TechniqueRLHF / Alignment2 recent entries3 Jun 2026Traj-Evolve: A Self-Evolving Multi-Agent System for Patient Trajectory Modeling in Lung Cancer Early DetectionarXiv:2606.02812v1 Announce Type: new Abstract: Modeling patient trajectories from longitudinal electronic health records (EHRs) requires reasoning over sparse, noisy, and long-context multimodal sequ→24 Sept 2026EnSIMem: Entity-Structured Indexing for Long-Term Agent MemoryarXiv:2609.27279v1 Announce Type: new Abstract: An agent that interacts with users over long periods must recall facts, preferences, events, and changes from a continuously growing interaction history
TechniqueRAG5 recent entries3 Jun 2026Traj-Evolve: A Self-Evolving Multi-Agent System for Patient Trajectory Modeling in Lung Cancer Early DetectionarXiv:2606.02812v1 Announce Type: new Abstract: Modeling patient trajectories from longitudinal electronic health records (EHRs) requires reasoning over sparse, noisy, and long-context multimodal sequ→3 Jun 2026eMEM: A Hybrid Spatio-Temporal Memory System For Embodied AgentsarXiv:2606.03374v1 Announce Type: new Abstract: We present eMEM (Embodied Memory), a hybrid graph-based memory system for embodied agents operating in physical environments. Current agent memory archi→17 Aug 2026MemoryLake on MemoryArena: A Matched Study of Agent Memory BackendsarXiv:2608.13883v1 Announce Type: new Abstract: Most agent-memory benchmarks test post-hoc recall, whereas MemoryArena evaluates whether memory supports interdependent, multi-session task completion. →2 Oct 2026From Knowledge Access to Source Learning: Developing Source-Specific CompetencearXiv:2610.02150v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly rely on persistent external sources to solve sequences of knowledge-intensive tasks. Existing methods i→7 Oct 2026Persistent Memory in Multi-Agent LLM Inference: What It Costs, What It Buys, and When You Can TellarXiv:2610.07782v1 Announce Type: new Abstract: Decomposing long-context inference across cooperating agents bounds the active KV cache per call rather than total evidence, which matters when KV-cache
TechniqueAgents8 recent entries2 Oct 2026Heavy-Tailed Memory Traces in Long-Horizon Language AgentsarXiv:2610.00010v1 Announce Type: new Abstract: Long-horizon language agents increasingly rely on external memory as a frozen world model, yet current memory systems are usually judged only by task su→2 Oct 2026From Knowledge Access to Source Learning: Developing Source-Specific CompetencearXiv:2610.02150v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly rely on persistent external sources to solve sequences of knowledge-intensive tasks. Existing methods i→5 Oct 2026Interpreting at Write Time: A Policy Ablation for Multi-Goal Agent MemoryarXiv:2610.02897v1 Announce Type: new Abstract: A long-running assistant cannot keep everything it has seen, so it summarises. Summarising is not neutral: what is kept is chosen against some notion of→6 Oct 2026MemPilot: Orchestrating On-Demand Multimodal Memory Curation for LLM AgentsarXiv:2610.06830v1 Announce Type: cross Abstract: Memory has become integral to the LLM agent ecosystem, supporting information retention and reuse across interactions. However, most existing agent me→7 Oct 2026Persistent Memory in Multi-Agent LLM Inference: What It Costs, What It Buys, and When You Can TellarXiv:2610.07782v1 Announce Type: new Abstract: Decomposing long-context inference across cooperating agents bounds the active KV cache per call rather than total evidence, which matters when KV-cache→7 Oct 2026Lineage-Aware Memory Governance: A Derivation-Gated Framework for Privacy-Preserving Column-Level Access Control in Enterprise AI AgentsarXiv:2610.07258v1 Announce Type: cross Abstract: Enterprise AI agents that share a memory store face two unaddressed risks: sensitive data can leak through legitimately computed results the requester→7 Oct 2026Beyond Corrected Memory: Execution Consistency in Multi-Agent SystemsarXiv:2610.08101v1 Announce Type: new Abstract: Shared memory coordinates agents' actions, but correct records do not establish that those actions satisfy task requirements. Memory governance and fail→9 Oct 2026MemoWM: How World Models Change What Agents Need to RememberarXiv:2610.10778v1 Announce Type: cross Abstract: Long-term agents face growing storage demands as they accumulate experience. World models capture reusable regularities that can reduce the informatio
