Skip to main content
Search

# Agentic Memory

10 related articles

Subscribe to updates
  1. arXiv

    6G slice placement stops relying on one fixed plan: ORION feeds verifier-checked outcomes back to its LLM planner

    Placing, routing and admitting multi-domain 6G network slices is an NP-hard online problem, fixed planning strategies reverse rank across topologies, and most rejected requests do have a feasible placement. ORION's hierarchical orchestrator uses two LLM agents to translate service intents and generate abstract placement plans, and records each attempt's network conditions, plan shape and verifier feasibility outcome in an episodic memory that returns to the planner as labelled examples. With selection and execution held fixed on held-out topology families, the memory-equipped planner admits more than both the memory-off and first-in-first-out variants on two seeds, though the magnitude is not established.

  2. arXiv

    Robot memory stops guessing from keyframes: per-tick text lines lift success from 44.5% to 66.0% under a fixed policy

    Gamma replaces pixel keyframe memory with auditable text lines, raising average success on RoboMME's sixteen memory tasks from 44.5% to 66.0% under a fixed execution policy and matching the privileged subgoal ceiling on three tasks.

  3. Claude Platform opens OpenTelemetry export: trace Messages API calls and managed-agent sessions in your own backend

    Claude Platform now exports tracing data for Messages API requests and Claude Managed Agents sessions as OpenTelemetry spans, so developers can view those calls in their own observability backend.

  4. arXiv

    MemTrim indexes memory at the evidence level, cutting memory-induced errors under partial overlap from 11.6% to 0.6%

    The authors identify and study memory overreliance, an inference-time failure in which benign, correctly stored, and appropriately retrieved memory misleads reasoning when it only partially overlaps the current query, and propose MemTrim, a plug-and-play framework that decomposes memories into evidence units indexed in a trie at write time and, at read time, removes evidence repeated in or conflicting with the query, retains memory-only information, and suppresses a previous answer when its supporting evidence has changed, reducing memory-induced errors across benchmarks, models, and memory architectures while preserving the benefits of useful memory.

  5. arXiv

    StegoMemory red-teaming: 20.1% of 14,000 trials achieved exact-match cross-session covert transmission, and 71.4% of those also passed task completion and safety oversight

    Using SHADE-Arena-style tasks in a large-scale red-teaming exercise across 14,000 attack trials, 91 model-attack configurations, 13 models, and 7 steganographic schemes, the work tested whether agentic memory can carry attacker-controlled strings across sessions without triggering safety oversight, finding that 41.2% of trials encoded the payload, 29.8% survived the memory-write step with the encoding intact, 25.4% yielded a recoverable payload at retrieval, and 20.1% achieved exact-match recovery, while 71.4% of exact-match transmissions also passed primary task-completion scoring and were judged safe by the oversight model, corresponding to 14.4% of all trials.

  6. arXiv

    AECG tops 11 of 12 framework-benchmark settings across three multi-agent frameworks and four benchmarks, with scope-preservation ablation dropping accuracy by up to 16.89 points

    The authors introduce AECG, a multi-agent memory governance framework that combines scope preservation, asymmetric evidence admission, dual-timescale reliability estimation, and downstream-exposure-aware budgeted review to turn memory from static storage into a reliability-governance loop; across three frameworks (AutoGen, MacNet, AgentNet) and four benchmarks (PDDL, FEVER, ScienceWorld, MBPP-Plus), AECG achieves the best score in 11 of 12 settings, improving over the strongest memory baseline by up to 10.23 percentage points, while removing scope preservation reduces accuracy by up to 16.89 points.

  7. arXiv

    MemLife builds entity-grounded first-person text memories read by a time-indexed agentic reader, beating the strongest training-free baseline by 4.6–12.0% on four long-horizon egocentric video benchmarks, with MemOpt adding 2.7–5.0% by training only the memory writer under the FIRM reward

    The work introduces MemLife, a multimodal memory system that compacts egocentric video into time- and entity-anchored first-person text episodes retrieved by a time-indexed agentic reader, improving over the strongest training-free baseline by 4.6–12.0% across four long-horizon benchmarks without training or query-time video access, and further proposes MemOpt, which applies reinforcement learning only to the memory writer under the faithful, informative, and retrievable FIRM reward, adding 2.7–5.0% with gains that transfer across writer and reader backbones, memory systems, and out-of-domain video and question distributions.

  8. arXiv

    NavHarness carries maps, search records and house notes into the next conversation, lifting GOAT-Bench s-SR by 18.6 to 34.8 points

    NavHarness is a training-free embodied harness that makes memory processing part of the navigation loop: each task opens a fresh multi-round agentic session that inherits prior experience through maps, task records and house notes, while outcome verification and run-end consolidation decide what later sessions inherit; on GOAT-Bench it improves s-SR over context-only independent sessions by 18.6 points with GPT-6 Astra, 22.6 with Opus 5, 34.8 with GPT-4o and 30.3 with Qwen3.8-27B, and with SLAM-estimated poses Astra reaches 83.7 s-SR with 36.9 e-SR on GOAT-Bench and 85.9 s-SR on IR2R-CE.

  9. arXiv

    Jev-Mem puts a System-One control plane over agentic memory, lifting LoCoMo overall score to 0.777 while cutting memory build time to 158 seconds

    Jev-Mem introduces an agentic memory architecture inspired by System-One/System-Two cognition, in which a dedicated System-One control plane handles memory typing, relation construction, query routing, retrieval-budget allocation, graph traversal, candidate scoring, and adaptive stopping, while System Two is reserved for complex reasoning and answer synthesis; on LoCoMo it reaches an overall LLM-as-a-Judge score of 0.777 (an 11.0% relative gain over the strongest baseline), a memory construction time of 158 seconds (a 6.6 speedup over the fastest competing memory system), and an average query latency of 0.93 seconds (a 36.7% reduction).

  10. arXiv

    SAP Signavio proposes an "organizational memory" architecture that lifts LLM agents' policy compliance in a procurement process from 30% to 88%–95%

    The work introduces the concept of an organizational memory for agentic business process execution—a shared, human-governed, agent-consumable reference layer of organization-specific procedural knowledge—and derives requirements (R1–R9), an architecture covering memory curation and runtime consumption, and an instantiation based on process atoms; in a purchase-to-pay proof-of-concept, the Policy Compliance Rate averaged over 10 scenarios with four runs each reached 88% with GPT-4.1 and 95% with Claude Sonnet 4.5 for the memory-equipped agent, versus 70% and 80% for RAG and 30% for the no-knowledge base setup with both models.

You’re all caught up