SkillWeaver formalizes compositional skill routing for LLM agents and introduces SAD, which raises step-level decomposition accuracy from 51% to 67.7% on a new 300-query benchmark over 2209 real MCP skills.
name" - concise snake_case identifier -
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 9roles
background 1polarities
background 1representative citing papers
A linear edge probe on Qwen3-32B residual streams decodes tool-call dependency graphs in agent trajectories above random and positional baselines, with evidence the signal tracks abstract topology.
ReGRPO augments group-relative policy optimization with a reflective data engine that generates ErrorType-Evidence-FixPlan triplets from near-miss tool actions to improve recovery in multimodal agents.
Empirical analysis across 15 LLMs and 1,141 skills identifies a logarithmic routing decay law and a multiplicative execution law coupled by a single fitted slope parameter b that enables targeted library optimizations improving routing accuracy and downstream task pass rates.
ToolMATH converts MATH solutions into controlled tool environments with gold tools and graded distractors to diagnose LLM adaptability, robustness, and long-horizon tool connectivity.
A framework automates multi-agent system creation via LLM planning and two-stage agent recommendation, claiming higher recall than prior methods.
Exploratory human evaluation of skill-augmented AI agents versus native models on an NSCLC transcriptomic task found directional but non-significant quality gains overshadowed by rater noise.
A survey that defines agent skills as reusable procedural artifacts and reviews methods, resources, and applications across their representation, acquisition, retrieval, and evolution stages.
citing papers explorer
-
Compositional Skill Routing for LLM Agents: Decompose, Retrieve, and Compose
SkillWeaver formalizes compositional skill routing for LLM agents and introduces SAD, which raises step-level decomposition accuracy from 51% to 67.7% on a new 300-query benchmark over 2209 real MCP skills.
-
Tool-Call Dependency Structure is Linearly Decodable in LLM Agent Residual Streams
A linear edge probe on Qwen3-32B residual streams decodes tool-call dependency graphs in agent trajectories above random and positional baselines, with evidence the signal tracks abstract topology.
-
ReGRPO: Reflection-Augmented Policy Optimization for Tool-Using Agents
ReGRPO augments group-relative policy optimization with a reflective data engine that generates ErrorType-Evidence-FixPlan triplets from near-miss tool actions to improve recovery in multimodal agents.
-
The Scaling Laws of Skills in LLM Agent Systems
Empirical analysis across 15 LLMs and 1,141 skills identifies a logarithmic routing decay law and a multiplicative execution law coupled by a single fitted slope parameter b that enables targeted library optimizations improving routing accuracy and downstream task pass rates.
-
ToolMATH: A Diagnostic Benchmark for Long-Horizon Tool Use under Systematic Tool-Catalog Constraints
ToolMATH converts MATH solutions into controlled tool environments with gold tools and graded distractors to diagnose LLM adaptability, robustness, and long-horizon tool connectivity.
-
From Intent to Execution: Composing Agentic Workflows with Agent Recommendation
A framework automates multi-agent system creation via LLM planning and two-stage agent recommendation, claiming higher recall than prior methods.
-
Skill-Augmented AI Agents for Medical Research Analysis: An Exploratory Multi-Model Human Evaluation in an NSCLC Transcriptomic Biomarker Task
Exploratory human evaluation of skill-augmented AI agents versus native models on an NSCLC transcriptomic task found directional but non-significant quality gains overshadowed by rater noise.
-
A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications
A survey that defines agent skills as reusable procedural artifacts and reviews methods, resources, and applications across their representation, acquisition, retrieval, and evolution stages.
- ArtifactLinker: Linking Scientific Artifacts for Automatic State-of-the-Art Discovery