SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure

• URL: http://arxiv.org/abs/2608.11079v2
• Date: Sun, 16 Aug 2026 16:13:50 GMT
• Title: SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure
• Abstract summary: Self-evolving agents accumulate reusable skills by appending successful procedures and failure fixes.<n> Generic prompt compression is ill-suited to this setting because a skill is not a flat passage.<n>We present SkillZip, an evaluation-free method that compresses a skill by finding its shortest faithful structural explanation.
• Score: 13.304443478478134
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Self-evolving agents accumulate reusable skills by appending successful procedures and failure fixes. Over time, the same requirement is often restated in several branches, examples, and warnings, while common action sequences are copied rather than reused. The resulting skill becomes expensive to inject and difficult to maintain. Generic prompt compression is ill-suited to this setting because a skill is not a flat passage: its name and description define when it applies, its workflow controls execution, its tool and output contracts constrain validity, and rare exceptions may remain essential even when no sampled task activates them. Evaluation-guided compression can test these behaviors, but it introduces rollouts, cost, and dependence on the compression-time evaluation set. We present SkillZip, an evaluation-free method that compresses a skill by finding its shortest faithful structural explanation. The intuition is explain once, reference many: state a repeated rule once at the scope where it applies, factor a repeated action sequence into a shared procedure, and keep only the differences as explicit exceptions. We formalize this intuition as a typed minimum description-length objective over a skill contract and a residual, subject to a hard coverage constraint for every extracted trigger, workflow edge, tool requirement, obligation, and output field. The formulation provides simple sharing thresholds, preserves unique rare rules by construction, and supports efficient local updates. SkillZip has a one-shot mode with one structured extraction call and deterministic optimization, and a continual Zip-on-Write mode that integrates each self-evolution patch without replaying tasks or reparsing the full history. Through comprehensive experimental evaluations, we demonstrate the effectiveness and superiority of SkillZip in compression performance, generalizability, and cost overhead.

Related papers

• SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries [23.125090024964674]
  Large Language Models (LLMs) increasingly act as agents whose procedural knowledge is stored in reusable skill packages and loaded at inference time.<n>Existing systems struggle to reuse routines below the whole-skill level, preserve procedural contracts during compression, keep compressed routines executable and expandable, and update the compressed library as skills evolve.<n>We propose SkillZip, an execution-aware procedural abstraction framework that performs contract-preserving compression over section-level graphs.
  arXiv  Detail & Related papers  (2026-08-06T05:03:31Z)
• Diagnosing Compositional Generalization in Sequential Robot Tasks [47.24821158025177]
  This paper studies compositional generalization through the lens of instruction-space coverage.<n>We decompose the generalization gap into three sources: textitmarginal instruction shift, textitinstruction-compositional shift, and textitcontext-action shift
  arXiv  Detail & Related papers  (2026-07-31T17:59:59Z)
• Adaptive state-action abstractions via rate-distortion [52.25810164390199]
  Reinforcement learning offers multiple techniques for building simple versions of complex tasks.<n>This paper proposes one such principle: refine the abstraction as soon as the learning error within it becomes comparable to the error induced by the abstraction itself.
  arXiv  Detail & Related papers  (2026-06-04T13:10:18Z)
• Skill-CMIB: Multimodal Agent Skill for Consistent Action via Conditional Multimodal Information Bottleneck [60.930825621351794]
  We introduce Conditional Multimodal Information Bottleneck (CMIB), a method for multimodal skill construction.<n>Unlike naive two-stream formulations, CMIB explicitly conditions the multimodal latent on the text skill, thus structurally reducing cross-modal redundancy.<n>We instantiate CMIB with a variational objective that makes its conditional decomposition tractable to optimize, yielding reusable multimodal skills.
  arXiv  Detail & Related papers  (2026-05-08T22:17:54Z)
• Explicit Dropout: Deterministic Regularization for Transformer Architectures [55.09895958546215]
  Dropout is a widely used regularization technique in deep learning, but its effects are typically realized through masking.<n>We propose a deterministic formulation that expresses dropout as an additive regularizer directly incorporated into the training loss.
  arXiv  Detail & Related papers  (2026-04-22T12:45:51Z)
• Compressed-Sensing-Guided, Inference-Aware Structured Reduction for Large Language Models [0.0]
  Large language models deliver strong generative performance but at the cost of massive parameter counts, memory use, and decoding latency.<n>We propose a unified compressed-sensing-guided framework for dynamic LLM execution.
  arXiv  Detail & Related papers  (2026-03-22T14:27:24Z)
• Theoretical Foundations of Prompt Engineering: From Heuristics to Expressivity [0.0]
  We study the family of functions obtainable by holding a Transformer backbone fixed as an executor and varying only the prompt.<n>We prove a constructive existential result showing that a single fixed backbone can approximate a broad class of target behaviors via prompts alone.
  arXiv  Detail & Related papers  (2025-12-14T13:42:20Z)
• One-Prompt Strikes Back: Sparse Mixture of Experts for Prompt-based Continual Learning [52.966712416640085]
  We propose SMoPE, a novel framework that integrates the benefits of both task-specific and shared prompt strategies.<n>SMoPE consistently outperforms task-specific prompt methods and achieves performance competitive with state-of-the-art approaches.
  arXiv  Detail & Related papers  (2025-09-29T08:54:58Z)
• EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation [8.757777529568383]
  Current RAG systems often struggle when retrieval models fail to rank the most relevant documents.<n>We introduce EXIT, an extractive context compression framework.<n>Our evaluations show that EXIT consistently surpasses existing compression methods.
  arXiv  Detail & Related papers  (2024-12-17T05:38:27Z)
• Once-for-All Sequence Compression for Self-Supervised Speech Models [62.60723685118747]
  We introduce a once-for-all sequence compression framework for self-supervised speech models. The framework is evaluated on various tasks, showing marginal degradation compared to the fixed compressing rate variants. We also explore adaptive compressing rate learning, demonstrating the ability to select task-specific preferred frame periods without needing a grid search.
  arXiv  Detail & Related papers  (2022-11-04T09:19:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.