{"id":"158057316084d0e66ec8707b81767260cdcf7b368ccf4cba6da9bd81d9591e84","title":"Feng and colleagues propose SCOPE for long-horizon Web tasks","argument":"The paper’s authors, Xueyang Feng, Xiaohe Bo, Xu Chen, Quanyu Dai and Feng Wen, propose Skill-Composed Progressive Exploration (SCOPE) to help LLM Web agents learn long tasks despite sparse rewards and few successful attempts. Their approach builds from reusable local skills: it finds skills and failure experiences in earlier attempts, combines skills into chains, then uses relevant failures to guide exploration of additional subskills. The authors say SCOPE progressively builds task-completing skill chains across attempts and incorporates them into the agent’s policy through agentic on-policy distillation. In experiments on WebArena, WebVoyager and WebShop, they report relative gains of 3.9% to 18.6% over the strongest baselines in each setting. These results concern the reported benchmarks; the abstract does not establish how the approach performs on other websites or real-world tasks. The paper’s central idea is to use failures not just as unsuccessful outcomes, but as guidance for learning the next piece of a longer task. How well do the reported gains carry over to web tasks beyond the three tested benchmarks?","topicIds":["intelligence-and-discovery"],"domain":"science","claimType":"attributed reading","limits":"The supplied evidence is the abstract, so it does not provide experiment details, baseline identities, or results on tasks beyond WebArena, WebVoyager, and WebShop.","speaker":{"name":"Feng, Xueyang, Bo, Xiaohe, Chen, Xu, Dai, Quanyu, Wen, Feng","roleAtSource":"Article author"},"source":{"title":"From Local Skills to Long-Horizon Web Tasks: Progressive Skill Exploration for LLM Web Agents","publisher":"arXiv cs.AI","format":"Article","url":"https://arxiv.org/abs/2611.03116","publishedAt":"2026-11-02","dateBasis":"Date basis not provided."},"evidence":[{"text":"The authors propose SCOPE, which progressively explores from local skills toward complete task-solving capability for long-horizon Web agents.","excerpt":"we propose Skill-Composed Progressive Exploration (SCOPE), a short-to-long learning framework for long-horizon Web agents","url":"https://arxiv.org/abs/2611.03116","relationship":"Source-stated"},{"text":"SCOPE finds reusable local skills and failure experiences, composes skills into chains, and uses aligned failures to guide exploration of new subskills.","excerpt":"Skill Expansion leverages failure experiences aligned with the current skill chain to guide the agent toward exploring new subskills.","url":"https://arxiv.org/abs/2611.03116","relationship":"Source-stated"},{"text":"The authors report relative gains of 3.9% to 18.6% over the strongest baselines in each of three benchmark settings.","excerpt":"achieves 3.9% to 18.6% relative gains over the strongest baselines in each setting.","url":"https://arxiv.org/abs/2611.03116","relationship":"Source-stated"}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.03116","checkedAt":"2026-11-10T23:36:09.115Z","items":[],"note":"No suitable media was found by the supported page extraction."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"How well do the reported gains carry over to web tasks beyond the three tested benchmarks?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Feng and colleagues propose SCOPE for long-horizon Web tasks","summary":"The paper’s authors, Xueyang Feng, Xiaohe Bo, Xu Chen, Quanyu Dai and Feng Wen, propose Skill-Composed Progressive Exploration (SCOPE) to help LLM Web agents learn long tasks despite sparse rewards and few successful attempts. Their approach builds from reusable local skills: it finds skills and failure experiences in earlier attempts, combines skills into chains, then uses relevant failures to guide exploration of additional subskills. The authors say SCOPE progressively builds task-completing skill chains across attempts and incorporates them into the agent’s policy through agentic on-policy distillation. In experiments on WebArena, WebVoyager and WebShop, they report relative gains of 3.9% to 18.6% over the strongest baselines in each setting. These results concern the reported