{"paper":{"title":"DuplexAgent-RSI: Recursive Harness Improvement for Full-Duplex Voice Agent Collaboration","arxiv_id":"2610.11299","primary_cat":"cs.AI","submitted_at":"2026-10-08T06:06:42+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":"Voice agents are converging on a collaboration pattern: a full-duplex interaction model stays on the live channel as the entry to the conversation, while search, reasoning, and coding are handled through asynchronous delegation.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.06,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.05,"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":0.91,"id":"s1","own":false,"role":"background","text":"A duplex model supports continuous listening and speaking, but complex reasoning and tool use may exceed its capabilities.","hedge":{"p":0.91,"label":"hedged_possibility"},"own_p":0.08,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.09,"role_probabilities":{"gap":0.07,"method":0.0,"result":0.0,"background":0.91,"limitation":0.02,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":0.93,"id":"s2","own":false,"role":"background","text":"A coding agent can plan and execute extended tasks, but its sequential interface is a poor fit for live conversation.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.08,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.19,"role_probabilities":{"gap":0.04,"method":0.0,"result":0.0,"background":0.93,"limitation":0.02,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":3,"p":0.7,"id":"s3","own":false,"role":"background","text":"Combining them requires a harness that coordinates task acceptance, progress, cancellation, replacement, and result delivery while keeping the conversation responsive.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.07,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.3,"method":0.0,"result":0.0,"background":0.7,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":4,"p":0.77,"id":"s4","own":false,"role":"gap","text":"Existing harnesses often rely on coupled heuristics, making them difficult to improve systematically from evidence.","hedge":{"p":0.94,"label":"asserted"},"own_p":0.07,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.77,"method":0.0,"result":0.0,"background":0.23,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":5,"p":0.99,"id":"s5","own":true,"role":"contribution","text":"We present DuplexAgent, a full-duplex collaboration system whose harness expresses this workflow as six editable modules, and Duplex-Harness-RSI, a closed loop that revises them from interaction traces.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.94,"main_claim_p":0.15,"quantitative":true,"quantitative_p":0.62,"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":6,"p":0.99,"id":"s6","own":true,"role":"method","text":"A simulator automatically generates timed test conversations, runs the system, and produces failure traces that identify the collaboration modules requiring repair.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.83,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.0,"method":0.99,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.01,"interpretation":0.0}},{"i":7,"p":0.96,"id":"s7","own":true,"role":"method","text":"Reasoning LLMs and coding agents in the delegation pool also serve the improvement loop: the Exam Planner selects the next tests from observed weaknesses and the repair archive, and the Harness Editor proposes targeted module changes.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.82,"main_claim_p":0.05,"quantitative":false,"quantitative_p":0.08,"role_probabilities":{"gap":0.0,"method":0.96,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.04,"interpretation":0.0}},{"i":8,"p":0.96,"id":"s8","own":false,"role":"interpretation","text":"The capabilities that serve the user thus also improve the system's coordination.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.42,"main_claim_p":0.09,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.01,"result":0.01,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.02,"interpretation":0.96}},{"i":9,"p":1.0,"id":"s9","own":true,"role":"result","text":"Experiments on intelligence, agentic, and duplex benchmarks show that DuplexAgent combines continuous interaction with difficult reasoning and complex task execution, achieving stronger spoken-knowledge and executable-tool scores than the compared delegated systems while maintaining strong interruption response.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.96,"main_claim_p":0.79,"quantitative":true,"quantitative_p":0.95,"role_probabilities":{"gap":0.0,"method":0.0,"result":1.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":10,"p":1.0,"id":"s10","own":true,"role":"result","text":"A harness ablation further shows that this modular, verifiable loop outperforms the initial harness and repeated editing that lacks its diagnosis and repair archive.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.96,"main_claim_p":0.16,"quantitative":true,"quantitative_p":0.91,"role_probabilities":{"gap":0.0,"method":0.0,"result":1.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}}]},"compiled":{"main_claim":{"p":1.0,"text":"Experiments on intelligence, agentic, and duplex benchmarks show that DuplexAgent combines continuous interaction with difficult reasoning and complex task execution, achieving stronger spoken-knowledge and executable-tool scores than the compared delegated systems while maintaining strong interruption response.","location":"abstract s9","hedge_strength":{"p":1.0,"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":8259,"cost_usd_reported":0.0},"compiled_at":"2026-10-09","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.07,"states_limitation":0.15,"human_participants":0.08,"controlled_comparison":0.89,"randomized_assignment":0.02,"states_quantitative_result":0.07,"compares_with_prior_results":0.96,"mentions_code_or_data_availability":0.04},"evidential_basis":{"p":0.97,"value":"observation or experiment","probabilities":{"argument":0.0,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.0,"observation_or_experiment":0.97,"simulation_or_computation":0.03}},"contribution_type":{"p":1.0,"value":"method or tool","probabilities":{"review":0.0,"method_or_tool":1.0,"empirical_study":0.0,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.0,"position_or_commentary":0.0}},"contribution_statement":{"p":1.0,"text":"We present DuplexAgent, a full-duplex collaboration system whose harness expresses this workflow as six editable modules, and Duplex-Harness-RSI, a closed loop that revises them from interaction traces.","location":"abstract s5"}},"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":11,"sentences_in_abstract":11},"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"}}}