{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RSLHGCOWXB22X3YAG6SMUE27HA","short_pith_number":"pith:RSLHGCOW","schema_version":"1.0","canonical_sha256":"8c967309d6b875abef0037a4ca135f3812be2599ee232b74f19d79d336018128","source":{"kind":"arxiv","id":"2603.02766","version":1},"attestation_state":"computed","paper":{"title":"EvoSkill: Automated Skill Discovery for Multi-Agent Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"EvoSkill automatically discovers reusable agent skills through failure analysis to improve performance without changing the model.","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Jaydon Bingham, Noah Provenzano, Salaheddin Alzubi, Tu Vu, Weiyuan Chen","submitted_at":"2026-03-03T09:07:22Z","abstract_excerpt":"Coding agents are increasingly used as general-purpose problem solvers, but their flexibility does not by itself confer the domain expertise needed for specialized tasks. Recent work addresses this through \\textit{agent skills}: reusable workflows, and code, that augment agents with domain-specific capabilities. Most skills today are hand-crafted, and existing evolutionary approaches optimize low-level artifacts (e.g. prompts \\& code) that are tightly coupled to specific models and tasks. We introduce \\textbf{EvoSkill}, a self-evolving framework that automatically discovers and refines agent s"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2603.02766","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-03-03T09:07:22Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"d1ff511b1c5f7b42bcb3120baa9ae8d47138de7e880d195e6f7eb9e02db0d795","abstract_canon_sha256":"0a3216ff28967491494c1c732d2e6dfe23e008c046bcc7f01c5b06866da9d63e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:15.401508Z","signature_b64":"EzMftA8vfg9a00XfRa1CoQh1xD8ynAGbOOTCgZwubt69RyQKwEhlbxDK/RJavO4YmUNRrY2v4lanfL4GjAquDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c967309d6b875abef0037a4ca135f3812be2599ee232b74f19d79d336018128","last_reissued_at":"2026-05-17T23:38:15.400988Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:15.400988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EvoSkill: Automated Skill Discovery for Multi-Agent Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"EvoSkill automatically discovers reusable agent skills through failure analysis to improve performance without changing the model.","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Jaydon Bingham, Noah Provenzano, Salaheddin Alzubi, Tu Vu, Weiyuan Chen","submitted_at":"2026-03-03T09:07:22Z","abstract_excerpt":"Coding agents are increasingly used as general-purpose problem solvers, but their flexibility does not by itself confer the domain expertise needed for specialized tasks. Recent work addresses this through \\textit{agent skills}: reusable workflows, and code, that augment agents with domain-specific capabilities. Most skills today are hand-crafted, and existing evolutionary approaches optimize low-level artifacts (e.g. prompts \\& code) that are tightly coupled to specific models and tasks. We introduce \\textbf{EvoSkill}, a self-evolving framework that automatically discovers and refines agent s"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"EvoSkill analyzes execution failures, proposes new skills or edits to existing ones, and materializes them into structured, reusable skill folders. A Pareto frontier of agent programs governs selection, retaining only skills that improve held-out validation performance while the underlying model remains frozen. We evaluate EvoSkill on two benchmarks: OfficeQA... improves exact-match accuracy by 7.3% (60.6% → 67.9%); and SealQA... yields a 12.1% gain (26.6% → 38.7%). ... skills evolved from SealQA transfers zero-shot to BrowseComp, improving accuracy by 5.3%.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That iterative failure analysis can reliably generate skills whose benefits on held-out validation reflect genuine generalization rather than benchmark-specific artifacts or unstated implementation choices in the skill proposal step.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"EvoSkill evolves agent skills via failure analysis and Pareto frontier selection, raising exact-match accuracy 7.3% on OfficeQA and 12.1% on SealQA with 5.3% zero-shot transfer to BrowseComp.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"EvoSkill automatically discovers reusable agent skills through failure analysis to improve performance without changing the model.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b5830b8b98826cb57710aab3eaed2c4f6e69c83294287853f53afdba0fb7884e"},"source":{"id":"2603.02766","kind":"arxiv","version":1},"verdict":{"id":"78deba2c-4398-4263-b6ca-bcc698571435","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T02:18:59.569796Z","strongest_claim":"EvoSkill analyzes execution failures, proposes new skills or edits to existing ones, and materializes them into structured, reusable skill folders. A Pareto frontier of agent programs governs selection, retaining only skills that improve held-out validation performance while the underlying model remains frozen. We evaluate EvoSkill on two benchmarks: OfficeQA... improves exact-match accuracy by 7.3% (60.6% → 67.9%); and SealQA... yields a 12.1% gain (26.6% → 38.7%). ... skills evolved from SealQA transfers zero-shot to BrowseComp, improving accuracy by 5.3%.","one_line_summary":"EvoSkill evolves agent skills via failure analysis and Pareto frontier selection, raising exact-match accuracy 7.3% on OfficeQA and 12.1% on SealQA with 5.3% zero-shot transfer to BrowseComp.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That iterative failure analysis can reliably generate skills whose benefits on held-out validation reflect genuine generalization rather than benchmark-specific artifacts or unstated implementation choices in the skill proposal step.","pith_extraction_headline":"EvoSkill automatically discovers reusable agent skills through failure analysis to improve performance without changing the model."