PolarMem: A Training-Free Polarized Latent Graph Memory for Verifiable Multimodal Agents

• URL: http://arxiv.org/abs/2602.00415v1
• Date: Sat, 31 Jan 2026 00:13:56 GMT
• Title: PolarMem: A Training-Free Polarized Latent Graph Memory for Verifiable Multimodal Agents
• Abstract summary: multimodal agents evolve from passive observers to long-horizon decision-makers.<n>Current memory systems fail to encode negative constraints.<n>We introduce PolarMem, a training-free Polarized Latent Graph Memory.
• Score: 5.350399160165104
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As multimodal agents evolve from passive observers to long-horizon decision-makers, they require memory systems that provide not just information availability but logical verifiability. A fundamental limitation of current architectures is the epistemic asymmetry inherent in probabilistic vision-language models and dense associative memories: they conflate semantic affinity with factual existence and structurally fail to encode negative constraints. To this end, we introduce PolarMem, a training-free Polarized Latent Graph Memory designed to ground agent reasoning in verifiable evidence. PolarMem transforms fuzzy perceptual likelihoods into discrete logical constraints through non-parametric distributional partitioning. Furthermore, it employs a polarized graph topology with orthogonal inhibitory connections to explicitly store verified negation as a primary cognitive state. At inference time, we enforce a logic-dominant retrieval paradigm, suppressing hallucinatory patterns that violate negative constraints. Extensive evaluation across eight frozen Vision--Language Models and six benchmarks demonstrates that PolarMem functions as a robust cognitive system, establishing a foundation for verifiable multimodal agents. Our code is available at https://github.com/czs-ict/PolarMem.

