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%.
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%).
12
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 12representative citing papers
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.
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.
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
-
Skill Drift Is Contract Violation: Proactive Maintenance for LLM Agent Skill Libraries
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: A Large-Scale Benchmark for Skill Retrieval in LLM Agents
SkillRet benchmark shows fine-tuned retrievers improve NDCG@10 by 13+ points over prior models on large-scale skill retrieval for LLM agents.
-
SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous 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: Multi-Objective Optimization of Agent Skills for Software Engineering
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: Revisiting Language VM for Skills across Heterogenous LLMs and Harnesses
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.
-
SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision
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.
-
Benchmarks are Not Enough: RAMP for Runtime Assessing of Agentic Models in Production Systems
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.
-
From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills
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: Benchmarking AI Coding Agents on Telecom Network Engineering Tasks
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.
-
Nautilus: From One Prompt to Plug-and-Play Robot Learning
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: From Vibe Coding to Verified Engineering in Software and Hardware Development
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.
- Counterfactual Trace Auditing of LLM Agent Skills