{"total":28,"items":[{"citing_arxiv_id":"2606.10546","ref_index":16,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SkillAxe: Sharpening LLM-Authored Agent Skills Through Evaluation-Guided Self-Refinement","primary_cat":"cs.MA","submitted_at":"2026-06-09T08:14:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.06752","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Pomona: Continuous Code Quality Improvement via Small, Automated Changes at Bloomberg","primary_cat":"cs.SE","submitted_at":"2026-06-04T22:31:48+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.06741","ref_index":43,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"OpenSkill: Open-World Self-Evolution for LLM Agents","primary_cat":"cs.AI","submitted_at":"2026-06-04T21:55:48+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.06416","ref_index":63,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Unsupervised Skill Discovery for Agentic Data Analysis","primary_cat":"cs.AI","submitted_at":"2026-06-04T17:20:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.03692","ref_index":1,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SkillPyramid: A Hierarchical Skill Consolidation Framework for Self-Evolving Agents","primary_cat":"cs.AI","submitted_at":"2026-06-02T14:14:27+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.03056","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale","primary_cat":"cs.AI","submitted_at":"2026-06-02T02:45:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.01311","ref_index":22,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories","primary_cat":"cs.CL","submitted_at":"2026-05-31T16:00:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SkillAdaptor introduces step-level failure attribution and targeted skill updates for LLM agents, yielding performance gains on WebShop, PinchBench, and Claw-Eval benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.01185","ref_index":21,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"\"Skill issues'': data-centric optimization of lakehouse agents","primary_cat":"cs.AI","submitted_at":"2026-05-31T11:58:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Data-centric optimization of skills for agents on a branching lakehouse improves accuracy by 31.9% on 25 tasks via state-verification evaluation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.00510","ref_index":33,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Skill or Skip? Learning Selective Skill Invocation in Agentic Tasks via Dual-Granularity Preference Learning","primary_cat":"cs.CL","submitted_at":"2026-05-30T04:00:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.20631","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Harnessing Agent Skills: Architectural Patterns and a Reference Architecture for Skill-Mediated LLM Agents","primary_cat":"cs.AI","submitted_at":"2026-05-29T02:12:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Catalogs ten patterns and synthesizes a four-layer reference architecture for skill harnessing in LLM agents, evaluated via cross-instantiation on eight systems.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.29940","ref_index":14,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Make LLM Learn to Synthesize from Streaming Experiences through Feedback","primary_cat":"cs.AI","submitted_at":"2026-05-28T13:51:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.26200","ref_index":67,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Workflow Closure Is Not Scientific Closure in Auto-Research Systems","primary_cat":"cs.SE","submitted_at":"2026-05-25T17:16:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18401","ref_index":26,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution","primary_cat":"cs.CL","submitted_at":"2026-05-18T13:44:19+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"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.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Beyond semantic similarity: Rethinking retrieval for agentic search via direct corpus interaction. arXiv preprint arXiv:2605.05242, 2026. [25] Jiaqing Liang, Jinyi Han, Weijia Li, Xinyi Wang, Zhoujia Zhang, Zishang Jiang, Ying Liao, Tingyun Li, Ying Huang, Hao Shen, et al. Genericagent: A token-efficient self-evolving llm agent via contextual information density maximization (v1. 0).arXiv preprint arXiv:2604.17091, 2026. [26] Yuan Liang, Ruobin Zhong, Haoming Xu, Chen Jiang, Yi Zhong, Runnan Fang, Jia-Chen Gu, Shumin Deng, Yunzhi Yao, Mengru Wang, et al. Skillnet: Create, evaluate, and connect ai skills.arXiv preprintarXiv:2603.04448, 2026. [27] Jiahang Lin, Shichun Liu, Chengjun Pan, Lizhi Lin, Shihan Dou, Xuanjing Huang, Hang Yan, Zhenhua Han, and Tao Gui. Agentic harness engineering: Observability-driven automatic evolution of coding-agent harnesses."},{"citing_arxiv_id":"2605.13391","ref_index":43,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"RS-Claw: Progressive Active Tool Exploration via Hierarchical Skill Trees for Remote Sensing Agents","primary_cat":"cs.AI","submitted_at":"2026-05-13T11:49:18+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09192","ref_index":6,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Evidence Over Plans: Online Trajectory Verification for Skill Distillation","primary_cat":"cs.AI","submitted_at":"2026-05-09T22:15:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"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.