Related papers

• Beyond the Cartesian Illusion: Testing Two-Stage Multi-Modal Theory of Mind under Perceptual Bottlenecks [16.03812136589077]
  We introduce an Anchor-Based Embodied Spatial Decomposition Chain-of-Thought (CoT)<n>CoT guides the MLLM through a "geometric-to-semantic" projection, forcing it to first establish B's local coordinate system and then dynamically weight visual and auditory modalities based on whether A falls within B's visual frustum.
  arXiv  Detail & Related papers  (2026-05-18T10:32:56Z)
• The Cartesian Shortcut: Re-evaluate Vision Reasoning in Polar Coordinate Space [29.35702264173152]
  We identify a pervasive vulnerability, the textbfCartesian Shortcut: visual reasoning benchmarks prevalently build on orthogonal grid-based layouts.<n>Models systematically exploit this property, heavily leveraging text-based deductive reasoning to assist visual problem-solving.<n>We introduce textbfPolaris-Bench, which re-formulates 53 visual reasoning tasks in Polar coordinate space with paired Cartesian counterparts as reference.
  arXiv  Detail & Related papers  (2026-05-11T02:16:48Z)
• Latent-Hysteresis Graph ODEs: Modeling Coupled Topology-Feature Evolution via Continuous Phase Transitions [4.104525618451057]
  Graph neural ordinary differential equations (Graph ODEs) extend graph learning from discrete message-passing layers to continuous-time representation flows.<n>We show that Graph ODEs with strictly positive irreducible mixing operators face an inherent emphmonostability trap: in the long-time regime, information leakage is unavoidable and the dynamics converge to a single global consensus attractor.
  arXiv  Detail & Related papers  (2026-04-27T10:27:41Z)
• Neural Uncertainty Principle: A Unified View of Adversarial Fragility and LLM Hallucination [60.197429875410286]
  Adversarial vulnerability in vision and hallucination in large language models are conventionally viewed as separate problems.<n>Formalizing a Neural Uncertainty Principle (NUP) under a loss-induced state, we find that in near-bound regimes, further compression must be accompanied by increased sensitivity dispersion.<n>In vision, masking highly coupled components improves robustness without costly adversarial training.<n>In language, the same prefill-stage probe detects hallucination risk before generating any answer tokens.
  arXiv  Detail & Related papers  (2026-03-20T02:07:10Z)
• Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models [62.932580559941414]
  Vision-Language Models (VLMs) frequently "hallucinate" - generate plausible yet factually incorrect statements.<n>We propose a new paradigm for diagnosing hallucinations, recasting them from static output errors into dynamic pathologies of a model's computational cognition.
  arXiv  Detail & Related papers  (2026-03-16T17:20:38Z)
• Graph-theoretic Agreement Framework for Multi-agent LLM Systems [0.228438857884398]
  This paper establishes a rigorous graph-theoretic framework for analyzing consensus in signed, directed interaction networks.<n>We show how unbalanced critique cycles produce logical frustration and persistent reasoning oscillations.<n>We prove that rank-one spectral edge perturbations deterministically break symmetry by shifting eigenvalues into the stable left-half plane.
  arXiv  Detail & Related papers  (2026-02-23T02:30:48Z)
• Digital Metabolism: Decoupling Logic from Facts via Regenerative Unlearning -- Towards a Pure Neural Logic Core [4.073707521515039]
  "Digital metabolism" is a hypothesis suggesting that targeted forgetting is necessary for distilling a pure neural logic core.<n>We introduce the Regenerative Logic-Core Protocol (RLCP), a dual-stream training framework that renders specific factual dependencies linearly undecodable.<n> Empirical analysis on GSM8K reveals that the "metabolized" model spontaneously adopts Symbolic chain-of-thought scaffolding.
  arXiv  Detail & Related papers  (2026-01-15T19:21:16Z)
• Forgetting as a Feature: Cognitive Alignment of Large Language Models [39.146761527401424]
  We show that Large Language Models (LLMs) exhibit systematic forgetting of past information.<n> Drawing inspiration from human memory dynamics, we model LLM inference as a probabilistic memory process governed by exponential decay.<n>Building on these observations, we propose probabilistic memory prompting, a lightweight strategy that shapes evidence integration to mimic human-like memory decay.
  arXiv  Detail & Related papers  (2025-12-28T10:43:00Z)
• MM-CoT:A Benchmark for Probing Visual Chain-of-Thought Reasoning in Multimodal Models [49.32415342913976]
  We introduce MM-CoT, a diagnostic benchmark designed to probe the visual grounding and logical coherence of CoT reasoning in multimodal models.<n>We evaluate leading vision-language models on MM-CoT and find that even the most advanced systems struggle, revealing a sharp discrepancy between generative fluency and true reasoning fidelity.
  arXiv  Detail & Related papers  (2025-12-09T04:13:31Z)
• More Than Irrational: Modeling Belief-Biased Agents [25.274115351731325]
  We introduce a class of computational-rational (CR) user models for cognitively-bounded agents acting optimally under biased beliefs.<n>We address the challenge of identifying the latent user-specific bound and inferring biased belief states from passive observations.<n>We show that our CR model generates intuitively plausible behaviors corresponding to different levels of memory capacity.
  arXiv  Detail & Related papers  (2025-11-15T21:14:37Z)
• Towards Inference-time Scaling for Continuous Space Reasoning [55.40260529506702]
  Inference-time scaling has proven effective for text-based reasoning in large language models.<n>This paper investigates whether such established techniques can be successfully adapted to reasoning in the continuous space.<n>We demonstrate the feasibility of generating diverse reasoning paths through dropout-based sampling.
  arXiv  Detail & Related papers  (2025-10-14T05:53:41Z)
• I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data? [76.15163242945813]
  Large language models (LLMs) have led many to conclude that they exhibit a form of intelligence.<n>We introduce a novel generative model that generates tokens on the basis of human-interpretable concepts represented as latent discrete variables.
  arXiv  Detail & Related papers  (2025-03-12T01:21:17Z)
• Exposing Attention Glitches with Flip-Flop Language Modeling [55.0688535574859]
  This work identifies and analyzes the phenomenon of attention glitches in large language models. We introduce flip-flop language modeling (FFLM), a family of synthetic benchmarks designed to probe the extrapolative behavior of neural language models. We find that Transformer FFLMs suffer from a long tail of sporadic reasoning errors, some of which we can eliminate using various regularization techniques.
  arXiv  Detail & Related papers  (2023-06-01T17:44:35Z)
• Neuro-Symbolic Entropy Regularization [78.16196949641079]
  In structured prediction, the goal is to jointly predict many output variables that together encode a structured object. One approach -- entropy regularization -- posits that decision boundaries should lie in low-probability regions. We propose a loss, neuro-symbolic entropy regularization, that encourages the model to confidently predict a valid object.
  arXiv  Detail & Related papers  (2022-01-25T06:23:10Z)
• Modeling Implicit Bias with Fuzzy Cognitive Maps [0.0]
  This paper presents a Fuzzy Cognitive Map model to quantify implicit bias in structured datasets. We introduce a new reasoning mechanism equipped with a normalization-like transfer function that prevents neurons from saturating.
  arXiv  Detail & Related papers  (2021-12-23T17:04:12Z)
• Tractable Inference in Credal Sentential Decision Diagrams [116.6516175350871]
  Probabilistic sentential decision diagrams are logic circuits where the inputs of disjunctive gates are annotated by probability values. We develop the credal sentential decision diagrams, a generalisation of their probabilistic counterpart that allows for replacing the local probabilities with credal sets of mass functions. For a first empirical validation, we consider a simple application based on noisy seven-segment display images.
  arXiv  Detail & Related papers  (2020-08-19T16:04:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.