World Model Robustness via Surprise Recognition

• URL: http://arxiv.org/abs/2512.01119v1
• Date: Sun, 30 Nov 2025 22:25:45 GMT
• Title: World Model Robustness via Surprise Recognition
• Authors: Geigh Zollicoffer, Tanush Chopra, Mingkuan Yan, Xiaoxu Ma, Kenneth Eaton, Mark Riedl,
• Abstract summary: We develop an algorithm that reduces the impact of noise in world model-based reinforcement learning agents.<n>We show that our techniques preserve performance relative to baselines under varying types and levels of noise.<n>We demonstrate that our methods enhance the stability of two state-of-the-art world models with markedly different underlying architectures.
• Score: 2.019328356430632
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: AI systems deployed in the real world must contend with distractions and out-of-distribution (OOD) noise that can destabilize their policies and lead to unsafe behavior. While robust training can reduce sensitivity to some forms of noise, it is infeasible to anticipate all possible OOD conditions. To mitigate this issue, we develop an algorithm that leverages a world model's inherent measure of surprise to reduce the impact of noise in world model--based reinforcement learning agents. We introduce both multi-representation and single-representation rejection sampling, enabling robustness to settings with multiple faulty sensors or a single faulty sensor. While the introduction of noise typically degrades agent performance, we show that our techniques preserve performance relative to baselines under varying types and levels of noise across multiple environments within self-driving simulation domains (CARLA and Safety Gymnasium). Furthermore, we demonstrate that our methods enhance the stability of two state-of-the-art world models with markedly different underlying architectures: Cosmos and DreamerV3. Together, these results highlight the robustness of our approach across world modeling domains. We release our code at https://github.com/Bluefin-Tuna/WISER .

Related papers

• AgentNoiseBench: Benchmarking Robustness of Tool-Using LLM Agents Under Noisy Condition [72.24180896265192]
  We introduce AgentNoiseBench, a framework for evaluating robustness of agentic models under noisy environments.<n>We first conduct an in-depth analysis of biases and uncertainties in real-world scenarios.<n>We then categorize environmental noise into two primary types: user-noise and tool-noise.<n>Building on this analysis, we develop an automated pipeline that injects controllable noise into existing agent-centric benchmarks.
  arXiv  Detail & Related papers  (2026-02-11T20:33:10Z)
• Noise Stability of Transformer Models [28.608164171197483]
  We argue that average sensitivity lacks a natural generalization to real-valued domains.<n>Noise stability expresses a model's robustness to correlated noise applied to coordinates simultaneously.<n>Our results sculpt a new connection between signal propagation in neural networks and interpretability.
  arXiv  Detail & Related papers  (2026-02-09T05:43:22Z)
• Explainable Transformer-CNN Fusion for Noise-Robust Speech Emotion Recognition [2.0391237204597363]
  Speech Emotion Recognition systems often degrade in performance when exposed to unpredictable acoustic interference.<n>We propose a Hybrid Transformer-CNN framework that unifies the contextual modeling of Wav2Vec 2.0 with the spectral stability of 1D-Convolutional Neural Networks.
  arXiv  Detail & Related papers  (2025-12-20T10:05:58Z)
• Ivan-ISTD: Rethinking Cross-domain Heteroscedastic Noise Perturbations in Infrared Small Target Detection [53.689841037081834]
  Ivan-ISTD is designed to address the dual challenges of cross-domain shift and heteroscedastic noise perturbations in ISTD.<n>Ivan-ISTD demonstrates excellent robustness in cross-domain scenarios.
  arXiv  Detail & Related papers  (2025-10-14T07:48:31Z)
• STORI: A Benchmark and Taxonomy for Stochastic Environments [2.8825582215429186]
  Reinforcement learning (RL) techniques have achieved impressive performance on simulated benchmarks such as Atari100k.<n>A central obstacle is environmentality, as real systems involve noisy observations, unpredictable dynamics, and non-stationary conditions.<n>We propose a comprehensive five-type taxonomy of environmentality and demonstrate systematic vulnerabilities in state-of-the-art model-based RL algorithms.
  arXiv  Detail & Related papers  (2025-09-01T21:43:22Z)
• RoHOI: Robustness Benchmark for Human-Object Interaction Detection [84.78366452133514]
  Human-Object Interaction (HOI) detection is crucial for robot-human assistance, enabling context-aware support.<n>We introduce the first benchmark for HOI detection, evaluating model resilience under diverse challenges.<n>Our benchmark, RoHOI, includes 20 corruption types based on the HICO-DET and V-COCO datasets and a new robustness-focused metric.
  arXiv  Detail & Related papers  (2025-07-12T01:58:04Z)
• AI in a vat: Fundamental limits of efficient world modelling for agent sandboxing and interpretability [84.52205243353761]
  Recent work proposes using world models to generate controlled virtual environments in which AI agents can be tested before deployment.<n>We investigate ways of simplifying world models that remain agnostic to the AI agent under evaluation.
  arXiv  Detail & Related papers  (2025-04-06T20:35:44Z)
• From Perfect to Noisy World Simulation: Customizable Embodied Multi-modal Perturbations for SLAM Robustness Benchmarking [32.52171076424419]
  Embodied agents require robust navigation systems to operate in unstructured environments. We propose a novel, customizable pipeline for noisy data synthesis. Our analysis uncovers the susceptibilities of both neural (NeRF) and non-neural SLAM models to disturbances.
  arXiv  Detail & Related papers  (2024-06-24T17:57:05Z)
• Advancing the Robustness of Large Language Models through Self-Denoised Smoothing [50.54276872204319]
  Large language models (LLMs) have achieved significant success, but their vulnerability to adversarial perturbations has raised considerable concerns. We propose to leverage the multitasking nature of LLMs to first denoise the noisy inputs and then to make predictions based on these denoised versions. Unlike previous denoised smoothing techniques in computer vision, which require training a separate model to enhance the robustness of LLMs, our method offers significantly better efficiency and flexibility.
  arXiv  Detail & Related papers  (2024-04-18T15:47:00Z)
• Customizable Perturbation Synthesis for Robust SLAM Benchmarking [33.74471840597803]
  We propose a novel, customizable pipeline for noisy data synthesis. This pipeline incorporates customizable hardware setups, software components, and perturbed environments. We instantiate the Robust-SLAM benchmark, which includes diverse perturbation types, to evaluate the risk tolerance of existing advanced SLAM models.
  arXiv  Detail & Related papers  (2024-02-12T23:49:40Z)
• Realistic Noise Synthesis with Diffusion Models [44.404059914652194]
  Deep denoising models require extensive real-world training data, which is challenging to acquire.<n>We propose a novel Realistic Noise Synthesis Diffusor (RNSD) method using diffusion models to address these challenges.
  arXiv  Detail & Related papers  (2023-05-23T12:56:01Z)
• Defensive Patches for Robust Recognition in the Physical World [111.46724655123813]
  Data-end defense improves robustness by operations on input data instead of modifying models. Previous data-end defenses show low generalization against diverse noises and weak transferability across multiple models. We propose a defensive patch generation framework to address these problems by helping models better exploit these features.
  arXiv  Detail & Related papers  (2022-04-13T07:34:51Z)

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.