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"human-written skills can remarkably boost task success rates, making such reusable procedural knowledge a promising abstraction for building scalable agent systems. Yet a pessimistic picture appears that the quality of these skills is nearly impossible to assess without environment-grounded verification [5]. Researchers propose lifelong skill accumulation [21], large- scale skill cataloging [6], or RL-based skill evolution [19]. These studies lack trajectory verification and solely rely on preference logs. As a result, they can not produce transferable skills between teacher and student models at different capabilities. This raises a fundamental question: What makes skill distillation transferable across tasks and models efficiently and reliably?"},{"citing_arxiv_id":"2605.07358","ref_index":66,"ref_count":6,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","primary_cat":"cs.IR","submitted_at":"2026-05-08T07:10:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"A survey that defines agent skills as reusable procedural artifacts and reviews methods, resources, and applications across their representation, acquisition, retrieval, and evolution stages.","context_count":2,"top_context_role":"background","top_context_polarity":"background","context_text":"Hybrid-BasedJARVIS-1 [55], Synapse [56], SkillWeaver [57], AgentSkillOS [58], TPTU [59], talker-reasoner [60], DAMCS [61], GraphSkill [62], Alita [63] Skill Acquisition (§IV) Human-DerivedSkillNet [64], AgentSkillOS [58], Agentic Skills [65], SkillOS [66], Agent Hospital [67] Experience-Derived V oyager [12], SkillCraft [44], Reflexion [19], ExpeL [23], BoT [24], Trace2Skill [27], EverMemOS [68], HyperMem [69], AWM [26], Synapse [56], PolySkill [45], GITM [31], Retroformer [33], MemGPT [34], Eureka [48], TiM [35], M+ [39], Learned Memory Bank [40], G-Memory [70], Nemori [41], AgentEvolver [71], STULIFE [72], AutoRefine [73], ProcMEM [43], SkillForge [43] Task-Derived CREATOR [14], ToolMakers [13], Cradle [74], CodeAct [51], SkillWeaver [57], SayCan [28], ReAct [4], DEPS [29],"},{"citing_arxiv_id":"2605.06978","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Group of Skills: Group-Structured Skill Retrieval for Agent Skill Libraries","primary_cat":"cs.CL","submitted_at":"2026-05-07T21:51:59+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.06130","ref_index":63,"ref_count":3,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning","primary_cat":"cs.AI","submitted_at":"2026-05-07T12:33:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Skill1 trains a single RL policy to co-evolve skill selection, utilization, and distillation in language model agents from one task-outcome reward, using low-frequency trends to credit selection and high-frequency variation to credit distillation, outperforming baselines on ALFWorld and WebShop.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.27660","ref_index":22,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"From Context to Skills: Can Language Models Learn from Context Skillfully?","primary_cat":"cs.AI","submitted_at":"2026-04-30T09:53:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"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.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"Skillnet: Create, evaluate, and connect ai skills.Preprint, arXiv:2603.04448. [21] Bo Liu, Leon Guertler, Simon Yu, Zichen Liu, Penghui Qi, Daniel Balcells, Mickel Liu, Cheston Tan, Weiyan Shi, Min Lin, Wee Sun Lee, and Natasha Jaques. 2026. Spiral: Self-play on zero- sum games incentivizes reasoning via multi-agent multi-turn reinforcement learning.Preprint, arXiv:2506.24119. [22] Hongliang Lu, Yuhang Wen, Pengyu Cheng, Ruijin Ding, Jiaqi Guo, Haotian Xu, Chutian Wang, Haonan Chen, xiaoxi jiang, and guanjunjiang. 2026. Search self-play: Pushing the frontier of agent capability without supervision. InThe Fourteenth International Conference on Learning Representations. [23] Zhengxi Lu, Zhiyuan Yao, Jinyang Wu, Chengcheng Han, Qi Gu, Xunliang Cai, Weiming"},{"citing_arxiv_id":"2604.25727","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Toward Scalable Terminal Task Synthesis via Skill Graphs","primary_cat":"cs.AI","submitted_at":"2026-04-28T14:53:59+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SkillSynth uses a scenario-mediated skill graph to sample workflow paths and generate executable terminal tasks, enabling controlled diversity in training trajectories for agents.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.24198","ref_index":26,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis","primary_cat":"cs.CL","submitted_at":"2026-04-27T09:00:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"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.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Similarly, the model trained with process- supervised rewards also demonstrates an increase in pass@3, which is likely attributable to the consistently high entropy maintained throughout training. In contrast, the model trained with outcome rewards shows no growth in the pass@3 metric. 