SkillEvolBench is a new diagnostic benchmark that evaluates the transition from episodic experience to procedural skills in LLM agents using role-conditioned task families and frozen deployment tests.
hub Mixed citations
Swe-skills-bench: Do agent skills actually help in real-world software engineering?
Mixed citation behavior. Most common role is background (60%).
15
Pith papers citing it
Background
60% of classified citations
hub tools
citation-role summary
background 3
dataset 1
method 1
citation-polarity summary
years
2026 15representative citing papers
Counterfactual Trace Auditing detects 522 behavioral change patterns from skills on 49 tasks where pass rates shift only 0.3 points on average.
SkillGuard extracts executable environment contracts from LLM skill documents to detect only relevant drifts, reporting zero false positives on 599 cases, 100% precision in known-drift tests, and raising one-round repair success from 10% to 78%.
SkillRet benchmark shows fine-tuned retrievers improve NDCG@10 by 13+ points over prior models on large-scale skill retrieval for LLM agents.
SkillFlow benchmark shows lifelong skill evolution yields modest gains for some models like Claude Opus 4.6 but limited or negative utility for others despite high skill usage.
SkillMOO applies LLM-proposed edits and NSGA-II Pareto optimization to skill bundles for SE agents, ranking top in pass rate on most SkillsBench tasks while cutting costs up to 31.7%.
SkVM uses capability profiling and compiler-style techniques to make skills portable across LLMs and harnesses, raising task completion rates while cutting token use by up to 40% and delivering up to 3.2x speedup.
SkillGuard presents a dual-plane permission framework for agent skills that achieves 99.76% taxonomy coverage and reduces attack success rates in evaluations on 315 skills.
SkillRevise iteratively refines initial LLM-generated agent skills using execution traces to diagnose defects and apply repairs, raising success rates from 36.05% to 61.63% on SkillsBench across three benchmarks and five LLMs.
RAMP evaluates 15 models on production-like serial workflows and reports completion rates collapsing from 100% to 20% with none finishing the full pipeline and costs varying by three orders of magnitude.
A systematic study across five domains finds model-generated skills yield average gains but non-uniform negative transfer, with a meta-skill improving extraction quality.
SWE-Bench 5G is the first benchmark for AI agents fixing bugs in 5G core network software, showing high diagnosis rates but low resolution that improves conditionally with specification context.
Survey of auto-research systems identifies objective, validation, and acceptance collapses, concluding that workflow closure does not equal scientific closure and advocating non-autonomous epistemic control.
NAUTILUS is a prompt-driven harness that automates plug-and-play adapters, typed contracts, and validation for policies, benchmarks, and robots in learning research.
Agentic Agile-V uses Agile-V as backbone and a Specify-Constrain-Orchestrate-Prove-Evolve-Verify loop to convert AI agent conversations into traceable engineering artifacts with acceptance evidence.
citing papers explorer
No citing papers match the current filters.