{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BQ3KTSURDRPAGR64X2VXHWRIJ2","short_pith_number":"pith:BQ3KTSUR","schema_version":"1.0","canonical_sha256":"0c36a9ca911c5e0347dcbeab73da284ea8a5ac3d112ef55ee1cc2ba1ea3903c5","source":{"kind":"arxiv","id":"2410.12361","version":3},"attestation_state":"computed","paper":{"title":"Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Cheng Qian, Fangming Liu, Guirong Chen, Huadong Wang, Maosong Sun, Qinyu Luo, Shenzhi Yang, Weiwen Liu, Xin Cong, Yankai Lin, Yasheng Wang, Yaxi Lu, Yesai Wu, Zhiyuan Liu, Zhong Zhang","submitted_at":"2024-10-16T08:24:09Z","abstract_excerpt":"Agents powered by large language models have shown remarkable abilities in solving complex tasks. However, most agent systems remain reactive, limiting their effectiveness in scenarios requiring foresight and autonomous decision-making. In this paper, we tackle the challenge of developing proactive agents capable of anticipating and initiating tasks without explicit human instructions. We propose a novel data-driven approach for this problem. Firstly, we collect real-world human activities to generate proactive task predictions. These predictions are then labeled by human annotators as either "},"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":"2410.12361","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-16T08:24:09Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f9192a42c0e408ee9615a8d9538800571aaa6f9b2d7448e9780f2946494bc9d6","abstract_canon_sha256":"81094267099289a545567173a73823739f2344284a701e44a962e0163f65d143"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:35.322344Z","signature_b64":"MDcph9LXeH225faX+hZmzeQUx4X6QBMYj10h+amx/3z2QFZ3ukjsnpoq1N1N5tySSflfHkeXI2xLMbgOWZKyBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c36a9ca911c5e0347dcbeab73da284ea8a5ac3d112ef55ee1cc2ba1ea3903c5","last_reissued_at":"2026-07-05T09:43:35.321770Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:35.321770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Cheng Qian, Fangming Liu, Guirong Chen, Huadong Wang, Maosong Sun, Qinyu Luo, Shenzhi Yang, Weiwen Liu, Xin Cong, Yankai Lin, Yasheng Wang, Yaxi Lu, Yesai Wu, Zhiyuan Liu, Zhong Zhang","submitted_at":"2024-10-16T08:24:09Z","abstract_excerpt":"Agents powered by large language models have shown remarkable abilities in solving complex tasks. However, most agent systems remain reactive, limiting their effectiveness in scenarios requiring foresight and autonomous decision-making. In this paper, we tackle the challenge of developing proactive agents capable of anticipating and initiating tasks without explicit human instructions. We propose a novel data-driven approach for this problem. Firstly, we collect real-world human activities to generate proactive task predictions. These predictions are then labeled by human annotators as either "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12361","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/2410.12361/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":"2410.12361","created_at":"2026-07-05T09:43:35.321843+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.12361v3","created_at":"2026-07-05T09:43:35.321843+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12361","created_at":"2026-07-05T09:43:35.321843+00:00"},{"alias_kind":"pith_short_12","alias_value":"BQ3KTSURDRPA","created_at":"2026-07-05T09:43:35.321843+00:00"},{"alias_kind":"pith_short_16","alias_value":"BQ3KTSURDRPAGR64","created_at":"2026-07-05T09:43:35.321843+00:00"},{"alias_kind":"pith_short_8","alias_value":"BQ3KTSUR","created_at":"2026-07-05T09:43:35.321843+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17929","citing_title":"PreAct: Computer-Using Agents that Get Faster on Repeated Tasks","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25971","citing_title":"Anticipate and Learn: Unleashing Idle-Time Compute in Proactive Agents","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2508.18167","citing_title":"DiscussLLM: Teaching Large Language Models When to Speak","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2512.06721","citing_title":"ProAgent: Harnessing On-Demand Sensory Contexts for Proactive LLM Agent Systems in the Wild","ref_index":38,"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":21,"is_internal_anchor":false},{"citing_arxiv_id":"2602.21858","citing_title":"ProactiveMobile: A Comprehensive Benchmark for Boosting Proactive Intelligence on Mobile Devices","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24348","citing_title":"OS-SPEAR: A Toolkit for the Safety, Performance,Efficiency, and Robustness Analysis of OS Agents","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05700","citing_title":"An Empirical Study of Proactive Coding Assistants in Real-World Software Development","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00497","citing_title":"\"What Are You Really Trying to Do?\": Co-Creating Life Goals from Everyday Computer Use","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18171","citing_title":"Alleviating Linguistic and Interactional Anxiety of Non-Native Speakers in Multilingual Communication","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18133","citing_title":"Multi-Agent Systems: From Classical Paradigms to Large Foundation Model-Enabled Futures","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11067","citing_title":"Contexty: Capturing and Organizing In-situ Thoughts for Context-Aware AI Support","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07645","citing_title":"PRIME: Training Free Proactive Reasoning via Iterative Memory Evolution for User-Centric Agent","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08000","citing_title":"PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06717","citing_title":"Agentic Coding Needs Proactivity, Not Just Autonomy","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15037","citing_title":"From Reactive to Proactive: Assessing the Proactivity of Voice Agents via ProVoice-Bench","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BQ3KTSURDRPAGR64X2VXHWRIJ2","json":"https://pith.science/pith/BQ3KTSURDRPAGR64X2VXHWRIJ2.json","graph_json":"https://pith.science/api/pith-number/BQ3KTSURDRPAGR64X2VXHWRIJ2/graph.json","events_json":"https://pith.science/api/pith-number/BQ3KTSURDRPAGR64X2VXHWRIJ2/events.json","paper":"https://pith.science/paper/BQ3KTSUR"},"agent_actions":{"view_html":"https://pith.science/pith/BQ3KTSURDRPAGR64X2VXHWRIJ2","download_json":"https://pith.science/pith/BQ3KTSURDRPAGR64X2VXHWRIJ2.json","view_paper":"https://pith.science/paper/BQ3KTSUR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.12361&json=true","fetch_graph":"https://pith.science/api/pith-number/BQ3KTSURDRPAGR64X2VXHWRIJ2/graph.json","fetch_events":"https://pith.science/api/pith-number/BQ3KTSURDRPAGR64X2VXHWRIJ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BQ3KTSURDRPAGR64X2VXHWRIJ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BQ3KTSURDRPAGR64X2VXHWRIJ2/action/storage_attestation","attest_author":"https://pith.science/pith/BQ3KTSURDRPAGR64X2VXHWRIJ2/action/author_attestation","sign_citation":"https://pith.science/pith/BQ3KTSURDRPAGR64X2VXHWRIJ2/action/citation_signature","submit_replication":"https://pith.science/pith/BQ3KTSURDRPAGR64X2VXHWRIJ2/action/replication_record"}},"created_at":"2026-07-05T09:43:35.321843+00:00","updated_at":"2026-07-05T09:43:35.321843+00:00"}