Skill-as-Pseudocode: Refactoring Skill Libraries to Pseudocode for LLM Agents

• URL: http://arxiv.org/abs/2605.27955v1
• Date: Wed, 27 May 2026 04:48:40 GMT
• Title: Skill-as-Pseudocode: Refactoring Skill Libraries to Pseudocode for LLM Agents
• Abstract summary: We propose Skill-as-Pseudocode (SaP), an automatic conversion of markdown skill libraries into typed pseudocode.<n>For each cluster of similar procedural passages drawn from one or more skills, SaP extracts a typed contract and filters it through a four-check deterministic verifier.<n>Promoted contracts are inlined into a rewritten skill skeleton together with restored concrete action templates, giving the agent two complementary signals.
• Score: 50.78646963535282
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Markdown skill libraries for LLM agents ship as free-form prose, forcing the agent to re-derive both the input schema and the concrete invocation syntax on every retrieval. We observe that this often produces a "confused -> re-retrieve -> still confused" loop in which the agent issues a partially-correct action, receives uninformative environment feedback, and re-retrieves the same prose. We propose Skill-as-Pseudocode (SaP), an automatic conversion of markdown skill libraries into typed pseudocode with deterministic quality control. For each cluster of similar procedural passages drawn from one or more skills, SaP extracts a typed contract and filters it through a four-check deterministic verifier (coverage, binding, replacement, risk). Promoted contracts are inlined into a rewritten skill skeleton together with restored concrete action templates, giving the agent two complementary signals: a typed signature for what the skill does and a concrete template for how to invoke it. On the 134-game ALFWorld unseen split with gpt-4o-mini, pooled across three seeds, SaP wins 82/402 paired games versus 47/402 for the Graph-of-Skills (GoS) baseline (pooled McNemar p = 8.2e-5), at -22.8 +/- 6.4% input tokens and -14.5 +/- 4.1% LLM calls per game.