6 Related Work 6.1 Process Reward Models Process Reward Models (PRMs) [26, 77] are capable of providing granular rewards and demonstrate significant potential for applica- tions in Test Time Scaling [17, 28, 50] and Reinforcement Learning [11, 13, 31, 46, 56]. Current PRMs primarily focus on scenarios that do not require environmental interaction, such as mathematics [21, 33, 54, 74, 75, 83], code generation [23, 65, 68], tabular reason-"},{"citing_arxiv_id":"2604.24026","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills","primary_cat":"cs.CL","submitted_at":"2026-04-27T04:25:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.20441","ref_index":2,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MedSkillAudit: A Domain-Specific Audit Framework for Medical Research Agent Skills","primary_cat":"cs.AI","submitted_at":"2026-04-22T11:01:48+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"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).","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.18292","ref_index":56,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence","primary_cat":"cs.AI","submitted_at":"2026-04-20T14:01:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"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.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Simulating environments with reasoning models for agent training.arXiv preprint arXiv:2511.01824, 2025. [55] Yuetai Li, Huseyin A Inan, Xiang Yue, Wei-Ning Chen, Lukas Wutschitz, Janardhan Kulkarni, Radha Poovendran, Robert Sim, and Saravan Rajmohan. Simulating environments with reasoning models for agent training, 2025. URLhttps://arxiv.org/abs/2511.01824. [56] Yuan Liang, Ruobin Zhong, Haoming Xu, Chen Jiang, Yi Zhong, Runnan Fang, Jia-Chen Gu, Shumin Deng, Yunzhi Yao, Mengru Wang, Shuofei Qiao, Xin Xu, Tongtong Wu, Kun Wang, Yang Liu, Zhen Bi, Jungang Lou, Yuchen Eleanor Jiang, Hangcheng Zhu, Gang Yu, Haiwen Hong, Longtao Huang, Hui Xue, Chenxi Wang, Yijun Wang, Zifei Shan, Xi Chen, Zhaopeng Tu, Feiyu Xiong, Xin Xie, Peng Zhang, Zhengke Gui, Lei Liang, Jun Zhou,"},{"citing_arxiv_id":"2604.17503","ref_index":27,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SkillGraph: Self-Evolving Multi-Agent Collaboration with Multimodal Graph Topology","primary_cat":"cs.AI","submitted_at":"2026-04-19T15:46:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"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.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"evolution of agentic skills through reinforcement learning and closed-loop analy- sis [1,37,41,43,51]. Concurrently, frequent skill iteration demands auditable veri- fication to ensure lifecycle safety [17,18]. As skill banks expand, researchers have introduced ontological networks, complete routing mechanisms, and advanced compositional benchmarks [6,27,54]. Despite this rapid progress, existing frame- works still treat the skill bank and the collaboration structure of multi-agent systems as largely decoupled. Skills are updated in response to task outcomes, but no signal is propagated to restructure how agents collaborate, and visual fea- tures play no role in skill retrieval or evolution. SkillGraph addresses both gaps"},{"citing_arxiv_id":"2604.17308","ref_index":20,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents","primary_cat":"cs.AI","submitted_at":"2026-04-19T07:51:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"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.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"realistic, long-horizon tasks under shared Harbor-based execution setups for reproducibility and comparability [6, 7, 9, 22, 36]. 4.2 Skills as Procedural Knowledge for Agents Recent studies treatskillsas reusable procedural knowledge bridging models and workflows, includ- ing large-scale skill management, skill-aware benchmarking, and trajectory distillation into reusable skills [20, 24, 29]. However, these works mainly focus on infrastructure or downstream performance, with limited evaluation of skill derivation and cross-task transfer. 4.3 Automatic Skill Discovery and Evolution Another line of work explores automatic skill discovery and evolution from interaction, including distilling interaction patterns, refining skills through feedback and failures [1, 16, 35, 39, 41, 43], and"},{"citing_arxiv_id":"2604.08491","ref_index":34,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Figures as Interfaces: Toward LLM-Native Artifacts for Scientific Discovery","primary_cat":"cs.HC","submitted_at":"2026-04-09T17:30:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"LLM-native figures embed provenance and enable direct LLM interaction with scientific visualizations to accelerate discovery and improve reproducibility.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.13064","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Red Skills or Blue Skills? A Dive Into Skills Published on ClawHub","primary_cat":"cs.CL","submitted_at":"2026-03-19T14:31:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Analysis of ClawHub shows language-based functional divides in agent skills, with over 30% flagged suspicious and submission-time documentation enabling 73% accurate risk prediction.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}