{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AL4EH5SDLY6V5RB3EVIF4O7PJZ","short_pith_number":"pith:AL4EH5SD","schema_version":"1.0","canonical_sha256":"02f843f6435e3d5ec43b25505e3bef4e7852891a07fb7e52d1ba316173ed9665","source":{"kind":"arxiv","id":"2606.27483","version":1},"attestation_state":"computed","paper":{"title":"Internalizing the Future: A Unified Agentic Training Paradigm for World Model Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chao Qu, Ke Li, Lingfeng Qiao, Xiaoyu Tan, Xing Sun, Xuan Zhang, Yuan Qi, Yulei Qin, Zhijian Zhou","submitted_at":"2026-06-25T19:05:44Z","abstract_excerpt":"Large language model (LLM) agents have demonstrated strong capability in sequential decision-making, yet they remains fundamentally reactive in long-horizon tasks. Unlike humans who employ \"what-if\" reasoning to evaluate potential plans before commitment, standard agents lack an internal world model to simulate future outcomes. Therefore, we propose to internalize future-aware planning by training a single autoregressive model to verbalize both a prospective state rollout and a plan-conditioned success estimate-a textual analogue of the Q-value. Crucially, we identify a format-capability gap: "},"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":"2606.27483","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-25T19:05:44Z","cross_cats_sorted":[],"title_canon_sha256":"9d86e7150567ac7907de11754ee510b550b2dc8050f6b467203a01bb72d41a1a","abstract_canon_sha256":"77d7385786b7b57be2aa9afab99929604a0db01da7913fb98ef0981c24512b38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T00:14:07.904269Z","signature_b64":"GeJv2ToxEUzNpo0XkPzBC7c3yjAQT+TufhBECpXD2y9we6LPP32MtNRUbl0C5FIsKYk1vXPkHrxjZSIUZqs/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02f843f6435e3d5ec43b25505e3bef4e7852891a07fb7e52d1ba316173ed9665","last_reissued_at":"2026-06-29T00:14:07.903886Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T00:14:07.903886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Internalizing the Future: A Unified Agentic Training Paradigm for World Model Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chao Qu, Ke Li, Lingfeng Qiao, Xiaoyu Tan, Xing Sun, Xuan Zhang, Yuan Qi, Yulei Qin, Zhijian Zhou","submitted_at":"2026-06-25T19:05:44Z","abstract_excerpt":"Large language model (LLM) agents have demonstrated strong capability in sequential decision-making, yet they remains fundamentally reactive in long-horizon tasks. Unlike humans who employ \"what-if\" reasoning to evaluate potential plans before commitment, standard agents lack an internal world model to simulate future outcomes. Therefore, we propose to internalize future-aware planning by training a single autoregressive model to verbalize both a prospective state rollout and a plan-conditioned success estimate-a textual analogue of the Q-value. Crucially, we identify a format-capability gap: "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27483","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/2606.27483/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":"2606.27483","created_at":"2026-06-29T00:14:07.903948+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.27483v1","created_at":"2026-06-29T00:14:07.903948+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27483","created_at":"2026-06-29T00:14:07.903948+00:00"},{"alias_kind":"pith_short_12","alias_value":"AL4EH5SDLY6V","created_at":"2026-06-29T00:14:07.903948+00:00"},{"alias_kind":"pith_short_16","alias_value":"AL4EH5SDLY6V5RB3","created_at":"2026-06-29T00:14:07.903948+00:00"},{"alias_kind":"pith_short_8","alias_value":"AL4EH5SD","created_at":"2026-06-29T00:14:07.903948+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AL4EH5SDLY6V5RB3EVIF4O7PJZ","json":"https://pith.science/pith/AL4EH5SDLY6V5RB3EVIF4O7PJZ.json","graph_json":"https://pith.science/api/pith-number/AL4EH5SDLY6V5RB3EVIF4O7PJZ/graph.json","events_json":"https://pith.science/api/pith-number/AL4EH5SDLY6V5RB3EVIF4O7PJZ/events.json","paper":"https://pith.science/paper/AL4EH5SD"},"agent_actions":{"view_html":"https://pith.science/pith/AL4EH5SDLY6V5RB3EVIF4O7PJZ","download_json":"https://pith.science/pith/AL4EH5SDLY6V5RB3EVIF4O7PJZ.json","view_paper":"https://pith.science/paper/AL4EH5SD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.27483&json=true","fetch_graph":"https://pith.science/api/pith-number/AL4EH5SDLY6V5RB3EVIF4O7PJZ/graph.json","fetch_events":"https://pith.science/api/pith-number/AL4EH5SDLY6V5RB3EVIF4O7PJZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AL4EH5SDLY6V5RB3EVIF4O7PJZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AL4EH5SDLY6V5RB3EVIF4O7PJZ/action/storage_attestation","attest_author":"https://pith.science/pith/AL4EH5SDLY6V5RB3EVIF4O7PJZ/action/author_attestation","sign_citation":"https://pith.science/pith/AL4EH5SDLY6V5RB3EVIF4O7PJZ/action/citation_signature","submit_replication":"https://pith.science/pith/AL4EH5SDLY6V5RB3EVIF4O7PJZ/action/replication_record"}},"created_at":"2026-06-29T00:14:07.903948+00:00","updated_at":"2026-06-29T00:14:07.903948+00:00"}