benchmarks; the abstract does not establish how the approach performs on other websites or real-world tasks. The paper’s central idea is to use failures not just as unsuccessful outcomes, but as guidance for learning the next piece of a longer task. How well do the reported gains carry over to web tasks beyond the three tested benchmarks?","question":"How well do the reported gains carry over to web tasks beyond the three tested benchmarks?","claims":[{"text":"The authors propose SCOPE, which progressively explores from local skills toward complete task-solving capability for long-horizon Web agents.","excerpt":"we propose Skill-Composed Progressive Exploration (SCOPE), a short-to-long learning framework for long-horizon Web agents","support":"source-stated"},{"text":"SCOPE finds reusable local skills and failure experiences, composes skills into chains, and uses aligned failures to guide exploration of new subskills.","excerpt":"Skill Expansion leverages failure experiences aligned with the current skill chain to guide the agent toward exploring new subskills.","support":"source-stated"},{"text":"The authors report relative gains of 3.9% to 18.6% over the strongest baselines in each of three benchmark settings.","excerpt":"achieves 3.9% to 18.6% relative gains over the strongest baselines in each setting.","support":"source-stated"}],"limitations":["The supplied evidence is the abstract, so it does not provide experiment details, baseline identities, or results on tasks beyond WebArena, WebVoyager, and WebShop."],"mediaId":"0d5d55460ed82f1e34aef974274d780c210902d462442c632535e762a723379e","correctionReason":null,"id":"158057316084d0e66ec8707b81767260cdcf7b368ccf4cba6da9bd81d9591e84","publicationId":"656384a5-7daf-4c8f-888f-39c8e7aa42bc","version":1,"sourceUrl":"https://arxiv.org/abs/2611.03116","sourceTitle":"From Local Skills to Long-Horizon Web Tasks: Progressive Skill Exploration for LLM Web Agents","publisher":"arXiv cs.AI","publishedAt":null,"originalPublished":{"value":"2026-11-02","precision":"day","basis":"publisher_citation_date"},"firstObservedAt":"2026-11-03T09:04:00.965Z","createdAt":"2026-11-10T06:32:47.184Z","historical":true,"entityIds":["arxiv"],"topicIds":["intelligence-and-discovery"],"media":[{"id":"0d5d55460ed82f1e34aef974274d780c210902d462442c632535e762a723379e","kind":"article","url":"https://arxiv.org/abs/2611.03116","sourceUrl":"https://arxiv.org/abs/2611.03116","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-04T03:32:46.972Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.03116","checkedAt":"2026-11-10T23:36:09.115Z","items":[],"note":"No suitable media was found by the supported page extraction."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v5","mediaId":"0d5d55460ed82f1e34aef974274d780c210902d462442c632535e762a723379e","confidence":0.8,"provider":"typesafe","model":"jev-1.13.0","inputHash":"e9cec862dc34ab1517d026ede1987046b248af1fbce75ea09125032befffb40e","decidedAt":"2026-11-04T03:32:49.347Z"},"provenance":{"textHash":"31ceaf09f29f7110683c7940acf0a96bbe317bd9ed15f07a8c2f717a8ad15c38","observationId":"853680bc26f2af4e34f7785fc9b88b11e8ab3bf14fccabc4951898052b8c801d","retrievedAt":"2026-11-04T03:32:46.637Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"30df258f-5c78-4172-83a8-9cb57e899b5a"},"reviewer":{"model":"gpt-6-luna","runId":"29ee3819-ba53-4a49-82fc-b7536dd19534"}},"audit":{"status":"passed","reviewedAt":"2026-11-10T06:32:47.184Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Feng, Xueyang","url":null,"kind":"unknown"},{"name":"Bo, Xiaohe","url":null,"kind":"unknown"},{"name":"Chen, Xu","url":null,"kind":"unknown"},{"name":"Dai, Quanyu","url":null,"kind":"unknown"},{"name":"Wen, Feng","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Feng, Xueyang","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Feng, Xueyang","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.03116","locator":"head/meta[name=author|citation_author]"},"assertionId":"0bf5bbb55d5c1ad1ac4d76d168fb6fab0ae2aa6adf6b9652bbb533dd952834d3:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T23:36:09.115Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"0bf5bbb55d5c1ad1ac4d76d168fb6fab0ae2aa6adf6b9652bbb533dd952834d3","sourceUrl":"https://arxiv.org/abs/2611.03116","contentSha256":"088fd2fb99560b8326e897e47f9f4608df5498822596c5a2e8e2c094b4de74a2","textHash":"31ceaf09f29f7110683c7940acf0a96bbe317bd9ed15f07a8c2f717a8ad15c38","observedAt":"2026-11-10T23:36:09.115Z"}},{"actor":{"name":"Bo, Xiaohe","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Bo, Xiaohe","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.03116","locator":"head/meta[name=author|citation_author]"},"assertionId":"0bf5bbb55d5c1ad1ac4d76d168fb6fab0ae2aa6adf6b9652bbb533dd952834d3:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T23:36:09.115Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"0bf5bbb55d5c1ad1ac4d76d168fb6fab0ae2aa6adf6b9652bbb533dd952834d3","sourceUrl":"https://arxiv.org/abs/2611.03116","contentSha256":"088fd2fb99560b8326e897e47f9f4608df5498822596c5a2e8e2c094b4de74a2","textHash":"31ceaf09f29f7110683c7940acf0a96bbe317bd9ed15f07a8c2f717a8ad15c38","observedAt":"2026-11-10T23:36:09.115Z"}},{"actor":{"name":"Chen, Xu","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Chen, Xu","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.03116","locator":"head/meta[name=author|citation_author]"},"assertionId":"0bf5bbb55d5c1ad1ac4d76d168fb6fab0ae2aa6adf6b9652bbb533dd952834d3:participation:2","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T23:36:09.115Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"0bf5bbb55d5c1ad1ac4d76d168fb6fab0ae2aa6adf6b9652bbb533dd952834d3","sourceUrl":"https://arxiv.org/abs/2611.03116","contentSha256":"088fd2fb99560b8326e897e47f9f4608df5498822596c5a2e8e2c094b4de74a2","textHash":"31ceaf09f29f7110683c7940acf0a96bbe317bd9ed15f07a8c2f717a8ad15c38","observedAt":"2026-11-10T23:36:09.115Z"}},{"actor":{"name":"Dai, Quanyu","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Dai, Quanyu","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.03116","locator":"head/meta[name=author|citation_author]"},"assertionId":"0bf5bbb55d5c1ad1ac4d76d168fb6fab0ae2aa6adf6b9652bbb533dd952834d3:participation:3","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T23:36:09.115Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"0bf5bbb55d5c1ad1ac4d76d168fb6fab0ae2aa6adf6b9652bbb533dd952834d3","sourceUrl":"https://arxiv.org/abs/2611.03116","contentSha256":"088fd2fb99560b8326e897e47f9f4608df5498822596c5a2e8e2c094b4de74a2","textHash":"31ceaf09f29f7110683c7940acf0a96bbe317bd9ed15f07a8c2f717a8ad15c38","observedAt":"2026-11-10T23:36:09.115Z"}},{"actor":{"name":"Wen, Feng","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Wen, Feng","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.03116","locator":"head/meta[name=author|citation_author]"},"assertionId":"0bf5bbb55d5c1ad1ac4d76d168fb6fab0ae2aa6adf6b9652bbb533dd952834d3:participation:4","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T23:36:09.115Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"0bf5bbb55d5c1ad1ac4d76d168fb6fab0ae2aa6adf6b9652bbb533dd952834d3","sourceUrl":"https://arxiv.org/abs/2611.03116","contentSha256":"088fd2fb99560b8326e897e47f9f4608df5498822596c5a2e8e2c094b4de74a2","textHash":"31ceaf09f29f7110683c7940acf0a96bbe317bd9ed15f07a8c2f717a8ad15c38","observedAt":"2026-11-10T23:36:09.115Z"}}],"participationCoverage":{"total":5,"returned":5,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://arxiv.org/abs/2611.03116","snapshotId":"0bf5bbb55d5c1ad1ac4d76d168fb6fab0ae2aa6adf6b9652bbb533dd952834d3","contentSha256":"088fd2fb99560b8326e897e47f9f4608df5498822596c5a2e8e2c094b4de74a2","textHash":"31ceaf09f29f7110683c7940acf0a96bbe317bd9ed15f07a8c2f717a8ad15c38","observedAt":"2026-11-10T23:36:09.115Z","basis":"publisher-page-metadata","sourceLinks":43,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/158057316084d0e66ec8707b81767260cdcf7b368ccf4cba6da9bd81d9591e84/source"}},"canonicalUrl":"https://escapemeridian.com/readings/feng-and-colleagues-propose-scope-for-long-horizon-web-tasks-15805731","formats":{"html":"/readings/feng-and-colleagues-propose-scope-for-long-horizon-web-tasks-15805731","markdown":"/readings/feng-and-colleagues-propose-scope-for-long-horizon-web-tasks-15805731.md","json":"/readings/feng-and-colleagues-propose-scope-for-long-horizon-web-tasks-15805731.json"},"attribution":"Headline and summary