{"paper":{"title":"Knowing What is Missing: Efficient Conversational Memory via Explicit Evidence-Gap Tracking","arxiv_id":"2512.20237","primary_cat":"cs.AI","submitted_at":"2025-12-23T10:49:42+00:00","version_compiled":"v2"},"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 v2","sentences":[{"i":0,"p":0.99,"id":"s0","own":false,"role":"background","text":"Long-term conversational memory poses a fundamental system challenge for LLM agents: reasoning over all past interactions improves coverage but incurs prohibitive token costs and noise, while retrieval-based methods are efficient yet often fail on multi-hop and temporal questions.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.06,"main_claim_p":0.03,"quantitative":true,"quantitative_p":0.67,"role_probabilities":{"gap":0.01,"method":0.0,"result":0.0,"background":0.99,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.8,"id":"s1","own":false,"role":"background","text":"Existing multi-step retrievers partially address this gap, but typically operate over an ever-growing textual history, causing context expansion and noise accumulation across iterations.","hedge":{"p":0.97,"label":"asserted"},"own_p":0.03,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.13,"role_probabilities":{"gap":0.18,"method":0.0,"result":0.0,"background":0.8,"limitation":0.02,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":0.93,"id":"s2","own":true,"role":"contribution","text":"We propose MemR$^3$, a backend-agnostic closed-loop controller that reformulates conversational memory retrieval as explicit stateful decision-making.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.86,"main_claim_p":0.07,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.07,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.93,"interpretation":0.0}},{"i":3,"p":0.98,"id":"s3","own":true,"role":"method","text":"At each iteration, MemR$^3$ maintains an evidence-gap state consisting of grounded information (evidence) and unresolved information requirements (gaps), and uses this state to route among three actions: retrieve, reflect, and answer.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.85,"main_claim_p":0.05,"quantitative":false,"quantitative_p":0.45,"role_probabilities":{"gap":0.0,"method":0.98,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.02,"interpretation":0.0}},{"i":4,"p":0.99,"id":"s4","own":true,"role":"method","text":"Newly retrieved snippets are incorporated into the state and then masked from subsequent prompts, so the model conditions on a compact summary of progress rather than the full retrieval history.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.84,"main_claim_p":0.05,"quantitative":false,"quantitative_p":0.11,"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":5,"p":0.64,"id":"s5","own":true,"role":"method","text":"This design turns multi-step memory retrieval into a bounded, inspectable control process whose query-time context scales with the state instead of raw accumulated text.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.71,"main_claim_p":0.14,"quantitative":true,"quantitative_p":0.66,"role_probabilities":{"gap":0.0,"method":0.64,"result":0.01,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.22,"interpretation":0.13}},{"i":6,"p":1.0,"id":"s6","own":true,"role":"result","text":"Experiments on LongMemEval$_s$ show that MemR$^3$ surpasses implicit multi-step retrieval baselines and often approaches or exceeds full-context prompting while retrieving only 1%-5% of the full conversation tokens on long conversations.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.96,"main_claim_p":0.22,"quantitative":true,"quantitative_p":0.99,"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":7,"p":1.0,"id":"s7","own":true,"role":"result","text":"On LoCoMo, MemR$^3$ consistently improves over its underlying RAG- and Zep-based memory backbones.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.94,"main_claim_p":0.08,"quantitative":true,"quantitative_p":0.87,"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":8,"p":1.0,"id":"s8","own":true,"role":"interpretation","text":"These results suggest that explicit evidence-gap tracking is an effective abstraction for token-efficient conversational memory.","hedge":{"p":1.0,"label":"hedged_possibility"},"own_p":0.69,"main_claim_p":0.88,"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":0.0,"interpretation":1.0}}]},"compiled":{"main_claim":{"p":1.0,"text":"These results suggest that explicit evidence-gap tracking is an effective abstraction for token-efficient conversational memory.","location":"abstract s8","hedge_strength":{"p":1.0,"label":"hedged possibility"}},"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":7076,"cost_usd_reported":0.0},"compiled_at":"2026-11-10","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.06,"states_limitation":0.1,"human_participants":0.05,"controlled_comparison":0.93,"randomized_assignment":0.01,"states_quantitative_result":0.98,"compares_with_prior_results":0.98,"mentions_code_or_data_availability":0.03},"evidential_basis":{"p":1.0,"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":1.0,"simulation_or_computation":0.0}},"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":0.99,"text":"We propose MemR$^3$, a backend-agnostic closed-loop controller that reformulates conversational memory retrieval as explicit stateful decision-making.","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 v2"],"levels_not_run":["S sections","T body sentences","C citations","R cross-paper relations"],"sentences_examined":9,"sentences_in_abstract":9},"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"}}}