{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HTFM2ZG3T27EMHPFF6EWIDXI3I","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6a805cd9245afc737b08fd2ef39970923ad01ce612a94cdf83820cbf74252fdf","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-11T20:57:46Z","title_canon_sha256":"03a56950972d6e29d01c8a6dc2169e12a5f6c23234c57ef83678386479da1b22"},"schema_version":"1.0","source":{"id":"2502.07949","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07949","created_at":"2026-07-05T11:06:28Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07949v2","created_at":"2026-07-05T11:06:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07949","created_at":"2026-07-05T11:06:28Z"},{"alias_kind":"pith_short_12","alias_value":"HTFM2ZG3T27E","created_at":"2026-07-05T11:06:28Z"},{"alias_kind":"pith_short_16","alias_value":"HTFM2ZG3T27EMHPF","created_at":"2026-07-05T11:06:28Z"},{"alias_kind":"pith_short_8","alias_value":"HTFM2ZG3","created_at":"2026-07-05T11:06:28Z"}],"graph_snapshots":[{"event_id":"sha256:b803721b51c4821c08a0581336f8c29f8fa20b1ffb029f393b5273d6792907d5","target":"graph","created_at":"2026-07-05T11:06:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.07949/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"State-of-the-art (SOTA) reinforcement learning (RL) methods have enabled vision-language model (VLM) agents to learn from interaction with online environments without human supervision. However, these methods often struggle with learning inefficiencies when applied to complex, real-world decision-making tasks with sparse rewards and long-horizon dependencies. We propose a novel framework, Variational Subgoal-Conditioned Reinforcement Learning (VSC-RL), advancing the VLM agents in resolving challenging decision-making tasks. Fundamentally distinct from existing methods, VSC-RL reformulates the ","authors_text":"Jianheng Liu, Jianye Hao, Jun Wang, Kun Shao, Qingyuan Wu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-11T20:57:46Z","title":"Advancing Autonomous VLM Agents via Variational Subgoal-Conditioned Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07949","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b6a2c40d63c3bec6ad1ab8b7e4973c6cefc916f1deadc46045d52e59062f04d9","target":"record","created_at":"2026-07-05T11:06:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6a805cd9245afc737b08fd2ef39970923ad01ce612a94cdf83820cbf74252fdf","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-11T20:57:46Z","title_canon_sha256":"03a56950972d6e29d01c8a6dc2169e12a5f6c23234c57ef83678386479da1b22"},"schema_version":"1.0","source":{"id":"2502.07949","kind":"arxiv","version":2}},"canonical_sha256":"3ccacd64db9ebe461de52f89640ee8da232642baccc009f3ca2c84bf652800cb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ccacd64db9ebe461de52f89640ee8da232642baccc009f3ca2c84bf652800cb","first_computed_at":"2026-07-05T11:06:28.155776Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:28.155776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GmlNxZNYT1ZqkBLEozaVFxhuBXOEfeKdXO8fy0hWEDcPXcNcWdrNkwGBQBZ886a5D5wn9XbBZbxj99+vbwEOCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:28.156261Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.07949","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6a2c40d63c3bec6ad1ab8b7e4973c6cefc916f1deadc46045d52e59062f04d9","sha256:b803721b51c4821c08a0581336f8c29f8fa20b1ffb029f393b5273d6792907d5"],"state_sha256":"3a84b61299c7a57421be06c3babc997e30c4e8f7a9cbeed1a68aa2bbd380235e"}