arXiv AI
Aug 21
Beyond Memory Majority: Latent-Source Reasoning for Multi-Agent Memory Arbitration
arXiv:2608. 19701v1 Announce Type: new Abstract: Long-term multi-agent systems continuously accumulate the memories produced by different agents.
Beyond Memory Majority: Latent-Source Reasoning for Multi-Agent Memory Arbitration
Long-term multi-agent systems continuously accumulate the memories produced by different agents. Existing memory methods typically treat retrieved memories as independent evidence and combine them through voting or weighting.
Related stories
Hugging Face Trending Papers
Jun 22
RaMem: Contextual Reinstatement for Long-term Agentic Memory
Long-term memory has become increasingly important for LLM agents that operate across extended interactions and evolving task contexts. Recent memory systems have made past experiences more persistent, compact, and retrievable, but retrieval alone does not ensure that a memory provides valid evidence for the current query.
arXiv Computer Vision
Oct 27
Intuition with Evidence: Adaptive Dual Memory for Multimodal Agents
arXiv:2610.33019v1 Announce Type: new Abstract: As multimodal agents engage in sustained interactions, long-term memory serves two distinct but complementary functions: fine-grained evidence recall a...
arXiv AI
Oct 15
Recall What Is Missing: Composing Evidence from Long-Term Agent Memory
arXiv:2610.15642v1 Announce Type: new Abstract: Under a limited context budget, a long-term agent must recall not merely memories that are individually relevant, but evidence that is collectively suf...
arXiv AI
Oct 7
Understanding and Mitigating Inference-Time Overreliance Using Agentic Memory
The paper investigates how large language model agents can over-rely on agentic memory, a phenomenon where retrieved memories distort inference even when they are correctly stored and retrieved. It shows that memory is helpful when past experience fully transfers to the current task but becomes misleading under partial query-memory overlap, a pattern confirmed by controlled experiments. To address this, the authors propose MEMTRIM, a plug‑and‑play framework that indexes memory evidence at write time and limits its reuse at read time, thereby reducing over-reliance without retraining and preserving useful memory benefits across models and memory architectures.
arXiv AI
Jul 17
When Does Belief-Based Agent Memory Help? Reliability-Conditional Updating and Provenance-Capped Poisoning Defense
arXiv:2606. 22030v2 Announce Type: replace Abstract: We investigate when belief-based memory actually improves large language model (LLM) agents.
arXiv AI
Aug 20
MemFuse: Multi-Source Memory Fusion from Fragmented Observations
MemFuseBench is a benchmark for multi‑source memory fusion that generates source‑tagged observations, evidence‑grounded questions, and adversarial distractors using a Scene‑to‑Sensor pipeline. The proposed MemFuse system preserves source‑level evidence in atomic memory and clusters related events into fused memory via a causal fusion graph, enabling traceable retrieval of dispersed observations. Experiments show that MemFuse outperforms other memory systems across all LLM settings, especially on questions requiring cross‑source evidence fusion.
arXiv Machine Learning
Sep 4
MemoryLACE: Memory Lifecycle-Aware Consolidation and Evidence Retrieval
MemoryLACE (MemLACE) is a lightweight memory framework that explicitly models the lifecycle of textual evidence—capturing sparse merge, supersession, and contradiction relations—while preserving atomic natural‑language memories and their provenance. Unlike traditional systems that retrieve memories independently, MemLACE reconstructs relation‑aware evidence units that expose current, historical, supporting, and conflicting evidence for downstream reasoning. In benchmark evaluations (BEAM and StructMemEval) using both open‑weight and proprietary LLM backbones, MemLACE achieves the highest overall performance among same‑backbone comparisons and reduces BEAM runtime by 66.6% compared to the strongest reflective‑memory baseline, Hindsight.
arXiv AI
Oct 19
From Relevant Memories to Sufficient Evidence: Rethinking Memory Utilization in LLM Agents
The paper introduces QEMem, a framework that rethinks how large language model agents use long‑term memory by constructing query‑specific evidence sets rather than relying on individual memory relevance. QEMem combines query‑guided discovery, source‑grounded reification into structured ViewCards, and sufficiency‑guided refinement to assemble comprehensive evidence from multiple memory granularities. Experiments show that QEMem achieves 91.43% LLM‑judge accuracy on LoCoMo with Claude Opus 4.5, surpassing leading baselines by significant margins and improving evidence coverage for cross‑session queries.
Hugging Face Trending Papers
Aug 19
MemFuse: Multi-Source Memory Fusion from Fragmented Observations
MemFuse introduces a multi‑source memory fusion system and a corresponding benchmark, MemFuseBench, designed to evaluate agents that must integrate fragmented observations from multiple applications, devices, users, and time points. The benchmark uses a Scene‑to‑Sensor pipeline to generate source‑tagged observations, evidence‑grounded questions, and adversarial distractors, enabling systematic assessment of temporal reasoning, cross‑source evidence fusion, and noise robustness. Experiments show that MemFuse outperforms other memory systems across all evaluated LLM settings, especially on questions requiring cross‑source evidence fusion.
arXiv Computation and Language
Oct 1
LatentHarness: Learning Latent Actions for Memory and Reasoning via Counterfactual Policy Distillation
LatentHarness unifies memory access and latent reasoning by treating them as sequential latent actions—THINK, RECALL, and EXIT—within a language model. It is trained via counterfactual policy distillation, which evaluates the impact of each action on the emitted token and learns when to recall evidence versus continue reasoning. On six long‑context reasoning benchmarks, a 1.4B‑parameter LatentHarness model outperforms the strongest baselines by 2.8% and 10.0% relative, while running 5.9× faster than the leading long‑context baseline.
arXiv AI
Sep 30
CoEM: Empowering Long-Context Reasoning with Commit-on-Evidence Memory
CoEM introduces a Commit-on-Evidence Memory system that learns when to compress source evidence into compact memory facts while preserving potentially useful excerpts verbatim in a pending set. The system uses a learned policy to decide whether to promote, retain, or discard each pending excerpt as new context arrives, and a frozen verifier ensures only supported facts are committed. Reinforcement learning trains this policy with step-level evidence rewards and final answer rewards, leading to consistent improvements in long-context reasoning, achieving 10.4–11.4 F1 points over the strongest baseline on 6,400-document inputs.