让小模型高效执行复杂任务，关键在学会控上下文和分步规划。
Scaling Agentic Capabilities, Not Context: Efficient Reinforcement Finetuning for Large Toolspaces
- 把上下文管理和动作执行当作可学策略，动态加载工具并编排流程。
- 在MCP基准上，40亿小模型性能逼近大模型，上下文占用减少80%。
- 适合资源有限但需长流程决策的智能体应用，如自动化运维、数据分析。
在大规模工具生态中运行的智能体需在弱监督或不可验证环境下规划并执行长周期工作流。尽管前沿模型通过规模和大上下文预算缓解挑战，小语言模型（SLMs）仍存在脆弱性：工具过早加载会耗尽上下文，执行错误随时间累积，稀疏奖励限制学习效果。我们提出ATLAS，一种强化微调框架，使SLMs能在大规模工具空间中有效运作，通过学习如何获取上下文与执行动作实现优化。方法上，将上下文控制与执行结构视为可学习决策，结合迭代式工具加载与程序化工具编排，抑制上下文增长并稳定长周期轨迹；同时引入基于评分标准的强化微调，将任务成功分解为结构化、任务对齐的评估指标，支持使用小型裁判模型进行可扩展训练。在MCP基准测试中，该设计显著优于通用强化学习基线，使40亿参数的SLM在远更紧的参数与上下文约束下接近前沿智能体表现。
原文摘要 · Abstract (English)
Agentic systems operating over large tool ecosystems must plan and execute long-horizon workflows under weak or non-verifiable supervision. While frontier models mitigate these challenges through scale and large context budgets, small language models (SLMs) remain brittle: eager tool loading saturates context, execution errors compound over time, and sparse rewards limit learning. We introduce ATLAS, a reinforcement finetuning framework that enables SLMs to operate effectively in large-scale toolspace environments by learning how to acquire context and how to execute actions. Our approach makes two key contributions. First, we treat context control and execution structure as learnable decisions, combining iterative tool loading with programmatic tool orchestration to bound context growth and stabilize long-horizon trajectories. Second, we propose rubric-based reinforcement finetuning, which decomposes task success into structured, task-aligned criteria and enables scalable training using small judge models. Across MCP benchmarks, these design choices yield large and consistent gains over generic RL baselines, allowing a 4B SLM to approach frontier-agent performance under far tighter parameter and context budgets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。