by Escape Meridian, prepared by Luna from the attributed source. A source check is not independent confirmation of the source’s claims.","maintainedGuideLinks":[],"readerContext":{"version":"reader-context-v1","attribution":"Reference context selected by Escape Meridian; separate from source evidence. Entity mentions do not establish authorship, involvement or endorsement.","terms":[{"id":"term-llm","name":"Large language model","explanation":"A language model with many learned numerical settings, used to process and generate language.","referenceUrl":"https://developers.google.com/machine-learning/glossary#large-language-model"},{"id":"term-agentic","name":"Agentic AI","explanation":"AI systems that plan and carry out a series of steps toward a goal, often by using other software, rather than giving one answer.","referenceUrl":"https://developers.google.com/machine-learning/glossary#agentic"},{"id":"term-benchmark","name":"Benchmark","explanation":"A defined set of tests used to compare systems. Results depend on the tasks and measures selected.","referenceUrl":"https://arxiv.org/abs/2211.09110"}],"entities":[{"id":"arxiv","name":"arXiv","kind":"organization","context":"arXiv is a research manuscript repository where authors share papers that may not yet have been peer reviewed.","referenceUrls":["https://arxiv.org/","https://info.arxiv.org/help/api/index.html"],"path":"/entities/arxiv","json":"/entities/arxiv.json","markdown":"/entities/arxiv.md"}]},"researchQuestions":[],"withdrawn":false,"references":{"schemaVersion":1,"target":{"type":"reading","id":"158057316084d0e66ec8707b81767260cdcf7b368ccf4cba6da9bd81d9591e84","revision":"656384a5-7daf-4c8f-888f-39c8e7aa42bc","revisionKind":"publication-id","title":"Feng and colleagues propose SCOPE for long-horizon Web tasks","url":"https://escapemeridian.com/readings/feng-and-colleagues-propose-scope-for-long-horizon-web-tasks-15805731"},"source":{"type":"source","id":"https://arxiv.org/abs/2611.03116","revision":"31ceaf09f29f7110683c7940acf0a96bbe317bd9ed15f07a8c2f717a8ad15c38","revisionKind":"sha256-source-text","title":"From Local Skills to Long-Horizon Web Tasks: Progressive Skill Exploration for LLM Web Agents","url":"https://arxiv.org/abs/2611.03116"},"status":"available","items":[],"next":null,"scope":"Explicit citations in public readings and public file attachments to this reading. Shared topics are not citations. Other artifact types need an explicit reference adapter."},"revisions":[{"id":"158057316084d0e66ec8707b81767260cdcf7b368ccf4cba6da9bd81d9591e84","title":"Feng and colleagues propose SCOPE for long-horizon Web tasks","argument":"The paper’s authors, Xueyang Feng, Xiaohe Bo, Xu Chen, Quanyu Dai and Feng Wen, propose Skill-Composed Progressive Exploration (SCOPE) to help LLM Web agents learn long tasks despite sparse rewards and few successful attempts. Their approach builds from reusable local skills: it finds skills and failure experiences in earlier attempts, combines skills into chains, then uses relevant failures to guide exploration of additional subskills. The authors say SCOPE progressively builds task-completing skill chains across attempts and incorporates them into the agent’s policy through agentic on-policy distillation. In experiments on WebArena, WebVoyager and WebShop, they report relative gains of 3.9% to 18.6% over the strongest baselines in each setting. These results concern the reported benchmarks; the abstract does not establish how the approach performs on other websites or real-world tasks. The paper’s central idea is to use failures not just as unsuccessful outcomes, but as guidance for learning the next piece of a longer task. How well do the reported gains carry over to web tasks beyond the three tested benchmarks?","topicIds":["intelligence-and-discovery"],"domain":"science","claimType":"attributed reading","limits":"The supplied evidence is the abstract, so it does not provide experiment details, baseline identities, or results on tasks beyond WebArena, WebVoyager, and WebShop.","speaker":{"name":"Feng, Xueyang, Bo, Xiaohe, Chen, Xu, Dai, Quanyu, Wen, Feng","roleAtSource":"Article author"},"source":{"title":"From Local Skills to Long-Horizon Web Tasks: Progressive Skill Exploration for LLM Web Agents","publisher":"arXiv cs.AI","format":"Article","url":"https://arxiv.org/abs/2611.03116","publishedAt":"2026-11-02","dateBasis":"Date basis not provided."