},"references":{"count":55,"sample":[{"doi":"","year":2025,"title":"Agent skills specification, 2025","work_id":"cc370620-94eb-4f6b-8c2b-a40f797b4ead","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning","work_id":"40b60d06-dc1c-4799-b75d-ff1eca653049","ref_index":2,"cited_arxiv_id":"2507.19457","is_internal_anchor":true},{"doi":"","year":2026,"title":"Roma: Recursive open meta-agent framework for long-horizon multi-agent systems, 2026","work_id":"f9efd630-2181-4456-941f-bc772bac6627","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Anthropic skills documentation, 2025","work_id":"04711a91-a683-427a-a581-6222c2c3b80d","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"Claude code overview, 2026","work_id":"56e50904-fb0b-4d6f-a71f-44d583dec220","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":55,"snapshot_sha256":"ed781fa73596c9e64980e686db68b19e93c8cece7c614defac0549434068392a","internal_anchors":6},"formal_canon":{"evidence_count":2,"snapshot_sha256":"fff1fb79c4f29ec0c1e34e4ec4f045feabae2ad949bdc77b2c2f4e7d1168c483"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2603.02766","created_at":"2026-05-17T23:38:15.401073+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.02766v1","created_at":"2026-05-17T23:38:15.401073+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.02766","created_at":"2026-05-17T23:38:15.401073+00:00"},{"alias_kind":"pith_short_12","alias_value":"RSLHGCOWXB22","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"RSLHGCOWXB22X3YA","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"RSLHGCOW","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":25,"internal_anchor_count":25,"sample":[{"citing_arxiv_id":"2605.23657","citing_title":"OpenSkillEval: Automatically Auditing the Open Skill Ecosystem for LLM Agents","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23904","citing_title":"SkillOpt: Executive Strategy for Self-Evolving Agent Skills","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23899","citing_title":"From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09297","citing_title":"SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":102,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18401","citing_title":"SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13527","citing_title":"MMSkills: Towards Multimodal Skills for General Visual Agents","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14477","citing_title":"Test-Time Learning with an Evolving Library","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13527","citing_title":"MMSkills: Towards Multimodal Skills for General Visual Agents","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03964","citing_title":"SKILLFOUNDRY: Building Self-Evolving Agent Skill Libraries from Heterogeneous Scientific Resources","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10999","citing_title":"SkillGen: Verified Inference-Time Agent Skill Synthesis","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27660","citing_title":"From Context to Skills: Can Language Models Learn from Context Skillfully?","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08386","citing_title":"SkillLens: Adaptive Multi-Granularity Skill Reuse for Cost-Efficient LLM Agents","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09192","citing_title":"Evidence Over Plans: Online Trajectory Verification for Skill Distillation","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10663","citing_title":"Evolving-RL: End-to-End Optimization of Experience-Driven Self-Evolving Capability within Agents","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.03808","citing_title":"Agentic-imodels: Evolving agentic interpretability tools via autoresearch","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23853","citing_title":"ClawTrace: Cost-Aware Tracing for LLM Agent Skill Distillation","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06230","citing_title":"Safactory: A Scalable Agentic Infrastructure for Training Trustworthy Autonomous Intelligence","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09297","citing_title":"SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06230","citing_title":"Safactory: A Scalable Agentic Infrastructure for Training Trustworthy Autonomous Intelligence","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":102,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15877","citing_title":"Experience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agents","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17308","citing_title":"SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17503","citing_title":"SkillGraph: Self-Evolving Multi-Agent Collaboration with Multimodal Graph Topology","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24198","citing_title":"Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RSLHGCOWXB22X3YAG6SMUE27HA","json":"https://pith.science/pith/RSLHGCOWXB22X3YAG6SMUE27HA.json","graph_json":"https://pith.science/api/pith-number/RSLHGCOWXB22X3YAG6SMUE27HA/graph.json","events_json":"https://pith.science/api/pith-number/RSLHGCOWXB22X3YAG6SMUE27HA/events.json","paper":"https://pith.science/paper/RSLHGCOW"},"agent_actions":{"view_html":"https://pith.science/pith/RSLHGCOWXB22X3YAG6SMUE27HA","download_json":"https://pith.science/pith/RSLHGCOWXB22X3YAG6SMUE27HA.json","view_paper":"https://pith.science/paper/RSLHGCOW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.02766&json=true","fetch_graph":"https://pith.science/api/pith-number/RSLHGCOWXB22X3YAG6SMUE27HA/graph.json","fetch_events":"https://pith.science/api/pith-number/RSLHGCOWXB22X3YAG6SMUE27HA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RSLHGCOWXB22X3YAG6SMUE27HA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RSLHGCOWXB22X3YAG6SMUE27HA/action/storage_attestation","attest_author":"https://pith.science/pith/RSLHGCOWXB22X3YAG6SMUE27HA/action/author_attestation","sign_citation":"https://pith.science/pith/RSLHGCOWXB22X3YAG6SMUE27HA/action/citation_signature","submit_replication":"https://pith.science/pith/RSLHGCOWXB22X3YAG6SMUE27HA/action/replication_record"}},"created_at":"2026-05-17T23:38:15.401073+00:00","updated_at":"2026-05-17T23:38:15.401073+00:00"}