SIGMA: Structured Noise-Effect-Aware Grouped Multi-Agent Aggregation

• URL: http://arxiv.org/abs/2608.26683v1
• Date: Thu, 27 Aug 2026 06:40:42 GMT
• Title: SIGMA: Structured Noise-Effect-Aware Grouped Multi-Agent Aggregation
• Abstract summary: We propose SIGMA, a hierarchical collaboration framework that exploits cooperation structures to learn robust representations under noisy observations.<n>Experiments on noisy-observation tasks in StarCraft II empirically validate the structured noise effects and demonstrate that SIGMA consistently improves robustness under observation noise.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Cooperative multi-agent reinforcement learning (MARL) faces significant challenges in maintaining robust coordination under noisy observations. Although observation disturbances are often introduced independently across agents, their downstream effects on cooperative decision-making can become structured through underlying cooperation structures. We characterize this phenomenon as structured noise effects, where noise-induced decision effects exhibit local correlation among agents with stronger task-related dependencies while remaining globally heterogeneous across different agents and local structures. Existing robust MARL methods, however, rarely explicitly characterize or exploit such structure-dependent noise effects. To address this limitation, we propose SIGMA, a hierarchical collaboration framework that exploits cooperation structures to learn robust representations under noisy observations. SIGMA first organizes agents into adaptive local structures through density-based grouping and performs intra-group consensus aggregation to preserve shared task-relevant information while smoothing agent-specific representation deviations. Inter-group attention then adaptively integrates information across different groups to preserve global coordination while accommodating their heterogeneous contributions. Experiments on noisy-observation tasks in StarCraft II empirically validate the structured noise effects and demonstrate that SIGMA consistently improves robustness under observation noise while maintaining competitive performance in noise-free environments.

Related papers

• DCRA: Diffusion-Conditioned Representation Alignment for Robust Time-Series Learning [7.328100870402178]
  We propose a training framework that repurposes the forward diffusion process as a structured corruption scheduler for representation learning.<n>DCRA produces more balanced and structured representations compared to baseline and diffusion-only models.
  arXiv  Detail & Related papers  (2026-09-09T22:52:37Z)
• Dynamic Spectral Denoising with Global-Context Attention for Multi-Behavior Recommendation [58.33732779555114]
  We argue that the key bottleneck is a representation-level failure caused by two coupled heterogeneities.<n>We propose Dynamic Spectral Denoising with Global-Context Attention for Multi-Behavior Recommendation (SpectraMB)<n>SpectraMB achieves the best results in most evaluation settings and exhibits improved robustness under noisy interactions.
  arXiv  Detail & Related papers  (2026-06-01T15:58:13Z)
• Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments [68.02342920827135]
  We propose NoisyAgent, an agentic training framework that explicitly incorporates environmental imperfections into the agent learning process.<n>We identify two major sources of interaction noise in real-world scenarios: user noise, which captures ambiguity and variability in user interaction, and tool noise, which reflects failures and anomalies in tool execution.<n>Extensive experiments demonstrate that our approach consistently improves agent robustness under noisy and dynamic environments.
  arXiv  Detail & Related papers  (2026-05-26T16:02:00Z)
• Your CLIP has 164 dimensions of noise: Exploring the embeddings covariance eigenspectrum of contrastively pretrained vision-language transformers [0.764671395172401]
  Pre-trained Vision-Language Models (VLMs) serve as powerful feature extractors.<n>Their shared latent spaces are prone to structural anomalies and act as repositories for non-semantic, multi-modal noise.<n>We decompose the VLM latent space into a multi-modal semantic signal component and a shared noise subspace.
  arXiv  Detail & Related papers  (2026-05-14T14:37:50Z)
• Quality-Aware Robust Multi-View Clustering for Heterogeneous Observation Noise [12.720216418233795]
  We propose a novel framework termed Quality-Aware Robust Multi-View Clustering (QARMVC)<n>QARMVC employs an information bottleneck mechanism to extract intrinsic semantics for view reconstruction.<n>In experiments on five benchmark datasets, QARMVC consistently outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-02-26T03:16:44Z)
• Test-time Adaptive Hierarchical Co-enhanced Denoising Network for Reliable Multimodal Classification [55.56234913868664]
  We propose Test-time Adaptive Hierarchical Co-enhanced Denoising Network (TAHCD) for reliable learning on multimodal data.<n>The proposed method achieves superior classification performance, robustness, and generalization compared with state-of-the-art reliable multimodal learning approaches.
  arXiv  Detail & Related papers  (2026-01-12T03:14:12Z)
• Global-focal Adaptation with Information Separation for Noise-robust Transfer Fault Diagnosis [48.69961294481149]
  We propose an information separation global-focal adversarial network (ISGFAN) for cross-domain fault diagnosis under noise conditions.<n>ISGFAN is built on an information separation architecture that integrates adversarial learning with an improved loss to decouple domain-invariant fault representation.<n>Experiments conducted on three public datasets demonstrate that the proposed method outperforms other prominent existing approaches.
  arXiv  Detail & Related papers  (2025-10-16T01:13:06Z)
• Robust Spectral Fuzzy Clustering of Multivariate Time Series with Applications to Electroencephalogram [6.62414474989199]
  We introduce a fuzzy clustering framework in the spectral domain to extract frequency-specific monotonic relationships across variables.<n>Our method takes advantage of dominant frequency-based cross-regional connectivity patterns to improve clustering accuracy.<n>As a flagship application, we analyze electroencephalogram recordings, where our approach uncovers frequency- and connectivity-specific markers of latent cognitive states.
  arXiv  Detail & Related papers  (2025-06-28T12:02:01Z)
• Multi-Agent Collaboration via Evolving Orchestration [55.574417128944226]
  Large language models (LLMs) have achieved remarkable results across diverse downstream tasks, but their monolithic nature restricts scalability and efficiency in complex problem-solving.<n>We propose a puppeteer-style paradigm for LLM-based multi-agent collaboration, where a centralized orchestrator ("puppeteer") dynamically directs agents ("puppets") in response to evolving task states.<n> Experiments on closed- and open-domain scenarios show that this method achieves superior performance with reduced computational costs.
  arXiv  Detail & Related papers  (2025-05-26T07:02:17Z)
• LoSAM: Local Search in Additive Noise Models with Mixed Mechanisms and General Noise for Global Causal Discovery [2.4305626489408465]
  Local search in additive noise models, LoSAM, is a topological ordering for learning a unique DAG in ANMs with mixed causal mechanisms and general noise distributions.<n>We prove consistency and criteria, ensuring scalability and sample efficiency.
  arXiv  Detail & Related papers  (2024-10-15T16:28:55Z)
• Improving Weakly Supervised Sound Event Detection with Causal Intervention [46.229038054764956]
  Existing weakly supervised sound event detection work has not explored both types of co-occurrences simultaneously. We first establish a structural causal model (SCM) to reveal that the context is the main cause of co-occurrence confounders. Based on the causal analysis, we propose a causal intervention (CI) method for WSSED to remove the negative impact of co-occurrence confounders.
  arXiv  Detail & Related papers  (2023-03-10T03:13:36Z)
• Cross-Supervised Joint-Event-Extraction with Heterogeneous Information Networks [61.950353376870154]
  Joint-event-extraction is a sequence-to-sequence labeling task with a tag set composed of tags of triggers and entities. We propose a Cross-Supervised Mechanism (CSM) to alternately supervise the extraction of triggers or entities. Our approach outperforms the state-of-the-art methods in both entity and trigger extraction.
  arXiv  Detail & Related papers  (2020-10-13T11:51:17Z)

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.