Related papers

• The Router Within: Eliciting Native Skill Routing from a Frozen LLM [36.31894794808421]
  Skills extend an agent's parametric knowledge, and the gain they promise rests on picking the right one.<n>We show that the frozen agent LLM already carries the routing signal in its own forward passes.<n>A glance projects the task's and each skill's mid-layer states through the two maps, the only parameters trained.<n>A verdict then resumes the shortlisted skills' forward passes and reads the model's own likelihood and yes/no judgment.
  arXiv  Detail & Related papers  (2026-09-14T17:58:27Z)
• Codebook Agent: Amortized Topology Design for LLM Multi-Agent Systems [67.04448659688579]
  We develop a query-independent 16-entry codebook that ranks the top decoded candidates in a single batched forward pass.<n>With no iterative search and no message passing at test time, Codebook Agent is the most accurate method on all six benchmarks.
  arXiv  Detail & Related papers  (2026-09-02T08:10:22Z)
• LMSM: LLM Security Framework Inspired by Linux Security Modules [56.93644694627783]
  Large language models (LLMs) are increasingly deployed with layered defenses, yet malicious prompts can still bypass them.<n>We present Language Model Security Modules (LMSM), a security framework that adapts the separation behind Linux Security Modules (LSM) to LLM serving.
  arXiv  Detail & Related papers  (2026-08-26T12:13:05Z)
• SkillConsist: Detecting Inconsistencies in Agent Skills via Bidirectional Graph Alignment [8.140228855572433]
  Agent Skill inconsistencies expose undisclosed dangerous behavior or cause wrong Skill selection.<n>Recent Agent Skill research has increasingly examined Agent SkillConsist consistency detection.<n>We present SkillConsist to address both challenges.
  arXiv  Detail & Related papers  (2026-08-07T16:04:21Z)
• Preventing Premature Commitment in Coding Agents with an Evidence-Conditioned Execution Layer [38.62073085926841]
  LLM-based coding agents edit source code or submit patches before examining enough repository evidence to justify the change.<n>We present ECLoop, an execution layer that interposes between the agent and the repository to enforce evidence-conditioned execution.
  arXiv  Detail & Related papers  (2026-07-30T20:16:35Z)
• Generative Skill Composition for LLM Agents [58.47191648555256]
  LLM agents benefit from skills for solving complex tasks.<n>As skill libraries grow, selecting an appropriate skill composition has emerged as a central bottleneck.<n>We propose SkillComposer, which instantiates structured skill composition as task-conditioned skill sequence prediction.
  arXiv  Detail & Related papers  (2026-06-30T17:53:09Z)
• From Attack Simulation to SIEM Rule: Deterministic Detection-as-Code Synthesis with Probe-Level Traceability [51.56484100374058]
  Security teams simulate attacks against their own systems to check whether their monitoring would catch a real intruder.<n>A human bridges that gap by hand, reading each finding and writing the corresponding Sigma rule.<n>We show this translation can be partially automated when probes are drawn from a locked corpus.
  arXiv  Detail & Related papers  (2026-06-03T14:26:25Z)
• SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale [54.70985426016736]
  We present SkillDAG, which models inter-skill relationships as a typed directed graph.<n>Each search returns vector matches, typed-edge neighbors, and conflict signals, and a propose-then-commit protocol lets the agent register execution-backed edges.<n>On ALFWorld and SkillsBench with MiniMax-M2.7, SkillDAG reaches 67.1% success and 27.3% reward.
  arXiv  Detail & Related papers  (2026-06-02T02:45:21Z)
• Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces [3.651838585096184]
  Large language model (LLM) agents evolve from isolated tool users into coordinated teams.<n> reinforcement learning must optimize not only individual actions but also how work is spawned, delegated, communicated, aggregated, and stopped.<n>This paper studies reinforcement learning for multi-agent systems through orchestration traces.
  arXiv  Detail & Related papers  (2026-05-04T16:42:18Z)
• Semia: Auditing Agent Skills via Constraint-Guided Representation Synthesis [11.214847720120192]
  We present Semia, a static auditor for agent skills.<n>Semia lifts each skill into the Skill Description Language (SDL), a Datalog fact base.<n>We evaluate Semia on 13,728 real-world skills from public marketplaces.
  arXiv  Detail & Related papers  (2026-05-01T00:48:47Z)
• Resilient Write: A Six-Layer Durable Write Surface for LLM Coding Agents [0.0]
  Resilient Write is an MCP server that interposes a six-layer durable write surface between the agent and the server.<n>Each layer maps to a concrete failure mode observed during a real agent session in April 2026.<n>A 186-test suite validates correctness at each layer, and a 13x improvement in agent self-correction rate.
  arXiv  Detail & Related papers  (2026-04-12T22:23:55Z)
• SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills [0.0]
  SkillSieve is a three-layer detection framework that applies progressively deeper analysis only where needed.<n>On a 400-skill labeled benchmark, SkillSieve achieves 0.800 F1, outperforming ClawVet's 0.421, at an average cost of 0.006 per skill.
  arXiv  Detail & Related papers  (2026-04-08T00:58:48Z)
• APEX-EM: Non-Parametric Online Learning for Autonomous Agents via Structured Procedural-Episodic Experience Replay [7.370176470430802]
  LLM-based autonomous agents lack persistent procedural memory.<n>We present APEX-EM, a non-parametric online learning framework that accumulates, retrieves, and reuses structured procedural plans.
  arXiv  Detail & Related papers  (2026-03-31T00:24:56Z)
• TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework [62.66056331998838]
  TeaRAG is a token-efficient agentic RAG framework capable of compressing both retrieval content and reasoning steps.<n>Our reward function evaluates the knowledge sufficiency by a knowledge matching mechanism, while penalizing excessive reasoning steps.
  arXiv  Detail & Related papers  (2025-11-07T16:08:34Z)
• ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code [76.84199699772903]
  ML-Bench is a benchmark rooted in real-world programming applications that leverage existing code repositories to perform tasks. To evaluate both Large Language Models (LLMs) and AI agents, two setups are employed: ML-LLM-Bench for assessing LLMs' text-to-code conversion within a predefined deployment environment, and ML-Agent-Bench for testing autonomous agents in an end-to-end task execution within a Linux sandbox environment.
  arXiv  Detail & Related papers  (2023-11-16T12:03:21Z)
• Contrastive Code Representation Learning [95.86686147053958]
  We show that the popular reconstruction-based BERT model is sensitive to source code edits, even when the edits preserve semantics. We propose ContraCode: a contrastive pre-training task that learns code functionality, not form.
  arXiv  Detail & Related papers  (2020-07-09T17:59:06Z)

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.