},"evidence":[{"text":"The authors propose SCOPE, which progressively explores from local skills toward complete task-solving capability for long-horizon Web agents.","excerpt":"we propose Skill-Composed Progressive Exploration (SCOPE), a short-to-long learning framework for long-horizon Web agents","url":"https://arxiv.org/abs/2611.03116","relationship":"Source-stated"},{"text":"SCOPE finds reusable local skills and failure experiences, composes skills into chains, and uses aligned failures to guide exploration of new subskills.","excerpt":"Skill Expansion leverages failure experiences aligned with the current skill chain to guide the agent toward exploring new subskills.","url":"https://arxiv.org/abs/2611.03116","relationship":"Source-stated"},{"text":"The authors report relative gains of 3.9% to 18.6% over the strongest baselines in each of three benchmark settings.","excerpt":"achieves 3.9% to 18.6% relative gains over the strongest baselines in each setting.","url":"https://arxiv.org/abs/2611.03116","relationship":"Source-stated"}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.03116","checkedAt":"2026-11-10T23:36:09.115Z","items":[],"note":"No suitable media was found by the supported page extraction."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"How well do the reported gains carry over to web tasks beyond the three tested benchmarks?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Feng and colleagues propose SCOPE for long-horizon Web tasks","summary":"The paper’s authors, Xueyang Feng, Xiaohe Bo, Xu Chen, Quanyu Dai and Feng Wen, propose Skill-Composed Progressive Exploration (SCOPE) to help LLM Web agents learn long tasks despite sparse rewards and few successful attempts. Their approach builds from reusable local skills: it finds skills and failure experiences in earlier attempts, combines skills into chains, then uses relevant failures to guide exploration of additional subskills. The authors say SCOPE progressively builds task-completing skill chains across attempts and incorporates them into the agent’s policy through agentic on-policy distillation. In experiments on WebArena, WebVoyager and WebShop, they report relative gains of 3.9% to 18.6% over the strongest baselines in each setting. These results concern the reported benchmarks; the abstract does not establish how the approach performs on other websites or real-world tasks. The paper’s central idea is to use failures not just as unsuccessful outcomes, but as guidance for learning the next piece of a longer task. How well do the reported gains carry over to web tasks beyond the three tested benchmarks?","question":"How well do the reported gains carry over to web tasks beyond the three tested benchmarks?","claims":[{"text":"The authors propose SCOPE, which progressively explores from local skills toward complete task-solving capability for long-horizon Web agents.","excerpt":"we propose Skill-Composed Progressive Exploration (SCOPE), a short-to-long learning framework for long-horizon Web agents","support":"source-stated"},{"text":"SCOPE finds reusable local skills and failure experiences, composes skills into chains, and uses aligned failures to guide exploration of new subskills.","excerpt":"Skill Expansion leverages failure experiences aligned with the current skill chain to guide the agent toward exploring new subskills.","support":"source-stated"},{"text":"The authors report relative gains of 3.9% to 18.6% over the strongest baselines in each of three benchmark settings.","excerpt":"achieves 3.9% to 18.6% relative gains over the strongest baselines in each setting.","support":"source-stated"}],"limitations":["The supplied evidence is the abstract, so it does not provide experiment details, baseline identities, or results on tasks beyond WebArena, WebVoyager, and WebShop."],"mediaId":"0d5d55460ed82f1e34aef974274d780c210902d462442c632535e762a723379e","correctionReason":null,"id":"158057316084d0e66ec8707b81767260cdcf7b368ccf4cba6da9bd81d9591e84","publicationId":"656384a5-7daf-4c8f-888f-39c8e7aa42bc","version":1,"sourceUrl":"https://arxiv.org/abs/2611.03116","sourceTitle":"From