBench: A Benchmark for Multi-LLM Routing System](https://mlsanity.com/paper/2403.12031/) (2024) - [MIRIX: Multi-Agent Memory System for LLM-Based Agents](https://mlsanity.com/paper/2507.07957/) (2025) - [Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution](https://mlsanity.com/paper/2512.10696/) (2025) - [LeetCodeDataset: A Temporal Dataset for Robust Evaluation and Efficient Training of Code LLMs](https://mlsanity.com/paper/2504.14655/) (2025) - [The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs](https://mlsanity.com/paper/2509.09677/) (2025) - [OdysseyBench: Evaluating LLM Agents on Long-Horizon Complex Office Application Workflows](https://mlsanity.com/paper/2508.09124/) (2025) - [From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents](https://mlsanity.com/paper/2506.18959/) (2025) - [CARROT: A Cost Aware Rate Optimal Router](https://mlsanity.com/paper/2502.03261/) (2025) - [Metacognitive Reuse: Turning Recurring LLM Reasoning Into Concise Behaviors](https://mlsanity.com/paper/2509.13237/) (2025) - [ARE: Scaling Up Agent Environments and Evaluations](https://mlsanity.com/paper/2509.17158/) (2025) - [Causal LLM Routing: End-to-End Regret Minimization from Observational Data](https://mlsanity.com/paper/2505.16037/) (2025) - [AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities](https://mlsanity.com/paper/2508.11126/) (2025) - [Virtual Agent Economies](https://mlsanity.com/paper/2509.10147/) (2025) - [Grading Scale Impact on LLM-as-a-Judge: Human-LLM Alignment Is Highest on 0-5 Grading Scale](https://mlsanity.com/paper/2601.03444/) (2026) - [Agent Exchange: Shaping the Future of AI Agent Economics](https://mlsanity.com/paper/2507.03904/) (2025) - [LLM Bidders Preserve the Mechanism-Level Orderings of Human Bidders](https://mlsanity.com/paper/2507.09083/) (2025) - [Can LLM-Reasoning Models Replace Classical Planning? A Benchmark Study](https://mlsanity.com/paper/2507.23589/) (2025) - [Efficient LLM Collaboration via Planning](https://mlsanity.com/paper/2506.11578/) (2025) - [Profile-Aware Maneuvering: A Dynamic Multi-Agent System for Robust GAIA Problem Solving by AWorld](https://mlsanity.com/paper/2508.09889/) (2025) - [Open Agent Specification (Agent Spec): A Unified Representation for AI Agents](https://mlsanity.com/paper/2510.04173/) (2025) - [GitHub Copilot: the perfect Code compLeeter?](https://mlsanity.com/paper/2406.11326/) (2024) - [Provable Benefits of In-Tool Learning for Large Language Models](https://mlsanity.com/paper/2508.20755/) (2025) - [Bayesian Orchestration of Multi-LLM Agents for Cost-Aware Sequential Decision-Making](https://mlsanity.com/paper/2601.01522/) (2026) - [Reasoning-Aware Prompt Orchestration: A Foundation Model for Multi-Agent Language Model Coordination](https://mlsanity.com/paper/2510.00326/) (2025) ## Built on by (most cited first, 3 of 3) - [MarketBench: Evaluating AI Agents as Market Participants](https://mlsanity.com/paper/2604.23897/) (2026) - [RSI-Router: Evolving Subtask-Level LLM Routing and Skills for Cost-Efficient Agents](https://mlsanity.com/paper/2609.34712/) (2026) - [What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agents](https://mlsanity.com/paper/2609.39989/) (2026) ## Abstract (arXiv) Small language models are increasingly viewed as a promising, cost-effective approach to agentic AI, with proponents claiming they are sufficiently capable for agentic workflows. However, while smaller agents can closely match larger ones on simple tasks, it remains unclear how their performance scales with task complexity, when large models become necessary, and how to better leverage small agents for long-horizon workloads. In this work, we empirically show that small agents' performance fails to scale with task complexity on deep search and coding tasks, and we introduce Strategy Auctions for Workload Efficiency (SALE), an agent framework inspired by freelancer marketplaces. In SALE, agents bid with short strategic plans, which are scored by a systematic cost-value mechanism and refined via a shared auction memory, enabling per-task routing and continual self-improvement without training a separate router or running all models to completion. Across deep search and coding tasks of varying complexity, SALE reduces reliance on the largest agent by 52%, lowers overall cost by 35%, and consistently improves upon the largest agent's pass@1 with only a negligible overhead beyond executing the final trace. In contrast, established routers that rely on task descriptions either underperform the largest agent or fail to reduce cost, often both, underscoring their poor fit for agentic workflows. These results suggest that while small agents may be insufficient for complex workloads, they can be effectively "scaled up" through coordinated task allocation and test-time self-improvement. More broadly, they motivate a systems-level view of agentic AI in which performance gains come less from ever-larger individual models and more from market-inspired coordination mechanisms that organize heterogeneous agents into efficient, adaptive ecosystems.