A Benchmark and Diagnostic Study of Epistemic Admission in Shared Agent Memory

arXiv:2609.30813 · cs.AI · Submitted 2026-09-25 · Read on arXiv

cs.AI

Submitted: 2026-09-25

Updated: 2026-09-25

Code: https://github.com/lxy1134/iclr_2027

Terminology

• LLM judge — 21× in this paper · explained in 2 episodes
• Provenance — 19× in this paper · explained in 4 episodes
• Trace — 17× in this paper · explained in 2 episodes
• Agent Memory — 12× in this paper · explained in 1 episode
• Consistency — 12× in this paper · explained in 3 episodes
• Benchmark — 10× in this paper · explained in 2 episodes
• Abstention — 7× in this paper · explained in 1 episode
• Accuracy — 7× in this paper · explained in 1 episode
• Multi-Agent System — 6× in this paper · explained in 6 episodes
• Verification — 5× in this paper · explained in 2 episodes
• AI Agents — 4× in this paper · explained in 2 episodes
• Benchmarking — 3× in this paper · explained in 3 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Empirical Methods in Natural Language Processing — 2× in this paper
• In International Conference on Learning Representations — 2× in this paper
• Agentic System — 1× in this paper · explained in 2 episodes
• Annotator Agreement — 1× in this paper · explained in 1 episode
• Redundancy — 1× in this paper · explained in 2 episodes
• Self-consistency — 1× in this paper · explained in 2 episodes
• Sycophancy — 1× in this paper · explained in 4 episodes
• Verifiability — 1× in this paper · explained in 2 episodes

Sources

• Misinformation Propagation in Benign Multi-Agent Systems
• SuperLocalMemory 4.0: The Governed Memory Operating System for AI Agents
• AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases
• Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
• Governed Collaborative Memory as Artificial Selection in LLM-Based Multi-Agent Systems
• Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents
• Memory Injection Attacks on LLM Agents via Query-Only Interaction
• Learning to Share: Selective Memory for Efficient Parallel Agentic Systems
• The Llama 3 Herd of Models
• Learning What to Share and What to Personalize: Hierarchical Strategy Co-Evolution for Agent Memory
• MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agents
• Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
• Capability Minimization as a Safety Primitive: Risk-Aware Causal Gating for Least-Privilege LLM Agents
• Gemma 3 Technical Report
• Nine Judges, Two Effective Votes: Correlated Errors Undermine LLM Evaluation Panels
• IMPACT-CYCLE: A Contract-Based Multi-Agent System for Claim-Level Supervisory Correction of Long-Video Semantic Memory
• Hindsight is 20/20: Building Agent Memory that Retains, Recalls, and Reflects
• MemTX: Transactional Belief Commit for Stateful Agent Memory
• Belief Memory: Agent Memory Under Partial Observability

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection