让大模型在测试时动态合成新技能，提升任务表现。
Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents
- 测试时检索相关训练轨迹，动态合成临时技能。
- 在多个基准上超越现有方法，用更少算力达到更高性能。
- 适合需要快速适应新任务的智能体系统开发者。
额外的测试时计算可使大模型智能体访问更多过往经验，但扩展上下文或增加推演并不必然提升智能体能力。我们称此为测试时算力到能力的转化挑战，并提出SkillTTA：该方法检索与任务相关的训练轨迹，基于可见目标上下文合成一个临时技能，且求解器参数固定。为进一步突破性能上限，SkillTTA引入元提示优化（MPO），用于适配生成技能的策略。MPO在成对任务上评估候选提示，强调信息量丰富的状态转移；同时将更新限制在特定基准的原子槽位中，降低因间接通过技能合成和求解器推演观察修改所导致的方差。在ALFWorld、SpreadsheetBench、BigCodeBench和WebShop四个基准上，SkillTTA均优于当前最先进的复用与优化基线，以更低的算力成本实现更高的性能天花板。
原文摘要 · Abstract (English)
Additional test-time compute can give LLM agents access to more past experience, yet expanding the context or adding rollouts does not necessarily yield greater agent capability. We call this challenge test-time compute-to-capability conversion and propose SkillTTA, which retrieves task-relevant training trajectories and synthesizes a temporary skill conditioned on the visible target context for a solver with fixed parameters. To pursue a higher performance ceiling, SkillTTA further uses meta prompt optimization (MPO) to adapt the policy that writes these skills. MPO evaluates candidate prompts on paired tasks and emphasizes informative transitions. It also confines updates to benchmark-specific atomic slots, reducing the variance caused by observing each edit only indirectly through skill synthesis and solver rollout. Across ALFWorld, SpreadsheetBench, BigCodeBench, and WebShop, SkillTTA outperforms state-of-the-art reuse and optimization baselines. It attains a higher performance ceiling at lower compute cost than baseline reuse and sampling strategies.
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。