TechniqueFine-tuning2 recent entries3 Jun 2026Traj-Evolve: A Self-Evolving Multi-Agent System for Patient Trajectory Modeling in Lung Cancer Early DetectionarXiv:2606.02812v1 Announce Type: new Abstract: Modeling patient trajectories from longitudinal electronic health records (EHRs) requires reasoning over sparse, noisy, and long-context multimodal sequ→29 Sept 2026Just-In-Time Agent Memory with Runtime Agentic ResearcharXiv:2609.34385v1 Announce Type: cross Abstract: Memory is critical for AI agents. Many existing agent-memory systems follow an Ahead-of-Time (AOT) design, constructing memory before a specific reque
TechniqueMultimodal5 recent entries3 Jun 2026Traj-Evolve: A Self-Evolving Multi-Agent System for Patient Trajectory Modeling in Lung Cancer Early DetectionarXiv:2606.02812v1 Announce Type: new Abstract: Modeling patient trajectories from longitudinal electronic health records (EHRs) requires reasoning over sparse, noisy, and long-context multimodal sequ→29 Jun 2026DMV-Bench: Diagnosing Long-Horizon Multimodal Agents' Visual Memory with Incidental Cue InjectionarXiv:2606.27499v1 Announce Type: cross Abstract: Research on agent memory has matured rapidly, but almost entirely on the text side: few existing benchmarks ask, in an interactive environment, when a→12 Sept 2026Grounding Agent Memory: Environment-Probing Curation for Enterprise AgentsarXiv:2609.11060v1 Announce Type: new Abstract: Persistent memory is entering production-oriented agent platforms to help long-horizon agents accumulate experience across sessions. Yet a post-task cur→24 Sept 2026EnSIMem: Entity-Structured Indexing for Long-Term Agent MemoryarXiv:2609.27279v1 Announce Type: new Abstract: An agent that interacts with users over long periods must recall facts, preferences, events, and changes from a continuously growing interaction history→6 Oct 2026MemPilot: Orchestrating On-Demand Multimodal Memory Curation for LLM AgentsarXiv:2610.06830v1 Announce Type: cross Abstract: Memory has become integral to the LLM agent ecosystem, supporting information retention and reuse across interactions. However, most existing agent me
TechniqueSafety8 recent entries13 Aug 2026Towards a Formal Definition of Agent Memory: Basis, Span, Optimality, and the Sequential Memory ProblemarXiv:2608.11654v1 Announce Type: new Abstract: Despite the wide deployment of memory in large-model agents, there is no unified formal account of what a memory is or when it is optimal. This paper ta→10 Sept 2026Revoked but Still Authoritative: An Empirical Study of Revocation Enforcement in Agent-Memory SystemsarXiv:2609.08258v1 Announce Type: new Abstract: Long-running language-model agents depend on persistent memory. Many agent-memory systems preserve history through soft revocation: a contradicted fact →29 Sept 2026Just-In-Time Agent Memory with Runtime Agentic ResearcharXiv:2609.34385v1 Announce Type: cross Abstract: Memory is critical for AI agents. Many existing agent-memory systems follow an Ahead-of-Time (AOT) design, constructing memory before a specific reque→30 Sept 2026Audience-Bound Persistent Memory: Authorization Across the Memory LifecyclearXiv:2609.36373v1 Announce Type: cross Abstract: A personal language agent that acts for its owner across private and shared conversations can learn a fact from one audience and later place it in the→2 Oct 2026Heavy-Tailed Memory Traces in Long-Horizon Language AgentsarXiv:2610.00010v1 Announce Type: new Abstract: Long-horizon language agents increasingly rely on external memory as a frozen world model, yet current memory systems are usually judged only by task su→5 Oct 2026Interpreting at Write Time: A Policy Ablation for Multi-Goal Agent MemoryarXiv:2610.02897v1 Announce Type: new Abstract: A long-running assistant cannot keep everything it has seen, so it summarises. Summarising is not neutral: what is kept is chosen against some notion of→6 Oct 2026MemPilot: Orchestrating On-Demand Multimodal Memory Curation for LLM AgentsarXiv:2610.06830v1 Announce Type: cross Abstract: Memory has become integral to the LLM agent ecosystem, supporting information retention and reuse across interactions. However, most existing agent me→7 Oct 2026Lineage-Aware Memory Governance: A Derivation-Gated Framework for Privacy-Preserving Column-Level Access Control in Enterprise AI AgentsarXiv:2610.07258v1 Announce Type: cross Abstract: Enterprise AI agents that share a memory store face two unaddressed risks: sensitive data can leak through legitimately computed results the requester