SPARO (Skill, Prompt, And Routing Optimization), a framework that jointly optimizes task instructions, reusable skill blocks, and routing rules, is proposed, suggesting that effective language-program optimization depends not only on discovering useful task knowledge, but also on deciding where that knowledge should be stored and when it should be activated.
Abstract
Large language models can solve increasingly diverse reasoning tasks, yet their performance remains highly sensitive to task prompts, intermediate instructions, and the way reusable problem-solving knowledge is incorporated. Existing optimization methods usually focus on only one part of this design space: they either optimize a monolithic prompt, or separately induce and refine skills from model traces. As a result, they lack a principled mechanism for deciding which component should be updated when failures occur, and they rarely optimize prompts, skills, and skill-use policies in a unified framework. We propose SPARO (Skill, Prompt, And Routing Optimization), a framework that jointly optimizes task instructions, reusable skill blocks, and routing rules. It performs controlled counterfactual evaluations, converts examples'effects into a probabilistic responsibility distribution over prompt, skill, and routing components, samples one component from that distribution, and applies the corresponding targeted mutation. This design moves language-program optimization beyond global prompt rewriting toward structured, reusable, and selectively activated task knowledge. Across five benchmarks and five worker models, SPARO consistently outperforms both prompt-centered and skill-centered optimization baselines. These results suggest that effective language-program optimization depends not only on discovering useful task knowledge, but also on deciding where that knowledge should be stored and when it should be activated.
Automated operations research (OR) modeling requires LLMs to translate natural-language decision problems into correct mathematical programs. Existing methods can improve individual formulations, but they often solve problems in isolation, retaining little reusable experience and repeating similar formulation errors. P...
StraTune (strategy-guided skill tuning), which lets a frozen optimizer LLM choose the revision operator at every round from the optimization state, which is defined as the current execution feedback together with the recorded outcomes of earlier strategies and forms.
Ze-Ping Liu, Yan Li, Ni Lao et al.· arXiv.org· 0 citations
Adaptive-GEPA is introduced, which learns both how to divide requests and how to solve them, and it evolves a router and a library of specialist programs under one search budget.
Tian-Yu Chen, Yasi Zhang, Rui-Yi Wang et al.· arXiv.org· 0 citations
Skills are external artifacts that Large Language Models (LLMs) consume at inference time to improve their performance on specialized domains by incorporating relevant procedural and domain knowledge. Expert-authored skills are expensive to produce, and the resulting artifacts are not optimized for the specific model t...
B. Ni, Li Li, Ryan A. Rossi et al.· arXiv.org· 0 citations
DynaContext is introduced, a framework that combines an offline-optimized extraction core, learned with GEPA or SkillOpt, with inference-time contextual adaptation and validation-gated self-improvement, with inference-time contextual adaptation and validation-gated self-improvement.
Joe Yu, Shibin Thomas Stanley Paul, Sven Mayer· 0 citations
SkillSandbox is proposed, a framework that dynamically synthesizes a task and its environment for each skill that are skill-relevant yet novel that yields the strongest downstream performance and improved execution efficiency across ALFWorld and WebShop with three models.
Serin Kim, Kwangwook Seo, Dok-Yung Song et al.· 0 citations