SkillChain: Closing the Loop on Skill Evolution for Image-Based E-Commerce AI Assistants
Not on the map. Why?
Abstract (arXiv)
Image-based AI assistants are now deployed at production scale on e-commerce platforms, where a single uploaded image can trigger fundamentally different user intents: product search, style recommendation, visual encyclopedia, or utility tool calls, each demanding its own response format, tool invocation, and domain knowledge. Without per-intent behavioral constraints, LLM-based systems conflate these heterogeneous modes and fall short of domain quality standards, while the breadth and dynamism of the intent space render manual engineering infeasible. To address this, we present SkillChain, which closes the production feedback loop on Skill evolution, automating the lifecycle of Skills through three stages: Skill Creator for bootstrapping from task specs and trajectories, Route Optimizer for routing alignment, and Body Refiner for iterative Skill Body refinement via dual-path LLM-Judge evaluation. Deployed on a production-scale e-commerce image assistant, SkillChain substantially improves aggregate response quality, with the strongest gains on structural compliance and content quality; a one-week online A/B experiment further confirms significant gains in user engagement, content consumption, and long-term retention.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 39 references that are in the map. First posted on arXiv 11 Jun 2026.
Builds on
27 of 39 references.
References · 27
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2022Training language models to follow instructions with human feedbackcited by 15,971
- 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
- 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
- 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
- 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
- 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
- 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
- 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
- 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,332
- 2023ExpeL: LLM Agents Are Experiential Learnerscited by 876
15 more
- 2023Large Language Models as Optimizerscited by 864
- 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 832
- 2023Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memorycited by 289
- 2026SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learningcited by 278
- 2026SoK: Agentic Skills -- Beyond Tool Use in LLM Agentscited by 130
- 2026CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verificationcited by 128
- 2026AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolutioncited by 115
- 2026SkillClaw: Let Skills Evolve Collectively with Agentic Evolvercited by 81
- 2026SkillX: Automatically Constructing Skill Knowledge Bases for Agentscited by 76
- 2026XSkill: Continual Learning from Experience and Skills in Multimodal Agentscited by 75
- 2026Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skillscited by 55
- 2026SkillForge: Forging Domain-Specific, Self-Evolving Agent Skills in Cloud Technical Supportcited by 48
- 2026Dynamic Dual-Granularity Skill Bank for Agentic RLcited by 34
- 2026ARISE: Agent Reasoning with Intrinsic Skill Evolution in Hierarchical Reinforcement Learningcited by 29
- 2026WebXSkill: Skill Learning for Autonomous Web Agentscited by 24
Built on by
Not cited yet.