Local Skills to Long-Horizon Web Tasks: Progressive Skill Exploration for LLM Web Agents","publisher":"arXiv cs.AI","publishedAt":null,"originalPublished":{"value":"2026-11-02","precision":"day","basis":"publisher_citation_date"},"firstObservedAt":"2026-11-03T09:04:00.965Z","createdAt":"2026-11-10T06:32:47.184Z","historical":true,"entityIds":["arxiv"],"topicIds":["intelligence-and-discovery"],"media":[{"id":"0d5d55460ed82f1e34aef974274d780c210902d462442c632535e762a723379e","kind":"article","url":"https://arxiv.org/abs/2611.03116","sourceUrl":"https://arxiv.org/abs/2611.03116","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-04T03:32:46.972Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.03116","checkedAt":"2026-11-10T23:36:09.115Z","items":[],"note":"No suitable media was found by the supported page extraction."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v5","mediaId":"0d5d55460ed82f1e34aef974274d780c210902d462442c632535e762a723379e","confidence":0.8,"provider":"typesafe","model":"jev-1.13.0","inputHash":"e9cec862dc34ab1517d026ede1987046b248af1fbce75ea09125032befffb40e","decidedAt":"2026-11-04T03:32:49.347Z"},"provenance":{"textHash":"31ceaf09f29f7110683c7940acf0a96bbe317bd9ed15f07a8c2f717a8ad15c38","observationId":"853680bc26f2af4e34f7785fc9b88b11e8ab3bf14fccabc4951898052b8c801d","retrievedAt":"2026-11-04T03:32:46.637Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"30df258f-5c78-4172-83a8-9cb57e899b5a"},"reviewer":{"model":"gpt-6-luna","runId":"29ee3819-ba53-4a49-82fc-b7536dd19534"}},"audit":{"status":"passed","reviewedAt":"2026-11-10T06:32:47.184Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Feng, Xueyang","url":null,"kind":"unknown"},{"name":"Bo, Xiaohe","url":null,"kind":"unknown"},{"name":"Chen, Xu","url":null,"kind":"unknown"},{"name":"Dai, Quanyu","url":null,"kind":"unknown"},{"name":"Wen, Feng","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Feng, Xueyang","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Feng, Xueyang","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.03116","locator":"head/meta[name=author|citation_author]"},"assertionId":"0bf5bbb55d5c1ad1ac4d76d168fb6fab0ae2aa6adf6b9652bbb533dd952834d3:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T23:36:09.115Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"0bf5bbb55d5c1ad1ac4d76d168fb6fab0ae2aa6adf6b9652bbb533dd952834d3","sourceUrl":"https://arxiv.org/abs/2611.03116","contentSha256":"088fd2fb99560b8326e897e47f9f4608df5498822596c5a2e8e2c094b4de74a2","textHash":"31ceaf09f29f7110683c7940acf0a96bbe317bd9ed15f07a8c2f717a8ad15c38","observedAt":"2026-11-10T23:36:09.115Z"}},{"actor":{"name":"Bo, Xiaohe","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Bo, Xiaohe","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.03116","locator":"head/meta[name=author|citation_author]"},"assertionId":"0bf5bbb55d5c1ad1ac4d76d168fb6fab0ae2aa6adf6b9652bbb533dd952834d3:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T23:36:09.115Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"0bf5bbb55d5c1ad1ac4d76d168fb6fab0ae2aa6adf6b9652bbb533dd952834d3","sourceUrl":"https://arxiv.org/abs/2611.03116","contentSha256":"088fd2fb99560b8326e897e47f9f4608df5498822596c5a2e8e2c094b4de74a2","textHash":"31ceaf09f29f7110683c7940acf0a96bbe317bd9ed15f07a8c2f717a8ad15c38","observedAt":"2026-11-10T23:36:09.115Z"}},{"actor":{"name":"Chen, Xu","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Chen, Xu","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.03116","locator":"head/meta[name=author|citation_author]"},"assertionId":"0bf5bbb55d5c1ad1ac4d76d168fb6fab0ae2aa6adf6b9652bbb533dd952834d3:participation:2","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T23:36:09.115Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"0bf5bbb55d5c1ad1ac4d76d168fb6fab0ae2aa6adf6b9652bbb533dd952834d3","sourceUrl":"https://arxiv.org/abs/2611.03116","contentSha256":"088fd2fb99560b8326e897e47f9f4608df5498822596c5a2e8e2c094b4de74a2","textHash":"31ceaf09f29f7110683c7940acf0a96bbe317bd9ed15f07a8c2f717a8ad15c38","observedAt":"2026-11-10T23:36:09.115Z"}},{"actor":{"name":"Dai, Quanyu","