Agentic Memory
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Channel Fracture: Architectural Blind Spots in Scheduled Cross-Agent Memory Injection for Multi-Agent Orchestration Systems
arXiv:2606.04896v1 Announce Type: new Abstract: Multi-agent AI orchestration systems increasingly rely on persistent memory to maintain context across sessions, agents, and tasks. When one agent must inject knowledge into another agent's memory -- a common requirement in hierarchical team architectures -- the delivery mechanism must be architecturally sound. We report the discovery of a systematic failure mode we term channel fracture: a condition where scheduled (cron) agents in...
Channel Fracture: Architectural Blind Spots in Scheduled Cross-Agent Memory Injection for Multi-Agent Orchestration Systems
arXiv:2606.04896v2 Announce Type: replace Abstract: Multi-agent AI orchestration systems increasingly rely on persistent memory to maintain context across sessions, agents, and tasks. When one agent must inject knowledge into another agent's memory -- a common requirement in hierarchical team architectures -- the delivery mechanism must be architecturally sound. We report the discovery of a systematic failure mode we term channel fracture: a condition where scheduled (cron) agents in...
Universal Memory Protocol – a shared format for agent memory
Universal Memory Protocol The third interoperability layer Section titled “The third interoperability layer”Agents can already call tools (MCP) and talk to each other (A2A). What they can’t do is carry memory across sessions, agents, and vendors.
eMEM: A Hybrid Spatio-Temporal Memory System For Embodied Agents
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 architectures, such as Generative Agents, MemGPT, and A-MEM, treat memory as text streams or knowledge graphs, but embodied agents require memory that is simultaneously searchable by meaning, space, and time. eMEM fills this gap with a multi-index architecture (SQL ITE for structured storage, hnswlib for approximate...
PEAM: Parametric Embodied Agent Memory through Contrastive Internalization of Experience in Minecraft
arXiv:2605.27762v2 Announce Type: replace Abstract: We present PEAM, a Parametric Embodied Agent Memory framework in Minecraft that transforms agent memory from inference-time retrieval into parameter-resident skills internalized through experience. PEAM pairs a slow deliberative LLM for open-ended reasoning with a fast parametric module for reflexive execution of consolidated skills. The fast module is a multimodal Mixture-of-Experts LoRA architecture with per-category physically isolated...
InfoMem: Training Long-Context Memory Agents with Answer-Conditioned Information Gain
arXiv:2606.03329v1 Announce Type: new Abstract: Long-context tasks require LLMs to identify and preserve answer-relevant information from large contexts. Chunk-wise memory agents address this issue by sequentially reading document chunks, updating a compact memory, and generating the final answer from the accumulated memory. However, existing RL-based chunk-wise agents either rely on sparse final-answer rewards or use lexical intermediate rewards for memory and retrieval actions.
Agent Memory: Characterization and System Implications of Stateful Long-Horizon Workloads
arXiv:2606.06448v1 Announce Type: new Abstract: LLM agents are increasingly deployed on long-horizon tasks requiring sustained reasoning over extended interaction histories. Realizing this at scale requires agents to persistently store, retrieve, and update their own memory across sessions. A rich ecosystem of agent memory systems has emerged spanning flat retrieval, LLM-mediated extraction, consolidating fact stores, and agentic control flows.
Exploring Cross-Scenario Generality of Agentic Memory Systems: Diagnostics and a Strong Baseline
Announce Type: new Abstract: LLM agents accumulate histories that outgrow their context windows, motivating a growing literature on memory systems. Yet most existing designs are tuned to a single scenario (multi-session chat or a single trajectory format), and there is little evidence that they generalize across the heterogeneous trajectories agents encounter in deployment. We revisit eight memory systems plus an agentic harness for search problems, on five scenarios: single-turn QA,...
Temporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents
Announce Type: new Abstract: Long-horizon conversational agents need to interact with users through evolving events, tasks, and goals. Such histories are naturally temporal, yet many existing memory systems organize information primarily by topical similarity and may ignore the order in which events occur. We introduce Segment Tree Memory, or SegTreeMem, a memory architecture that represents conversation history as a temporally ordered Segment Tree over utterances.
TAME: A Trustworthy Test-Time Evolution of Agent Memory with Systematic Benchmarking
arXiv:2602.03224v2 Announce Type: replace Abstract: Test-time evolution of agent memory represents a pivotal paradigm for advancing AGI, as it strengthens complex reasoning through experience accumulation without requiring parameter updates. However, even during benign task evolution, agent safety alignment remains vulnerable, a phenomenon known as Agent Memory Misevolution. To evaluate this phenomenon, we construct the Trust-Memevo benchmark and find that agents exhibit an overall decline...