{"paper":{"title":"Work Agents: Systems, Capabilities, and Optimization","arxiv_id":"2610.35845","primary_cat":"cs.LG","submitted_at":"2026-10-26T17:56:21+00:00","version_compiled":"v1"},"notice":"Every quoted sentence is the authors' text from the arXiv listing abstract. Labels and probabilities are the outputs of classifier-1.13.0 on the question bank abstract-p1-20260923, exactly as returned. No sentence in this record was written by a language model.","schema":"pith.compiled-record/v0","status":"compiled","abstract":{"source":"arXiv listing abstract v1","sentences":[{"i":0,"p":1.0,"id":"s0","own":false,"role":"background","text":"As foundation models evolve from information generation to digital work execution, agents are increasingly capable of completing complex tasks across tools, applications, and workflows.","hedge":{"p":0.94,"label":"asserted"},"own_p":0.06,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.11,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":1.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":1.0,"id":"s1","own":false,"role":"gap","text":"However, existing research lacks a unified perspective on how agents reliably accomplish delegated work.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.08,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.08,"role_probabilities":{"gap":1.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":1.0,"id":"s2","own":true,"role":"contribution","text":"To address this gap, we present a work-centric, system-level perspective that views work agents as systems combining foundation models and runtime harnesses to execute tasks in stateful workspaces and deliver verifiable outcomes.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.88,"main_claim_p":0.15,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":1.0,"interpretation":0.0}},{"i":3,"p":0.96,"id":"s3","own":true,"role":"contribution","text":"We introduce two complementary dimensions, work persistence and work openness, to characterize working conditions, and classify digital work into five forms according to task scope and organization.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.94,"main_claim_p":0.04,"quantitative":true,"quantitative_p":0.94,"role_probabilities":{"gap":0.0,"method":0.04,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.96,"interpretation":0.0}},{"i":4,"p":0.99,"id":"s4","own":true,"role":"contribution","text":"Building on this framework, we identify five core capability families required for reliable work execution and examine approaches to model optimization, harness optimization, and their joint optimization.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.87,"main_claim_p":0.06,"quantitative":true,"quantitative_p":0.91,"role_probabilities":{"gap":0.0,"method":0.01,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.99,"interpretation":0.0}},{"i":5,"p":0.95,"id":"s5","own":true,"role":"contribution","text":"We further analyze existing evaluation methods and metrics from the perspective of work outcomes.","hedge":{"p":0.92,"label":"asserted"},"own_p":0.6,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.0,"method":0.05,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.95,"interpretation":0.0}},{"i":6,"p":1.0,"id":"s6","own":false,"role":"future_work","text":"Finally, we discuss future research directions, including sustained work delegation, adaptation to open environments, and the interaction between work execution and capability improvement.","hedge":{"p":0.53,"label":"asserted"},"own_p":0.4,"main_claim_p":0.05,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":1.0,"contribution":0.0,"interpretation":0.0}},{"i":7,"p":0.9,"id":"s7","own":true,"role":"contribution","text":"This paper provides a unified framework for understanding, optimizing, and evaluating work agents, supporting the development of systems capable of delivering reliable, verifiable, and practically valuable work outcomes.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.81,"main_claim_p":0.92,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.9,"interpretation":0.1}}]},"compiled":{"main_claim":{"p":1.0,"text":"This paper provides a unified framework for understanding, optimizing, and evaluating work agents, supporting the development of systems capable of delivering reliable, verifiable, and practically valuable work outcomes.","location":"abstract s7","hedge_strength":{"p":0.99,"label":"asserted"}},"provenance":{"route":{"via":"TypeSafe API","model":"classifier-1.13.0","endpoint":"https://api.typesafe.ai/v1/systemone","provider":"TypeSafe"},"packing":"one request per paper","requests":1,"input_tokens":6206,"cost_usd_reported":0.0},"compiled_at":"2026-10-27","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.13,"states_limitation":0.1,"human_participants":0.05,"controlled_comparison":0.02,"randomized_assignment":0.01,"states_quantitative_result":0.37,"compares_with_prior_results":0.13,"mentions_code_or_data_availability":0.02},"evidential_basis":{"p":0.68,"value":"argument","probabilities":{"argument":0.68,"literature":0.32,"proof_or_derivation":0.0,"analysis_of_existing_data":0.0,"observation_or_experiment":0.0,"simulation_or_computation":0.0}},"contribution_type":{"p":0.52,"value":"position or commentary","probabilities":{"review":0.39,"method_or_tool":0.07,"empirical_study":0.0,"simulation_study":0.0,"theoretical_result":0.02,"dataset_or_benchmark":0.0,"position_or_commentary":0.52}},"contribution_statement":{"p":0.81,"text":"To address this gap, we present a work-centric, system-level perspective that views work agents as systems combining foundation models and runtime harnesses to execute tasks in stateful workspaces and deliver verifiable outcomes.","location":"abstract s2"}},"coverage":{"tier":"abstract","levels_run":["P abstract"],"not_examined":["full text","figures and tables","references and citing sentences","relations to other papers"],"sources_read":["arXiv listing abstract v1"],"levels_not_run":["S sections","T body sentences","C citations","R cross-paper relations"],"sentences_examined":8,"sentences_in_abstract":8},"measured_accuracy":{"url":"https://pith.science/accuracy","measured_on":"2026-10-02","method":"two independent model families labelled a fresh random sample blind; the figure is how often the published label matches their consensus","sentence_role_agreement":0.92,"main_claim_agreement":0.908,"typed_citation_agreement":0.933,"typed_citation_agreement_95_interval":[0.917,0.945],"review_comments_accurate":0.758,"review_comments_accurate_95_interval":[0.684,0.82],"review_caught_admitted_error_found_or_related":0.448,"review_comments_judged":{"judged_by":["gpt-5.6-luna","grok-4.7"],"judged_against":"Pith's own text copy of each paper: text extracted from the PDF, the first 90,000 characters","measured_on":"2026-10-04","accurate":113,"decided":149,"sampled_reviews":200,"split_by_lane":false,"by_lane":"https://pith.science/accuracy#by-lane"}}}