{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:T6Q27LRIBE3XCCEBEJFI74RTT4","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":"2a168690c78dfe07b88973493558119fd2f0865dbabc19777c7e1122cd4b6b1b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-02-03T06:06:27Z","title_canon_sha256":"e3fd620c9334ea0d3878e7ba3848de41d55fa299f2e33aaf50240dc0098199f3"},"schema_version":"1.0","source":{"id":"2302.01560","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.01560","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"arxiv_version","alias_value":"2302.01560v3","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.01560","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"pith_short_12","alias_value":"T6Q27LRIBE3X","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"T6Q27LRIBE3XCCEB","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"T6Q27LRI","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:5b4cffb1b2d8f7040aaa0bbc48d30f726e0ea1ac93d7f0c84841f2d2562e42f1","target":"graph","created_at":"2026-05-17T23:38:49Z","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":3,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Our experiments mark the milestone of the first zero-shot multi-task agent that can robustly accomplish 70+ Minecraft tasks and nearly double the overall performances."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That large language models can reliably produce accurate descriptions and self-explanations of plan failures without hallucination, and that the trained goal selector generalizes to estimate completion steps across diverse tasks."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"DEPS combines LLM-based interactive planning with a trainable goal selector to create a zero-shot multi-task agent that completes 70+ Minecraft tasks and nearly doubles prior performance."}],"snapshot_sha256":"5468a78e3ef7478e80f22524291f86337e301b2d129c82ec0b06c84469ad86d1"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"We investigate the challenge of task planning for multi-task embodied agents in open-world environments. Two main difficulties are identified: 1) executing plans in an open-world environment (e.g., Minecraft) necessitates accurate and multi-step reasoning due to the long-term nature of tasks, and 2) as vanilla planners do not consider how easy the current agent can achieve a given sub-task when ordering parallel sub-goals within a complicated plan, the resulting plan could be inefficient or even infeasible. To this end, we propose \"$\\underline{D}$escribe, $\\underline{E}$xplain, $\\underline{P}$","authors_text":"Anji Liu, Guanzhou Chen, Shaofei Cai, Xiaojian Ma, Yitao Liang, Zihao Wang","cross_cats":[],"headline":"DEPS combines LLM-based interactive planning with a trainable goal selector to create a zero-shot multi-task agent that completes 70+ Minecraft tasks and nearly doubles prior performance.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-02-03T06:06:27Z","title":"Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents"},"references":{"count":71,"internal_anchors":18,"resolved_work":71,"sample":[{"cited_arxiv_id":"2204.14198","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Flamingo: a Visual Language Model for Few-Shot Learning","work_id":"a110f764-38dc-41b2-a802-53744ecea1fc","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"P.-L. Bacon, J. Harb, and D. Precup. The option-critic architecture. In Proceedings of the AAAI conference on artificial intelligence, 2017. 1","work_id":"95e5f834-6420-4a4e-a0a0-c797157ae93e","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Video pretraining (vpt): Learning to act by watching unlabeled online videos","work_id":"2bf44de9-4b8f-4ab3-816e-2ffb5278c578","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"A. Brohan, Y . Chebotar, C. Finn, K. Hausman, A. Herzog, D. Ho, J. Ibarz, A. Irpan, E. Jang, R. Julian, et al. Do as i can, not as i say: Grounding language in robotic affordances. In 6th Annual Confe","work_id":"970cbc3b-0b27-4b39-b3fc-d86e1bf02280","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"T. Brown, B. Mann, N. Ryder, M. Subbiah, J. D. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell, et al. Language models are few-shot learners. Advances in neural information process","work_id":"bc17df25-2629-4184-aac1-f5bb84bd1856","year":1901}],"snapshot_sha256":"e9dac2d608cc2a91f80f55beaeb0d8f60e6ed49f19f98ad20b562ce4f2a4c63f"},"source":{"id":"2302.01560","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T03:20:17.333742Z","id":"cd7dafa9-292a-4bbe-82b3-f81a11658453","model_set":{"reader":"grok-4.3"},"one_line_summary":"DEPS combines LLM-based interactive planning with a trainable goal selector to create a zero-shot multi-task agent that completes 70+ Minecraft tasks and nearly doubles prior performance.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"","strongest_claim":"Our experiments mark the milestone of the first zero-shot multi-task agent that can robustly accomplish 70+ Minecraft tasks and nearly double the overall performances.","weakest_assumption":"That large language models can reliably produce accurate descriptions and self-explanations of plan failures without hallucination, and that the trained goal selector generalizes to estimate completion steps across diverse tasks."}},"verdict_id":"cd7dafa9-292a-4bbe-82b3-f81a11658453"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:58aad2479cff22d4fd7b0975442c08c294863f14c742878d34228d15d60645b7","target":"record","created_at":"2026-05-17T23:38:49Z","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":"2a168690c78dfe07b88973493558119fd2f0865dbabc19777c7e1122cd4b6b1b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-02-03T06:06:27Z","title_canon_sha256":"e3fd620c9334ea0d3878e7ba3848de41d55fa299f2e33aaf50240dc0098199f3"},"schema_version":"1.0","source":{"id":"2302.01560","kind":"arxiv","version":3}},"canonical_sha256":"9fa1afae280937710881224a8ff2339f02ae0972ba6e947650ad90e9c71f5898","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9fa1afae280937710881224a8ff2339f02ae0972ba6e947650ad90e9c71f5898","first_computed_at":"2026-05-17T23:38:49.267167Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:49.267167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XaWcvTqaEn8DrQOOq1M9lPaDNouTmK8AYG1OhVU9k3bcIhewMVkwRfTp0svJzT2gHvVvuEaM+R7xg269EKvLBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:49.267639Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.01560","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:58aad2479cff22d4fd7b0975442c08c294863f14c742878d34228d15d60645b7","sha256:5b4cffb1b2d8f7040aaa0bbc48d30f726e0ea1ac93d7f0c84841f2d2562e42f1"],"state_sha256":"a5d64ac87ed1d37913bb5330d15eca1634e0d464c9261fbc8c07621c89ab8abb"}