{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IMTWFGXJJ4GJ6NLFK7GQGIPEXV","short_pith_number":"pith:IMTWFGXJ","schema_version":"1.0","canonical_sha256":"4327629ae94f0c9f356557cd0321e4bd576a53803ae01eb235d5fab5ef7e1d22","source":{"kind":"arxiv","id":"2401.00006","version":3},"attestation_state":"computed","paper":{"title":"Building Open-Ended Embodied Agent via Language-Policy Bidirectional Adaptation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fuxian Huang, Jie Wang, Jing Hou, Ming Zhou, Qi Zhang, Shaopeng Zhai, Tianyi Zhang, Yu Liu, Yu Qiao","submitted_at":"2023-12-12T11:06:07Z","abstract_excerpt":"Building embodied agents on integrating Large Language Models (LLMs) and Reinforcement Learning (RL) have revolutionized human-AI interaction: researchers can now leverage language instructions to plan decision-making for open-ended tasks. However, existing research faces challenges in meeting the requirement of open-endedness. They typically either train LLM/RL models to adapt to a fixed counterpart, limiting exploration of novel skills and hindering the efficacy of human-AI interaction. To this end, we present OpenPAL, a co-training framework comprising two stages: (1) fine-tuning a pre-trai"},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2401.00006","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2023-12-12T11:06:07Z","cross_cats_sorted":[],"title_canon_sha256":"242e4185b88497eb5adcb9204c6d0848016aaa9247f92a5b5104382250fc1e46","abstract_canon_sha256":"1dfd21d5ba9a41a8034c60b2fe33bae875dd2b3a16d9ab64b0f44971e93b8bae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:46.530572Z","signature_b64":"SAFqxt1TmcsVUWnTu1H00nu7Pqe5jXqYYFMQxp1lhletd3fBxK10bK7rYuyRL/I4b9A7x0d+Y8jkVZHlgduPCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4327629ae94f0c9f356557cd0321e4bd576a53803ae01eb235d5fab5ef7e1d22","last_reissued_at":"2026-07-05T07:41:46.530174Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:46.530174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Building Open-Ended Embodied Agent via Language-Policy Bidirectional Adaptation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fuxian Huang, Jie Wang, Jing Hou, Ming Zhou, Qi Zhang, Shaopeng Zhai, Tianyi Zhang, Yu Liu, Yu Qiao","submitted_at":"2023-12-12T11:06:07Z","abstract_excerpt":"Building embodied agents on integrating Large Language Models (LLMs) and Reinforcement Learning (RL) have revolutionized human-AI interaction: researchers can now leverage language instructions to plan decision-making for open-ended tasks. However, existing research faces challenges in meeting the requirement of open-endedness. They typically either train LLM/RL models to adapt to a fixed counterpart, limiting exploration of novel skills and hindering the efficacy of human-AI interaction. To this end, we present OpenPAL, a co-training framework comprising two stages: (1) fine-tuning a pre-trai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00006","kind":"arxiv","version":3},"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/2401.00006/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2401.00006","created_at":"2026-07-05T07:41:46.530226+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.00006v3","created_at":"2026-07-05T07:41:46.530226+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00006","created_at":"2026-07-05T07:41:46.530226+00:00"},{"alias_kind":"pith_short_12","alias_value":"IMTWFGXJJ4GJ","created_at":"2026-07-05T07:41:46.530226+00:00"},{"alias_kind":"pith_short_16","alias_value":"IMTWFGXJJ4GJ6NLF","created_at":"2026-07-05T07:41:46.530226+00:00"},{"alias_kind":"pith_short_8","alias_value":"IMTWFGXJ","created_at":"2026-07-05T07:41:46.530226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.13410","citing_title":"A Survey On Enhancing Reinforcement Learning in Complex Environments: Insights from Human and LLM Feedback","ref_index":59,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IMTWFGXJJ4GJ6NLFK7GQGIPEXV","json":"https://pith.science/pith/IMTWFGXJJ4GJ6NLFK7GQGIPEXV.json","graph_json":"https://pith.science/api/pith-number/IMTWFGXJJ4GJ6NLFK7GQGIPEXV/graph.json","events_json":"https://pith.science/api/pith-number/IMTWFGXJJ4GJ6NLFK7GQGIPEXV/events.json","paper":"https://pith.science/paper/IMTWFGXJ"},"agent_actions":{"view_html":"https://pith.science/pith/IMTWFGXJJ4GJ6NLFK7GQGIPEXV","download_json":"https://pith.science/pith/IMTWFGXJJ4GJ6NLFK7GQGIPEXV.json","view_paper":"https://pith.science/paper/IMTWFGXJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.00006&json=true","fetch_graph":"https://pith.science/api/pith-number/IMTWFGXJJ4GJ6NLFK7GQGIPEXV/graph.json","fetch_events":"https://pith.science/api/pith-number/IMTWFGXJJ4GJ6NLFK7GQGIPEXV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IMTWFGXJJ4GJ6NLFK7GQGIPEXV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IMTWFGXJJ4GJ6NLFK7GQGIPEXV/action/storage_attestation","attest_author":"https://pith.science/pith/IMTWFGXJJ4GJ6NLFK7GQGIPEXV/action/author_attestation","sign_citation":"https://pith.science/pith/IMTWFGXJJ4GJ6NLFK7GQGIPEXV/action/citation_signature","submit_replication":"https://pith.science/pith/IMTWFGXJJ4GJ6NLFK7GQGIPEXV/action/replication_record"}},"created_at":"2026-07-05T07:41:46.530226+00:00","updated_at":"2026-07-05T07:41:46.530226+00:00"}