{"data":{"event":{"id":"c6b34c0e-f102-4cf1-a01e-15da0c10b1dd","slug":"aim-a-privacy-aware-interoperable-memory-framework-for-multi-agent-multi-d47ce9e1ec","title":"AIM: A Privacy-Aware Interoperable Memory Framework for Multi-Agent Multi-User LLM Systems","short_summary":"arXiv:2609.12320v1 Announce Type: new \nAbstract: Traditional large language models (LLMs) are scoped to individual user sessions, limiting their knowledge to a single conversation and preventing them from learning user preferences that evolve over time. Existing agentic memory systems address this limitation but generally operate at the individual-user level, restricting the public knowledge that could be shared across users to improve downstream responses. We introduce AIM (Agentic Interoperable Memory), a unified, privacy-aware memory framework that enables multi-agent, multi-user LLM system","full_description":"arXiv:2609.12320v1 Announce Type: new \nAbstract: Traditional large language models (LLMs) are scoped to individual user sessions, limiting their knowledge to a single conversation and preventing them from learning user preferences that evolve over time. Existing agentic memory systems address this limitation but generally operate at the individual-user level, restricting the public knowledge that could be shared across users to improve downstream responses. We introduce AIM (Agentic Interoperable Memory), a unified, privacy-aware memory framework that enables multi-agent, multi-user LLM systems to persistently manage private and shared memory. AIM dynamically classifies information as private, scoped to one user and inaccessible to others, or public, accessible to all users. It enforces index-level access controls so that private memories are retrievable only by their owner, protecting sensitive data while allowing beneficial shared knowledge to improve coordination and consistency. We also introduce MUMBench (Multi-User Memory Benchmark), a dataset of multi-user interactions containing private and shareable information across four domains. To our knowledge, MUMBench is the first public dataset designed to evaluate multiple memory operations, including retrieval, creation, update, and deletion, in a multi-user environment. Across three independent runs on MUMBench, AIM achieves 96.0% visibility classification accuracy, 58.8% strict operation accuracy, and 70.5% state-aware operation accuracy.","ledger_type":"benefit","primary_domain_id":"8f1af1b9-7302-4b51-aae9-fdfac04d158a","event_status":"provisional","event_date":"2026-09-14T00:00:00.000Z","discovery_date":"2026-09-14T00:00:00.000Z","first_published_date":"2026-09-14T00:00:00.000Z","last_reviewed_date":"2026-09-14T00:00:00.000Z","geographic_scope":"International","affected_population":null,"base_impact_tier":1,"base_score":"1.00","attribution_multiplier":"0.1000","evidence_multiplier":"0.1000","realization_multiplier":"0.2000","durability_multiplier":"0.5000","current_event_score":"0.001000","confidence_level":"low","score_explanation":"Auto-published from news ingest as a provisional placeholder. Score is conservative until a named release is identified and the record is rescored.","methodology_version_id":"d7881163-fb23-4e71-8625-bac1a8662c0f","original_methodology_version_id":"d7881163-fb23-4e71-8625-bac1a8662c0f","published_at":"2026-09-14T04:00:52.032Z","created_at":"2026-09-14T04:00:52.032Z","updated_at":"2026-09-14T04:00:52.032Z","flags":[],"domain_name":"Biology","domain_slug":"biology","methodology_version":"0.1"},"contributions":[{"id":"7adfc5b4-3f93-4e50-a632-3b7b22edf4b6","event_id":"c6b34c0e-f102-4cf1-a01e-15da0c10b1dd","model_id":"535014f7-c941-4d39-aa9b-8f9c1d3d07b7","role_description":"Unspecified system mentioned or implied by a news item. Remap to a named release when identified.","attribution_multiplier":"0.1000","credit_share":"1.0000","contribution_score":"0.001000","attribution_rationale":"News ingest does not infer a named model from the publisher alone. Attribution stays unspecified until a release is identified.","attribution_confidence":"medium","first_used_date":"2026-09-14T00:00:00.000Z","model_version_if_known":null,"review_status":"approved","created_at":"2026-09-14T04:00:52.042Z","model_slug":"unspecified-ai-system","model_name":"Unspecified AI system","identity_class":"unknown","is_internal":false,"family_name":"Unspecified","family_slug":"unknown-unspecified","organization_name":"Unknown","organization_slug":"unknown"}],"sources":[{"id":"e830f5dd-4cb8-42e4-b71a-f4f1ca64b62e","event_id":"c6b34c0e-f102-4cf1-a01e-15da0c10b1dd","url":"https://arxiv.org/abs/2609.12320","canonical_url":"https://arxiv.org/abs/2609.12320","source_type":"preprint","publisher":"arXiv cs.AI","author":null,"publication_date":"2026-09-14T00:00:00.000Z","retrieved_at":"2026-09-14T04:00:52.049Z","title":"AIM: A Privacy-Aware Interoperable Memory Framework for Multi-Agent Multi-User LLM Systems","excerpt":"arXiv:2609.12320v1 Announce Type: new \nAbstract: Traditional large language models (LLMs) are scoped to individual user sessions, limiting their knowledge to a single conversation and preventing them from learning user preferences that evolve over time. Existing agentic memory systems address this limitation but generally operate at the individual-user level, restricting the public knowledge that could be shared across users to improve downstream responses. We introduce AIM (Agentic Interoperabl","content_hash":null,"source_reliability_class":"medium","is_primary_source":true,"is_independent":true,"is_peer_reviewed":false,"archived_url":null,"created_at":"2026-09-14T04:00:52.049Z"}],"claims":[{"id":"9a1c203a-f953-41dd-9e91-5d89038f9035","event_id":"c6b34c0e-f102-4cf1-a01e-15da0c10b1dd","claim_text":"AIM: A Privacy-Aware Interoperable Memory Framework for Multi-Agent Multi-User LLM Systems","claim_type":"outcome","claim_status":"supported","confidence_score":null,"created_at":"2026-09-14T04:00:52.056Z","updated_at":"2026-09-14T04:00:52.056Z"}],"revisions":[{"id":"cab247ce-2da6-4c35-b6b4-df9193a12472","event_id":"c6b34c0e-f102-4cf1-a01e-15da0c10b1dd","model_id":null,"previous_score":"0.000000","new_score":"0.001000","previous_factors":{},"new_factors":{"evidence":0.1,"base_score":1,"durability":0.5,"attribution":0.1,"realization":0.2},"change_reason":"Auto-published from news ingest.","trigger_type":"news_ingest","trigger_source_ids":null,"reviewer_id":null,"review_status":"published","created_at":"2026-09-14T04:00:52.076Z"}],"secondary":[]},"methodology_version":"0.1"}