{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BPYAUG3GIK6RD57N53XF63G67W","short_pith_number":"pith:BPYAUG3G","canonical_record":{"source":{"id":"2502.15214","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-21T05:01:30Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"f6b9bb0cdc46139d592029b8a1b455a04f885101b0d55f84c2d603325d14c71f","abstract_canon_sha256":"de5b26fb39673c1b67ae1bc88fc2a0ca2397b7914f381e2dc1c793efeef3dc4e"},"schema_version":"1.0"},"canonical_sha256":"0bf00a1b6642bd11f7edeeee5f6cdefd8c18eff06edd082b1a97f5fbbd4c1224","source":{"kind":"arxiv","id":"2502.15214","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.15214","created_at":"2026-07-05T10:17:57Z"},{"alias_kind":"arxiv_version","alias_value":"2502.15214v1","created_at":"2026-07-05T10:17:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15214","created_at":"2026-07-05T10:17:57Z"},{"alias_kind":"pith_short_12","alias_value":"BPYAUG3GIK6R","created_at":"2026-07-05T10:17:57Z"},{"alias_kind":"pith_short_16","alias_value":"BPYAUG3GIK6RD57N","created_at":"2026-07-05T10:17:57Z"},{"alias_kind":"pith_short_8","alias_value":"BPYAUG3G","created_at":"2026-07-05T10:17:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BPYAUG3GIK6RD57N53XF63G67W","target":"record","payload":{"canonical_record":{"source":{"id":"2502.15214","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-21T05:01:30Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"f6b9bb0cdc46139d592029b8a1b455a04f885101b0d55f84c2d603325d14c71f","abstract_canon_sha256":"de5b26fb39673c1b67ae1bc88fc2a0ca2397b7914f381e2dc1c793efeef3dc4e"},"schema_version":"1.0"},"canonical_sha256":"0bf00a1b6642bd11f7edeeee5f6cdefd8c18eff06edd082b1a97f5fbbd4c1224","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:57.946689Z","signature_b64":"pEPxeZk25pgwFcEElYuu3Bd+rvUfyvM9Md8jkoa43U0HmsQGFlLKRGPfS5iGQlORsBl3hy1j+L+uC2smQ32FCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bf00a1b6642bd11f7edeeee5f6cdefd8c18eff06edd082b1a97f5fbbd4c1224","last_reissued_at":"2026-07-05T10:17:57.946192Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:57.946192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.15214","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:17:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r0XSg+J2p0fYD+zhBwl9gaLfSFauUTCOo0UmOF90HVm/s1t1uz2slRfuCPiGE014TLnOSJWBYLi7BDpAA0kBDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:35:48.203319Z"},"content_sha256":"00c4c0e2e6254959307349eed80db90e775b19bb22943f1f3175da7153502cdf","schema_version":"1.0","event_id":"sha256:00c4c0e2e6254959307349eed80db90e775b19bb22943f1f3175da7153502cdf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BPYAUG3GIK6RD57N53XF63G67W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Evolving Landscape of LLM- and VLM-Integrated Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Fatemeh Abdollahi, Masoud Jafaripour, Matthew E. Taylor, Osmar R. Zaiane, Shadan Golestan, Sheila Schoepp, Tianpei Yang, Yingyue Cao, Zahin Sufiyan","submitted_at":"2025-02-21T05:01:30Z","abstract_excerpt":"Reinforcement learning (RL) has shown impressive results in sequential decision-making tasks. Meanwhile, Large Language Models (LLMs) and Vision-Language Models (VLMs) have emerged, exhibiting impressive capabilities in multimodal understanding and reasoning. These advances have led to a surge of research integrating LLMs and VLMs into RL. In this survey, we review representative works in which LLMs and VLMs are used to overcome key challenges in RL, such as lack of prior knowledge, long-horizon planning, and reward design. We present a taxonomy that categorizes these LLM/VLM-assisted RL appro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15214","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.15214/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:17:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zpg7z+UeBmddWg2zIRf8QYxfstVlXZ1CIgO7u4Ow+BrryRyyOMLE7GiF2IIy3bBXOklUIUlNgWUG/7GHGL75Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:35:48.203825Z"},"content_sha256":"1d7267411c69814933007fd6097761fe61d5a2986b66d1e4d72c968fea310724","schema_version":"1.0","event_id":"sha256:1d7267411c69814933007fd6097761fe61d5a2986b66d1e4d72c968fea310724"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BPYAUG3GIK6RD57N53XF63G67W/bundle.json","state_url":"https://pith.science/pith/BPYAUG3GIK6RD57N53XF63G67W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BPYAUG3GIK6RD57N53XF63G67W/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T17:35:48Z","links":{"resolver":"https://pith.science/pith/BPYAUG3GIK6RD57N53XF63G67W","bundle":"https://pith.science/pith/BPYAUG3GIK6RD57N53XF63G67W/bundle.json","state":"https://pith.science/pith/BPYAUG3GIK6RD57N53XF63G67W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BPYAUG3GIK6RD57N53XF63G67W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BPYAUG3GIK6RD57N53XF63G67W","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":"de5b26fb39673c1b67ae1bc88fc2a0ca2397b7914f381e2dc1c793efeef3dc4e","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-21T05:01:30Z","title_canon_sha256":"f6b9bb0cdc46139d592029b8a1b455a04f885101b0d55f84c2d603325d14c71f"},"schema_version":"1.0","source":{"id":"2502.15214","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.15214","created_at":"2026-07-05T10:17:57Z"},{"alias_kind":"arxiv_version","alias_value":"2502.15214v1","created_at":"2026-07-05T10:17:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15214","created_at":"2026-07-05T10:17:57Z"},{"alias_kind":"pith_short_12","alias_value":"BPYAUG3GIK6R","created_at":"2026-07-05T10:17:57Z"},{"alias_kind":"pith_short_16","alias_value":"BPYAUG3GIK6RD57N","created_at":"2026-07-05T10:17:57Z"},{"alias_kind":"pith_short_8","alias_value":"BPYAUG3G","created_at":"2026-07-05T10:17:57Z"}],"graph_snapshots":[{"event_id":"sha256:1d7267411c69814933007fd6097761fe61d5a2986b66d1e4d72c968fea310724","target":"graph","created_at":"2026-07-05T10:17:57Z","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/2502.15214/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has shown impressive results in sequential decision-making tasks. Meanwhile, Large Language Models (LLMs) and Vision-Language Models (VLMs) have emerged, exhibiting impressive capabilities in multimodal understanding and reasoning. These advances have led to a surge of research integrating LLMs and VLMs into RL. In this survey, we review representative works in which LLMs and VLMs are used to overcome key challenges in RL, such as lack of prior knowledge, long-horizon planning, and reward design. We present a taxonomy that categorizes these LLM/VLM-assisted RL appro","authors_text":"Fatemeh Abdollahi, Masoud Jafaripour, Matthew E. Taylor, Osmar R. Zaiane, Shadan Golestan, Sheila Schoepp, Tianpei Yang, Yingyue Cao, Zahin Sufiyan","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-21T05:01:30Z","title":"The Evolving Landscape of LLM- and VLM-Integrated Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15214","kind":"arxiv","version":1},"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":"sha256:00c4c0e2e6254959307349eed80db90e775b19bb22943f1f3175da7153502cdf","target":"record","created_at":"2026-07-05T10:17:57Z","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":"de5b26fb39673c1b67ae1bc88fc2a0ca2397b7914f381e2dc1c793efeef3dc4e","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-21T05:01:30Z","title_canon_sha256":"f6b9bb0cdc46139d592029b8a1b455a04f885101b0d55f84c2d603325d14c71f"},"schema_version":"1.0","source":{"id":"2502.15214","kind":"arxiv","version":1}},"canonical_sha256":"0bf00a1b6642bd11f7edeeee5f6cdefd8c18eff06edd082b1a97f5fbbd4c1224","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0bf00a1b6642bd11f7edeeee5f6cdefd8c18eff06edd082b1a97f5fbbd4c1224","first_computed_at":"2026-07-05T10:17:57.946192Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:57.946192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pEPxeZk25pgwFcEElYuu3Bd+rvUfyvM9Md8jkoa43U0HmsQGFlLKRGPfS5iGQlORsBl3hy1j+L+uC2smQ32FCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:57.946689Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.15214","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00c4c0e2e6254959307349eed80db90e775b19bb22943f1f3175da7153502cdf","sha256:1d7267411c69814933007fd6097761fe61d5a2986b66d1e4d72c968fea310724"],"state_sha256":"5e57a3afd3ce7929cce0f11f9df0b8810b3fc677c18f3165f4dcb2e9fdf993b5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5qW9OOHBdO5kloyMVa32BJhe+S0OFpd5P9pMZSx2iePw//k/QjMO8SPztmCgjaf8mXn0BxcWozRF70MjfMEgCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T17:35:48.208033Z","bundle_sha256":"ddd30de2be14d01c5170bf8707aee968ac1a56073df2852a713449ba73deec7c"}}