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Dai, Quanyu","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.03116","locator":"head/meta[name=author|citation_author]"},"assertionId":"0bf5bbb55d5c1ad1ac4d76d168fb6fab0ae2aa6adf6b9652bbb533dd952834d3:participation:3","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T23:36:09.115Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"0bf5bbb55d5c1ad1ac4d76d168fb6fab0ae2aa6adf6b9652bbb533dd952834d3","sourceUrl":"https://arxiv.org/abs/2611.03116","contentSha256":"088fd2fb99560b8326e897e47f9f4608df5498822596c5a2e8e2c094b4de74a2","textHash":"31ceaf09f29f7110683c7940acf0a96bbe317bd9ed15f07a8c2f717a8ad15c38","observedAt":"2026-11-10T23:36:09.115Z"}},{"actor":{"name":"Wen, Feng","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Wen, Feng","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.03116","locator":"head/meta[name=author|citation_author]"},"assertionId":"0bf5bbb55d5c1ad1ac4d76d168fb6fab0ae2aa6adf6b9652bbb533dd952834d3:participation:4","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T23:36:09.115Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"0bf5bbb55d5c1ad1ac4d76d168fb6fab0ae2aa6adf6b9652bbb533dd952834d3","sourceUrl":"https://arxiv.org/abs/2611.03116","contentSha256":"088fd2fb99560b8326e897e47f9f4608df5498822596c5a2e8e2c094b4de74a2","textHash":"31ceaf09f29f7110683c7940acf0a96bbe317bd9ed15f07a8c2f717a8ad15c38","observedAt":"2026-11-10T23:36:09.115Z"}}],"participationCoverage":{"total":5,"returned":5,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://arxiv.org/abs/2611.03116","snapshotId":"0bf5bbb55d5c1ad1ac4d76d168fb6fab0ae2aa6adf6b9652bbb533dd952834d3","contentSha256":"088fd2fb99560b8326e897e47f9f4608df5498822596c5a2e8e2c094b4de74a2","textHash":"31ceaf09f29f7110683c7940acf0a96bbe317bd9ed15f07a8c2f717a8ad15c38","observedAt":"2026-11-10T23:36:09.115Z","basis":"publisher-page-metadata","sourceLinks":43,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/158057316084d0e66ec8707b81767260cdcf7b368ccf4cba6da9bd81d9591e84/source"}}}],"audits":[{"publicationId":"656384a5-7daf-4c8f-888f-39c8e7aa42bc","verdict":"passed","findings":[{"dimension":"attribution","status":"pass","explanation":"The reading correctly names all five listed authors and attributes the framework, mechanism and benchmark results to them as their proposal and reported findings, not as established fact.","excerpt":"Authors:Xueyang Feng, Xiaohe Bo, Xu Chen, Quanyu Dai, Feng Wen"},{"dimension":"summary","status":"pass","explanation":"The reading leads with the actor and proposal, explains the three-stage mechanism in plain language, and keeps the benchmark scope clear. The closing question about generalization follows from the evidence. Exact terms such as sparse rewards, long-horizon, policy and agentic on-policy distillation should rely on term-library tooltips; add entries if missing. Omitting the skill acquisition theory inspiration and the NeurIPS acceptance does not distort meaning.","excerpt":"decomposes complex task exploration into a gradual expansion process from local skills to complete task-solving capability"},{"dimension":"date","status":"pass","explanation":"originalPublished 2026-11-02 matches the v1 arXiv submission date. It is not the later feed date of 2026-11-03.","excerpt":"[Submitted on 2 Nov 2026]"},{"dimension":"support","status":"pass","explanation":"Each claim is supported by the abstract. The motivation, the mechanism (discovery, orchestration and expansion), the internalization into the policy, and the 3.9% to 18.6% relative gains are all source-stated. The idea of using failures as guidance is grounded in Skill Expansion. The reading correctly limits the results to the three benchmarks and does not imply real-world reliability.","excerpt":"leverages failure experiences aligned with the current skill chain to guide the agent toward exploring new subskills"},{"dimension":"media","status":"pass","explanation":"The selected media is the verified arXiv abstract page for this paper. It is the direct original source and its ID matches the decision.","excerpt":null}],"createdAt":"2026-11-10T06:32:47.184Z","model":"anthropic/claude-opus-5.5"}],"correctionUrl":"https://escapemeridian.com/corrections/"}