The ability to model interactions among agents is crucial for effective coordination and understanding their cooperation mechanisms in multi-agent reinforcement learning (MARL). However, previous efforts to model high-order interactions have been primarily hindered by the combinatorial explosion or the opaque nature of their black-box network structures. In this paper, we propose a novel value decomposition framework, called Continued Fraction Q-Learning (QCoFr), which can flexibly capture arbitrary-order agent interactions with only linear complexity O(n) in the number of agents, thus avoiding the combinatorial explosion when modeling rich cooperation. Furthermore, we introduce the variational information bottleneck to extract latent information for estimating credits. This latent information helps agents filter out noisy interactions, thereby significantly enhancing both cooperation and interpretability. Extensive experiments demonstrate that QCoFr not only consistently achieves better performance but also provides interpretability that aligns with our theoretical analysis.

Decision trees are prized for their interpretability and strong performance on tabular data. Yet, their reliance on simple axis-aligned linear splits often forces deep, complex structures to capture non-linear feature effects, undermining human comprehension of the constructed tree. To address this limitation, we propose a novel generalization of a decision tree, the Shape Generalized Tree (SGT), in which each internal node applies a learnable axis-aligned shape function to a single feature, enabling rich, non-linear partitioning in one split. As users can easily visualize each node's shape function, SGTs are inherently interpretable and provide intuitive, visual explanations of the model's decision mechanisms. To learn SGTs from data, we propose ShapeCART, an efficient induction algorithm for SGTs. We further extend the SGT framework to bivariate shape functions (S2GT) and multi-way trees (SGTK), and present Shape2CART and ShapeCARTK, extensions to ShapeCART for learning S2GTs and SGTKs, respectively. Experiments on various datasets show that SGTs achieve superior performance with reduced model size compared to traditional axis-aligned linear trees.

Graphs are complex, non-Euclidean structures that require specialized models, such as Graph Neural Networks (GNNs), Graph Transformers, or kernel-based approaches, to effectively capture their relational patterns. This inherent complexity makes explaining GNNs decisions particularly challenging. Most existing explainable AI (XAI) methods for GNNs focus on identifying influential nodes or extracting subgraphs that highlight relevant motifs. However, these approaches often fall short of clarifying how such elements contribute to the final prediction. To overcome this limitation, logic-based explanations aim to derive explicit logical rules that reflect the model's decision-making process.

Graph Neural Networks (GNNs) excel at jointly modeling node features and topology, yet their black-box nature limits their adoption in real-world applications where interpretability is desired. Inspired by the success of interpretable Neural Additive Models (NAM) for tabular data, Graph Neural Additive Network (GNAN) extends the additive modeling approach to graph data to overcome limitations of GNNs. While being interpretable, GNAN representation learning overlooks the importance of local aggregation and more importantly suffers from parameter complexity. To mitigate the above challenges, we introduce Graph Neural Additive Model with Random Fourier Features (G-NAMRFF), a lightweight, self interpretable graph additive architecture. G-NAMRFF represents each node embedding as the sum of feature wise contributions where contributions are modeled via a Gaussian process (GP) with a graph-and feature-aware kernel. Specifically, we construct a kernel using Radial Basis Function (RBF) with graph structure induced by Laplacian and learnable Finite Impulse Response (FIR) filter. We approximate the kernel using Random Fourier Features (RFFs) which transforms the GP prior to a Bayesian formulation, which are subsequently learnt using a single layer neural network with size equal to number of RFF features. G-NAMRFF is light weight with $168\times$ fewer parameters compared to GNAN. Despite its compact size, G-NAMRFF matches or outperforms state-of-the-art GNNs and GNAN on node and graph classification tasks, delivering real-time interpretability without sacrificing accuracy.

Encoding models using word embeddings or artificial neural network (ANN) features reliably predict brain responses to naturalistic stimuli, yet interpreting these models remains challenging. A central limitation is superposition: distinct semantic features become entangled along correlated directions in dense embeddings when latent features outnumber embedding dimensions. This entanglement renders regression weights non-identifiable--different combinations of semantic directions can produce identical predictions, precluding principled interpretation of voxel selectivity. To address this, we introduce the Sparse Concept Encoding Model, which transforms dense embeddings into a higher-dimensional, sparse, non-negative space of learned concept atoms.

