{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6BINZHFZAHM47LSIJUD2MNI52T","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":"49fd385b0673db63b9323c20ba7f1bbfb783b499b6ffc22c4c77972220f0cc23","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T14:17:53Z","title_canon_sha256":"9e68c6a3e2f7a50338609f13949977c99fcef2cb3b2658b926aabf70165b7f80"},"schema_version":"1.0","source":{"id":"2505.03792","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03792","created_at":"2026-07-05T11:14:59Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03792v2","created_at":"2026-07-05T11:14:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03792","created_at":"2026-07-05T11:14:59Z"},{"alias_kind":"pith_short_12","alias_value":"6BINZHFZAHM4","created_at":"2026-07-05T11:14:59Z"},{"alias_kind":"pith_short_16","alias_value":"6BINZHFZAHM47LSI","created_at":"2026-07-05T11:14:59Z"},{"alias_kind":"pith_short_8","alias_value":"6BINZHFZ","created_at":"2026-07-05T11:14:59Z"}],"graph_snapshots":[{"event_id":"sha256:93876459f642e147b00d98b677ca76f6a20c8bcd4d94049c9e93c358f33aad42","target":"graph","created_at":"2026-07-05T11:14:59Z","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/2505.03792/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Online fine-tuning vision-language model (VLM) agents with reinforcement learning (RL) has shown promise for equipping agents with multi-step, goal-oriented capabilities in dynamic environments. However, their open-ended textual action space and non-end-to-end nature of action generation present significant challenges to effective online exploration in RL, e.g., explosion of the exploration space. We propose a novel online fine-tuning method, Counterfactual Soft Reinforcement Learning (CoSo), better suited to the textual output space of VLM agents. Compared to prior methods that assign uniform","authors_text":"Bo An, Fei Huang, Haiyang Xu, Lang Feng, Longtao Zheng, Ming Yan, Weihao Tan, Zhiyi Lyu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T14:17:53Z","title":"Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03792","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:c1e76be210f271fe0fa3062c6fd2b41bebb5ba9efd65c07872cc48f57c621d5f","target":"record","created_at":"2026-07-05T11:14:59Z","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":"49fd385b0673db63b9323c20ba7f1bbfb783b499b6ffc22c4c77972220f0cc23","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T14:17:53Z","title_canon_sha256":"9e68c6a3e2f7a50338609f13949977c99fcef2cb3b2658b926aabf70165b7f80"},"schema_version":"1.0","source":{"id":"2505.03792","kind":"arxiv","version":2}},"canonical_sha256":"f050dc9cb901d9cfae484d07a6351dd4eaf7f068d0588f48022722c6d1eb56cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f050dc9cb901d9cfae484d07a6351dd4eaf7f068d0588f48022722c6d1eb56cf","first_computed_at":"2026-07-05T11:14:59.136699Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:59.136699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SR95jRQ6VuNRY/+92OOCVGNXGHJAHU0FBt20KGhyBd7q6zzyUR6Uh+EowOds7pUFErrIRS4EIdqK/hjUU/0OBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:59.137187Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.03792","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c1e76be210f271fe0fa3062c6fd2b41bebb5ba9efd65c07872cc48f57c621d5f","sha256:93876459f642e147b00d98b677ca76f6a20c8bcd4d94049c9e93c358f33aad42"],"state_sha256":"6c4c0da174b4d4d9f4b8f87f2ecb4f890e0883e0a70140774034a2edaf788f80"}