SkillZip Pro: Execution-Aware Dynamic Compression of Progressively Loaded Skills for Self-Evolving Agents

• URL: http://arxiv.org/abs/2608.30785v1
• Date: Mon, 31 Aug 2026 13:41:16 GMT
• Title: SkillZip Pro: Execution-Aware Dynamic Compression of Progressively Loaded Skills for Self-Evolving Agents
• Abstract summary: Method is an evaluation-free compressor for complete, progressively loaded skill bundles.<n>Method compresses emphacross files, removing content from a reference or subskill when the root or a declared environment contract already provides it.<n>It preserves routing, so every required file and directly callable entry remains reachable after rewriting.
• Score: 48.36946103539268
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Production agent skills are directory bundles, not isolated prompts. The root is loaded at activation; references, schemas, scripts, assets, and nested subskills are loaded only when an execution path needs them. Compressing only the root misses most deployment cost and may move branch-specific details into the always-loaded context. Flattening instead destroys progressive-loading boundaries. We introduce \method, an evaluation-free compressor for complete, progressively loaded skill bundles. It leaves the agent harness unchanged and emits an ordinary directory. The method combines two safeguards. First, it compresses \emph{across files}, removing content from a reference or subskill when the root or a declared environment contract already provides it. Second, it preserves routing, so every required file and directly callable entry remains reachable after rewriting. Users can configure \method along two independent axes. \emph{One-Shot} mode rebuilds the full bundle; \emph{Continual} mode reuses state and applies Zip-on-Write after each evolution patch. \emph{Persistent} compression rewrites the shipped bundle to reduce storage and runtime context. \emph{Transient} compression keeps that bundle byte-identical and builds a task-specific view, reducing only per-run context after build cost. Entry contracts mark private, public, and conditional resources; a multi-entry audit preserves standalone public subskills. On a production content-moderation skill evaluated by our industrial multi-round harness, \method removes \hl{38\%} of skill bundle tokens and \hl{10.4\%} of end-to-end per-run tokens with no quality loss, while an unprotected 71\% configuration loses up to 26 accuracy points to one-sided false positives. On a multi-entry bundle, \method effeciently reduces token cost while near-perfectly preserving every route and public entry.

Related papers

• TRACE: Trajectory-robust Admission with Evidence Ordering for Efficient GUI Agents [54.88208747581851]
  Training-free visual token pruning can reduce this cost, but cache reuse introduces a fundamental constraint.<n>We propose textbfmethod, a training-free framework for emphtextbfTrajectory-textbfrobust textbfAdmission and textbfCoverage-aware textbfEvidence ordering.
  arXiv  Detail & Related papers  (2026-09-09T15:12:48Z)
• SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure [13.304443478478134]
  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.
  arXiv  Detail & Related papers  (2026-08-11T15:41:19Z)
• 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)
• ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation [72.54604107217669]
  textscpass@$k$ nearly vanishes after compression, yet textscpass@$k$ recovers substantially under repeated sampling.<n>Recovery should train on the compressed model's own on-policy states with dense token-level supervision.<n>We propose textbfshortopd, a short-to-long OPD schedule that detects teacher-confirmed repetitive suffixes.
  arXiv  Detail & Related papers  (2026-07-14T17:50:50Z)
• Taming the Drift: Context-aware Repair of Dockerfile Drift during Software Evolution [52.50730821321986]
  Cadre is a context-aware framework for automated Dockerfile drift repair.<n>CDG maps each Dockerfile instruction to its file-level and inter-instruction dependencies.<n>DodeX mines real-world Dockerfile drift instances from GitHub Actions CI logs.
  arXiv  Detail & Related papers  (2026-07-14T09:12:26Z)
• OxyMake: A Formally-Specified, Content-Addressable Workflow Engine [0.0]
  Rust engine replaces the proxy with a content-addressed cache key.<n>The spec stays declarative and statically parseable, keeping the Make rule model so Snakemake pipelines port directly.<n>Execution is daemon-free via a cooperative claim/reclaim protocol.
  arXiv  Detail & Related papers  (2026-06-18T23:45:52Z)
• SoftSkill: Behavioral Compression for Contextual Adaptation [45.10778084241114]
  This paper asks whether a natural-language skill can instead initialize a compact continuous context object.<n>We propose SoftSkill, a frozen-backbone method that tunes such soft skills with next-token prediction.<n>Relative to Skill, SoftSkill improves accuracy by 5.2 points on SearchQA and 12.5 points on LiveMath.
  arXiv  Detail & Related papers  (2026-06-18T15:04:47Z)
• Enhancing Software Engineering Through Closed-Loop Memory Optimization [50.418699819003486]
  We introduce ours, a closed-loop framework for memory augmentation in software engineering (SE) agents.<n>ours grounds memory utility in textitvalidated downstream impact, establishing utility as a task-agnostic textbf benchmark and an annotation-free textbfoptimization signal.<n>Results demonstrate that ours consistently improves SE agents across settings, achieving absolute gains of up to $uparrow5.25%$ in success rate and $uparrow4.63%$ in resolve efficiency.
  arXiv  Detail & Related papers  (2026-06-04T03:17:21Z)
• Leyline: KV Cache Directives for Agentic Inference [0.11099872871193028]
  Leyline is a serving-side primitive for agentic editing.<n>A declarative directive 4-tuple separates what to edit from how to preserve position correctness.<n>A ten-line truncation rule routed through the same interface lifts agentic solve rate by +14.3 pp on debug-gym.
  arXiv  Detail & Related papers  (2026-05-31T07:13:15Z)
• When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning [60.714416943748866]
  In single-stream autoregressive interfaces, the same tokens both update the model state and constitute an irreversible public commitment.<n>We introduce Side-by-Side (SxS) Interleaved Reasoning, which makes disclosure timing a controllable decision within standard autoregressive generation.
  arXiv  Detail & Related papers  (2026-05-05T02:59:58Z)
• Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors [48.881343993730844]
  Safety-aligned large language models (LLMs) are increasingly deployed in real-world pipelines.<n> adversaries can distribute backdoored checkpoints that behave normally under standard evaluation but jailbreak when a hidden trigger is present.<n>Recent post-hoc weight-editing methods offer an efficient approach to injecting such backdoors.
  arXiv  Detail & Related papers  (2026-04-14T06:48:33Z)

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.