With the advancement of artificial intelligence (AI) and increasing integrated circuit (IC) design complexity, efficient chip design through electronic design automation (EDA) has become critical. Fast and accurate congestion prediction in chip layout and routing can significantly enhance automated design performance. Existing congestion modeling methods are limited by (i) ineffective processing and fusion of multi-view circuit data information, and (ii) insufficient reliability and interpretability in the prediction process. To address these challenges, we propose the Multi-view Interpretable Hypergraph for Chip (MIHC), a trustworthy multi-view hypergraph neural network framework that (i) processes both graph and image information in unified hypergraph representations, capturing topological and geometric circuit data; (ii) implements a novel subgraph Information Bottleneck mechanism, identifying critical congestion-correlated regions to guide predictions. This work is the first attempt to incorporate such interpretability into congestion prediction through informative graph reasoning. Experiments show that the MIHC method reduces NMAE by 16.67% and 8.57% in cell-based and grid-based predictions on ISPD2015, and 5.26% and 2.44% on CircuitNet-N28, respectively, compared to state-of-the-art methods. Rigorous cross-design generalization experiments further validate our method's capability to handle entirely unseen circuit designs.

Automated interpretability research aims to identify concepts encoded in neural network features to enhance human understanding of model behavior. Within the context of large language models (LLMs) for natural language processing (NLP), current automated neuron-level feature description methods face two key challenges: limited robustness and the assumption that each neuron encodes a single concept (monosemanticity), despite increasing evidence of polysemanticity. This assumption restricts the expressiveness of feature descriptions and limits their ability to capture the full range of behaviors encoded in model internals. To address this, we introduce Polysemantic FeatuRe Identification and Scoring Method (PRISM), a novel framework specifically designed to capture the complexity of features in LLMs. Unlike approaches that assign a single description per neuron, common in many automated interpretability methods in NLP, PRISM produces more nuanced descriptions that account for both monosemantic and polysemantic behavior. We apply PRISM to LLMs and, through extensive benchmarking against existing methods, demonstrate that our approach produces more accurate and faithful feature descriptions, improving both overall description quality (via a description score) and the ability to capture distinct concepts when polysemanticity is present (via a polysemanticity score).

Understanding the behavior of deep reinforcement learning (DRL) agents-- particularly as task and agent sophistication increase--requires more than simple comparison of reward curves, yet standard methods for behavioral analysis remain underdeveloped in DRL. We apply tools from neuroscience and ethology to study DRL agents in a novel, complex, partially observable environment, ForageWorld, designed to capture key aspects of real-world animal foraging--including sparse, depleting resource patches, predator threats, and spatially extended arenas. We use this environment as a platform for applying joint behavioral and neural analysis to agents, revealing detailed, quantitatively grounded insights into agent strategies, memory, and planning. Contrary to common assumptions, we find that modelfree RNN-based DRL agents can exhibit structured, planning-like behavior purely through emergent dynamics--without requiring explicit memory modules or world models. Our results show that studying DRL agents like animals--analyzing them with neuroethology-inspired tools that reveal structure in both behavior and neural dynamics--uncovers rich structure in their learning dynamics that would otherwise remain invisible. We distill these tools into a general analysis framework linking core behavioral and representational features to diagnostic methods, which can be reused for a wide range of tasks and agents. As agents grow more complex and autonomous, bridging neuroscience, cognitive science, and AI will be essential--not just for understanding their behavior, but for ensuring safe alignment and maximizing desirable behaviors that are hard to measure via reward. We show how this can be done by drawing on lessons from how biological intelligence is studied.

Neural networks are often described as black boxes, reflecting the significant challenge of understanding their internal workings and interactions. We propose a different perspective that challenges the prevailing view: rather than being inscrutable, neural networks exhibit patterns in their raw population activity that mirror regularities in the training data. We refer to this as the Reflection Hypothesis and provide evidence for this phenomenon in both simple recurrent neural networks (RNNs) and complex large language models (LLMs). Building on this insight, we propose to leverage our cognitive tendency of chunking to segment high-dimensional neural population dynamics into interpretable units that reflect underlying concepts. We propose three methods to extract recurring chunks on a neural population level, complementing each other based on label availability and neural data dimensionality.

How do vision transformers (ViTs) represent and process the world? This paper addresses this long-standing question through the first systematic analysis of 6.6K features across all layers, extracted via sparse autoencoders, and by introducing the residual replacement model, which replaces ViT computations with interpretable features in the residual stream. Our analysis reveals not only a feature evolution from low-level patterns to high-level semantics, but also how ViTs encode curves and spatial positions through specialized feature types. The residual replacement model scalably produces a faithful yet parsimonious circuit for human-scale interpretability by significantly simplifying the original computations. As a result, this framework enables intuitive understanding of ViT mechanisms. Finally, we demonstrate the utility of our framework in debiasing spurious correlations.