{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JEDGIX5TYAUK7OKKNQCM4Y5KJB","short_pith_number":"pith:JEDGIX5T","schema_version":"1.0","canonical_sha256":"4906645fb3c028afb94a6c04ce63aa48668d7052ca7740c7bb0041cbb889bf81","source":{"kind":"arxiv","id":"2406.12639","version":2},"attestation_state":"computed","paper":{"title":"Ask-before-Plan: Proactive Language Agents for Real-World Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"See-kiong Ng, Tat-Seng Chua, Xuan Zhang, Yang Deng, Zifeng Ren","submitted_at":"2024-06-18T14:07:28Z","abstract_excerpt":"The evolution of large language models (LLMs) has enhanced the planning capabilities of language agents in diverse real-world scenarios. Despite these advancements, the potential of LLM-powered agents to comprehend ambiguous user instructions for reasoning and decision-making is still under exploration. In this work, we introduce a new task, Proactive Agent Planning, which requires language agents to predict clarification needs based on user-agent conversation and agent-environment interaction, invoke external tools to collect valid information, and generate a plan to fulfill the user's demand"},"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":"2406.12639","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T14:07:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8fb5762ea595572bc58eba97ecfe796e33add9ab100f0206a4ec47be95434f14","abstract_canon_sha256":"f65e717b580d98cf5e55b5bb6111c4feb8d73b59eea00c1fd7710bd288b88763"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:34.749993Z","signature_b64":"+vfjYzG3ESijdRHiu+5EcRmVeANgOGQXysNc2gUf9l9D/Ge1cqAeZEuUo0E2iW0E0HMdouQRnRGtO09dbnFnCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4906645fb3c028afb94a6c04ce63aa48668d7052ca7740c7bb0041cbb889bf81","last_reissued_at":"2026-07-05T09:14:34.749500Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:34.749500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ask-before-Plan: Proactive Language Agents for Real-World Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"See-kiong Ng, Tat-Seng Chua, Xuan Zhang, Yang Deng, Zifeng Ren","submitted_at":"2024-06-18T14:07:28Z","abstract_excerpt":"The evolution of large language models (LLMs) has enhanced the planning capabilities of language agents in diverse real-world scenarios. Despite these advancements, the potential of LLM-powered agents to comprehend ambiguous user instructions for reasoning and decision-making is still under exploration. In this work, we introduce a new task, Proactive Agent Planning, which requires language agents to predict clarification needs based on user-agent conversation and agent-environment interaction, invoke external tools to collect valid information, and generate a plan to fulfill the user's demand"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12639","kind":"arxiv","version":2},"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/2406.12639/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":"2406.12639","created_at":"2026-07-05T09:14:34.749558+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.12639v2","created_at":"2026-07-05T09:14:34.749558+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12639","created_at":"2026-07-05T09:14:34.749558+00:00"},{"alias_kind":"pith_short_12","alias_value":"JEDGIX5TYAUK","created_at":"2026-07-05T09:14:34.749558+00:00"},{"alias_kind":"pith_short_16","alias_value":"JEDGIX5TYAUK7OKK","created_at":"2026-07-05T09:14:34.749558+00:00"},{"alias_kind":"pith_short_8","alias_value":"JEDGIX5T","created_at":"2026-07-05T09:14:34.749558+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.06721","citing_title":"ProAgent: Harnessing On-Demand Sensory Contexts for Proactive LLM Agent Systems in the Wild","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09579","citing_title":"Help Without Being Asked: A Deployed Proactive Agent System for On-Call Support with Continuous Self-Improvement","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16813","citing_title":"PersonalHomeBench: Evaluating Agents in Personalized Smart Homes","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08898","citing_title":"Omakase: proactive assistance with actionable suggestions for evolving scientific research projects","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JEDGIX5TYAUK7OKKNQCM4Y5KJB","json":"https://pith.science/pith/JEDGIX5TYAUK7OKKNQCM4Y5KJB.json","graph_json":"https://pith.science/api/pith-number/JEDGIX5TYAUK7OKKNQCM4Y5KJB/graph.json","events_json":"https://pith.science/api/pith-number/JEDGIX5TYAUK7OKKNQCM4Y5KJB/events.json","paper":"https://pith.science/paper/JEDGIX5T"},"agent_actions":{"view_html":"https://pith.science/pith/JEDGIX5TYAUK7OKKNQCM4Y5KJB","download_json":"https://pith.science/pith/JEDGIX5TYAUK7OKKNQCM4Y5KJB.json","view_paper":"https://pith.science/paper/JEDGIX5T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.12639&json=true","fetch_graph":"https://pith.science/api/pith-number/JEDGIX5TYAUK7OKKNQCM4Y5KJB/graph.json","fetch_events":"https://pith.science/api/pith-number/JEDGIX5TYAUK7OKKNQCM4Y5KJB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JEDGIX5TYAUK7OKKNQCM4Y5KJB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JEDGIX5TYAUK7OKKNQCM4Y5KJB/action/storage_attestation","attest_author":"https://pith.science/pith/JEDGIX5TYAUK7OKKNQCM4Y5KJB/action/author_attestation","sign_citation":"https://pith.science/pith/JEDGIX5TYAUK7OKKNQCM4Y5KJB/action/citation_signature","submit_replication":"https://pith.science/pith/JEDGIX5TYAUK7OKKNQCM4Y5KJB/action/replication_record"}},"created_at":"2026-07-05T09:14:34.749558+00:00","updated_at":"2026-07-05T09:14:34.749558+00:00"}