SkillDAG builds a self-evolving typed skill graph that LLM agents query and update at inference time, raising success on ALFWorld and SkillsBench by 12.8 and 8.6 points over graph baselines.
hub Canonical reference
Available: https://arxiv.org/abs/2603.04448
Canonical reference. 89% of citing Pith papers cite this work as background.
28
Pith papers citing it
Background
89% of classified citations
hub tools
citation-role summary
background 8
method 1
citation-polarity summary
years
2026 28representative citing papers
SelSkill applies dual-granularity preference learning to selective skill-or-skip decisions, improving task success by 10.9 points and execution precision by 29.1 points on ALFWorld with Qwen3-8B.
RS-Claw enables remote sensing agents to actively explore tools via hierarchical skill trees, achieving up to 86% token compression and outperforming flat registration and RAG baselines on Earth-Bench.
DataPRM is an environment-aware generative process reward model that improves LLM data analysis agents by 7-11% on benchmarks via active verification and reflection-aware ternary rewards.
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.
LLM-native figures embed provenance and enable direct LLM interaction with scientific visualizations to accelerate discovery and improve reproducibility.
SkillAxe is an unsupervised framework that decomposes LLM skill quality into four dimensions to generate improvement briefs, raising pass rates 28% relative on SkillsBench and from 16% to 52% on SpreadsheetBench.
SkillPyramid introduces a hierarchical skill consolidation framework with self-evolution, reporting 38% higher average reward and 27.7% fewer execution steps on ALFWorld, WebShop, and ScienceWorld across four models.
SkillAdaptor introduces step-level failure attribution and targeted skill updates for LLM agents, yielding performance gains on WebShop, PinchBench, and Claw-Eval benchmarks.
Catalogs ten patterns and synthesizes a four-layer reference architecture for skill harnessing in LLM agents, evaluated via cross-instantiation on eight systems.
SynLearner lets LLMs improve synthetic data generation on later tasks in a stream by learning reusable patterns and balancing quality with diversity from feedback on earlier tasks.
SPARK generates environment-verified trajectories to compute PDI, enabling posterior skill distillation that outperforms no-skill baselines and human-written skills across 86 tasks with up to 1000x cheaper inference.
GoSkills converts flat skill lists into role-labeled execution contexts via anchor-centered groups and graph expansion, preserving coverage and improving rewards on SkillsBench and ALFWorld under small skill budgets.
Ctx2Skill uses a self-evolving multi-agent loop with Challenger, Reasoner, Judge, and Cross-time Replay to discover context-specific skills, improving task-solving rates on CL-bench benchmarks across models.
SkillSynth uses a scenario-mediated skill graph to sample workflow paths and generate executable terminal tasks, enabling controlled diversity in training trajectories for agents.
SSL representation disentangles skill scheduling, structure, and logic using an LLM normalizer, improving skill discovery MRR@50 from 0.649 to 0.729 and risk assessment macro F1 from 0.409 to 0.509 over text baselines.
MedSkillAudit is a new domain-specific audit framework for medical research agent skills that achieved moderate agreement with expert reviews (ICC 0.449), exceeding the human inter-rater baseline (ICC 0.300).
Agent-World autonomously synthesizes verifiable real-world tasks and uses continuous self-evolution to train 8B and 14B agents that outperform proprietary models on 23 benchmarks.
SkillGraph jointly evolves agent skills and collaboration topologies in multi-agent vision-language systems using a multimodal graph transformer and a skill designer, yielding consistent performance gains on benchmarks.
Pomona automates discovery and repair of small code quality issues via agent skills, achieving 15 of 17 PRs merged with median close time under 2 hours in a one-month Bloomberg team deployment.
OpenSkill bootstraps LLM agent self-evolution by pulling grounded knowledge and anchors from open-world sources, synthesizing transferable skills, and refining them on self-generated virtual tasks, achieving top benchmark pass rates without supervision.
DataCOPE uses verifier-guided contrastive distillation from agent trajectories to discover skills, yielding average gains of 9.71% on report-style and 32.30% on reasoning-style data analysis tasks across four model settings.
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.
SkillsVote is a governance system for agent skills that profiles corpora, recommends via search, and gates updates on successful reusable outcomes, yielding benchmark gains without model changes.
citing papers explorer
-
Figures as Interfaces: Toward LLM-Native Artifacts for Scientific Discovery
LLM-native figures embed provenance and enable direct LLM interaction with scientific visualizations to accelerate discovery and improve reproducibility.