SkillProx: Self-Evolving Agent Skills via Proximal Textual Gradient Descent

• URL: http://arxiv.org/abs/2608.07449v1
• Date: Fri, 07 Aug 2026 17:40:33 GMT
• Title: SkillProx: Self-Evolving Agent Skills via Proximal Textual Gradient Descent
• Abstract summary: LLM agents increasingly adapt to recurring tasks by accumulating procedural knowledge in skills.<n>Recent methods refine skills through iterative task execution, failure diagnosis, and trajectory-guided text-space updates.<n>We introduce SkillProx, a proximal-gradient-inspired forward--backward framework that couples closed-loop diagnostic evolution with utility-aware proximal refinement.
• Score: 27.354076514186094
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LLM agents increasingly adapt to recurring tasks by accumulating procedural knowledge in skills. These skills are lightweight, reusable textual artifacts that are loaded into the agent's context without weight updates. Recent methods refine skills through iterative task execution, failure diagnosis, and trajectory-guided text-space updates. However, existing frameworks lack explicit diagnosis--outcome feedback and treat deletion as a generic edit operation rather than a dedicated mechanism for consolidating accumulated knowledge. We introduce SkillProx, a proximal-gradient-inspired forward--backward framework that couples closed-loop diagnostic evolution with utility-aware proximal refinement. Motivated by a composite objective balancing task loss and skill complexity, the forward stage re-executes diagnosis-driven edits on the same task batch, rolls back regressions, and feeds measured outcomes into subsequent diagnoses. The backward stage decomposes the resulting skill into auditable knowledge units, estimates their contributions using a frozen leave-one-out utility audit, and applies validation-gated consolidation, demotion, or removal. Experiments on in-distribution and out-of-distribution benchmarks across multiple backbone LLMs show that SkillProx improves average accuracy by 3.0 percentage points over the strongest gradient-based baseline. Component ablations demonstrate the complementary effects of closed-loop diagnosis and proximal refinement.

Related papers

• Demystifying Agent Skills: Why They Work-Until They Don't [58.92875630998418]
  Existing evaluations largely measure whether skills improve aggregated task success, leaving a more fundamental question underexplored: emphtextbfWhen do skills help, why do they work, and where do they fail?<n>We isolate the effects of representation, outcome annotation, retrieval difficulty, and cross-framework of skills.<n>We consolidate these observations into a taxonomy of three high-level categories and twelve skill-use modes.
  arXiv  Detail & Related papers  (2026-08-14T07:26:38Z)
• Rethinking Self-Evolution: A Constrained Exploration-Exploitation Process for Mitigating Skill Overfitting [20.811638832981178]
  Large language model (LLM) agents need to accumulate and reuse experience from past interactions.<n>Data-driven skill optimization is prone to overfitting to the limited trajectories collected from real environments.<n>We propose SkillBoost, a three-stage framework that mitigates both risks.
  arXiv  Detail & Related papers  (2026-07-29T09:05:40Z)
• Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills [53.15216425100295]
  We introduce Skill Self-Play (Skill-SP), a co-evolutionary framework comprising a proposer, a solver, and a skill controller.<n>The proposer generates challenging tasks conditioned on dynamically sampled skills; the solver explores candidate solutions to push its capability boundaries; and the skill controller collects execution feedback to update and expand the skill library.<n>This interactive co-evolution effectively bridges the gap between structured verification and open-ended exploration.
  arXiv  Detail & Related papers  (2026-07-24T17:59:22Z)
• SkillAudit: Ground-Truth-Free Skill Evolution via Paired Trajectory Auditing [81.51044612408793]
  SkillAudit is a framework for evolving agent skills without ground-truth feedback.<n>To turn behavioral differences into edit guidance, SkillAudit uses Process-Aligned Contrastive Evaluation.<n>It routes edits through two pipelines: Refine removes noisy or irrelevant guidance from broadly useful skills, while Repair replaces passages that conflict with the task.
  arXiv  Detail & Related papers  (2026-06-12T08:20:09Z)
• SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision [41.562357872885826]
  We propose SkillRevise, an execution-grounded framework designed to iteratively refine agent skills.<n>SkillRevise diagnoses skill defects from execution evidence, retrieves relevant repair principles from a general memory, and applies execution-anchored edits.<n>It substantially outperforms one-shot baselines, improving the base agent's success rate on SkillsBench from 36.05% to 61.63%.
  arXiv  Detail & Related papers  (2026-05-31T10:19:13Z)
• SkillGrad: Optimizing Agent Skills Like Gradient Descent [30.781132643932338]
  Agent skills provide a lightweight way to adapt LLM agents to specialized domains by storing reusable procedural knowledge in structured files.<n>Existing skill-evolution methods often address these deficiencies through reflections without an explicit formulation.<n>We propose SkillGrad, a gradient-descent-inspired framework for optimizing agent skills.
  arXiv  Detail & Related papers  (2026-05-26T23:18:43Z)
• SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills [31.23929961213889]
  Large language model (LLM) agents accumulate rich episodic trajectories while solving real-world tasks.<n>We introduce SkillEvolBench, a diagnostic benchmark for evaluating this step from experience reuse to skill formation.<n>We find that current agents often adapt locally but rarely form robust reusable skills.
  arXiv  Detail & Related papers  (2026-05-22T18:23:31Z)
• Harnessing LLM Agents with Skill Programs [58.356514745548026]
  We introduce HASP, a new framework that upgrades skills into executable Program Functions (PFs)<n>PFs act as executable guardrails that activate on failure-prone states and modify the next action or inject corrective context.<n> HASP drives substantial gains compared to both training-free and training-based methods on web-search, math reasoning, and coding tasks.
  arXiv  Detail & Related papers  (2026-05-18T01:35:11Z)
• DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning [60.35032268606525]
  Agent-compiled knowledge bases provide persistent external knowledge for large language model (LLM) agents in downstream tasks.<n>Yet their quality is systematically limited by emphincompleteness, emphincorrectness, and emphredundancy
  arXiv  Detail & Related papers  (2026-05-11T12:48:31Z)
• SkillGen: Verified Inference-Time Agent Skill Synthesis [60.927977774369516]
  SkillGen is a framework that synthesizes a single auditable skill from trajectories generated by a base agent.<n>It identifies reusable success patterns, recurring failure modes, and behaviors that appear in nearby successes but are missing from failures.<n>A key novelty in SkillGen is that we model agent skills as interventions to empirically verify the net effect of skills on the overall performance.
  arXiv  Detail & Related papers  (2026-05-09T19:24:11Z)
• Diagnostics of cognitive failures in multi-agent expert systems using dynamic evaluation protocols and subsequent mutation of the processing context [0.0]
  This work introduces a diagnostic framework for expert systems that not only evaluates but also facilitates the transfer of expert behaviour into LLM-powered agents.<n>We demonstrate the framework on a multi-agent recruiter-assistant system, showing that it uncovers latent cognitive failures.
  arXiv  Detail & Related papers  (2025-09-18T19:08:03Z)
• Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification [52.095460362197336]
  Large language models (LLMs) struggle with consistent and accurate reasoning. LLMs are trained primarily on correct solutions, reducing their ability to detect and learn from errors. We propose a novel collaborative method integrating Chain-of-Thought (CoT) and Program-of-Thought (PoT) solutions for verification.
  arXiv  Detail & Related papers  (2024-10-05T05:21:48Z)

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.