{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4LZHQ3BONJLE3BHVEIAV3HOWGV","short_pith_number":"pith:4LZHQ3BO","schema_version":"1.0","canonical_sha256":"e2f2786c2e6a564d84f522015d9dd6356e76e033219db38a1fee45518956e92a","source":{"kind":"arxiv","id":"2601.08173","version":2},"attestation_state":"computed","paper":{"title":"The Agent's First Day: Benchmarking Learning, Exploration, and Scheduling in the Workplace Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Botian Shi, Daocheng Fu, Ding Wang, Jianbiao Mei, Jia Xu, Licheng Wen, Pinlong Cai, Rong Wu, Xuemeng Yang, Yong Liu","submitted_at":"2026-01-13T03:09:18Z","abstract_excerpt":"The rapid evolution of Multi-modal Large Language Models (MLLMs) has advanced workflow automation; however, existing research mainly targets performance upper bounds in static environments, overlooking robustness for stochastic real-world deployment. We identify three key challenges: dynamic task scheduling, active exploration under uncertainty, and continuous learning from experience. To bridge this gap, we introduce \\method{}, a dynamic evaluation environment that simulates a \"trainee\" agent continuously exploring a novel setting. Unlike traditional benchmarks, \\method{} evaluates agents alo"},"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":"2601.08173","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-01-13T03:09:18Z","cross_cats_sorted":[],"title_canon_sha256":"45cbae0e37eb8ec70d9c2397c11f1e4a38cf60b6d7f01191e5fd639fdbf12afb","abstract_canon_sha256":"dabf9a0cbd92122eea6835acbacc2e97a954c30ab8ac9dbf3beadeb574a997ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:47.644511Z","signature_b64":"nvAdLmZ9xQJatp3cabZXdvliHxjMOj0nHAwxR2a/EkT4NexpzVrm6o5mrKX0Dq50mroHFBqaqU/ZQpyvXTZRAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2f2786c2e6a564d84f522015d9dd6356e76e033219db38a1fee45518956e92a","last_reissued_at":"2026-06-03T01:05:47.644038Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:47.644038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Agent's First Day: Benchmarking Learning, Exploration, and Scheduling in the Workplace Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Botian Shi, Daocheng Fu, Ding Wang, Jianbiao Mei, Jia Xu, Licheng Wen, Pinlong Cai, Rong Wu, Xuemeng Yang, Yong Liu","submitted_at":"2026-01-13T03:09:18Z","abstract_excerpt":"The rapid evolution of Multi-modal Large Language Models (MLLMs) has advanced workflow automation; however, existing research mainly targets performance upper bounds in static environments, overlooking robustness for stochastic real-world deployment. We identify three key challenges: dynamic task scheduling, active exploration under uncertainty, and continuous learning from experience. To bridge this gap, we introduce \\method{}, a dynamic evaluation environment that simulates a \"trainee\" agent continuously exploring a novel setting. Unlike traditional benchmarks, \\method{} evaluates agents alo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.08173","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/2601.08173/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":"2601.08173","created_at":"2026-06-03T01:05:47.644096+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.08173v2","created_at":"2026-06-03T01:05:47.644096+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.08173","created_at":"2026-06-03T01:05:47.644096+00:00"},{"alias_kind":"pith_short_12","alias_value":"4LZHQ3BONJLE","created_at":"2026-06-03T01:05:47.644096+00:00"},{"alias_kind":"pith_short_16","alias_value":"4LZHQ3BONJLE3BHV","created_at":"2026-06-03T01:05:47.644096+00:00"},{"alias_kind":"pith_short_8","alias_value":"4LZHQ3BO","created_at":"2026-06-03T01:05:47.644096+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/4LZHQ3BONJLE3BHVEIAV3HOWGV","json":"https://pith.science/pith/4LZHQ3BONJLE3BHVEIAV3HOWGV.json","graph_json":"https://pith.science/api/pith-number/4LZHQ3BONJLE3BHVEIAV3HOWGV/graph.json","events_json":"https://pith.science/api/pith-number/4LZHQ3BONJLE3BHVEIAV3HOWGV/events.json","paper":"https://pith.science/paper/4LZHQ3BO"},"agent_actions":{"view_html":"https://pith.science/pith/4LZHQ3BONJLE3BHVEIAV3HOWGV","download_json":"https://pith.science/pith/4LZHQ3BONJLE3BHVEIAV3HOWGV.json","view_paper":"https://pith.science/paper/4LZHQ3BO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.08173&json=true","fetch_graph":"https://pith.science/api/pith-number/4LZHQ3BONJLE3BHVEIAV3HOWGV/graph.json","fetch_events":"https://pith.science/api/pith-number/4LZHQ3BONJLE3BHVEIAV3HOWGV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4LZHQ3BONJLE3BHVEIAV3HOWGV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4LZHQ3BONJLE3BHVEIAV3HOWGV/action/storage_attestation","attest_author":"https://pith.science/pith/4LZHQ3BONJLE3BHVEIAV3HOWGV/action/author_attestation","sign_citation":"https://pith.science/pith/4LZHQ3BONJLE3BHVEIAV3HOWGV/action/citation_signature","submit_replication":"https://pith.science/pith/4LZHQ3BONJLE3BHVEIAV3HOWGV/action/replication_record"}},"created_at":"2026-06-03T01:05:47.644096+00:00","updated_at":"2026-06-03T01:05:47.644096+00:00"}