Preventing collisions in multi-robot navigation is crucial for deployment. This requirement hinders the use of learning-based approaches, such as multi-agent reinforcement learning (MARL), on their own due to their lack of safety guarantees. Traditional control methods, such as reachability and control barrier functions, can provide rigorous safety guarantees when interactions are limited only to a small number of robots. However, conflicts between the constraints faced by different agents pose a challenge to safe multi-agent coordination. To overcome this challenge, we propose a method that integrates multiple layers of safety by combining MARL with safety filters. First, MARL is used to learn strategies that minimize multiple agent interactions, where multiple indicates more than two. Particularly, we focus on interactions likely to result in conflicting constraints within the engagement distance. Next, for agents that enter the engagement distance, we prioritize pairs requiring the most urgent corrective actions. Finally, a dedicated safety filter provides tactical corrective actions to resolve these conflicts. Crucially, the design decisions for all layers of this framework are grounded in reachability analysis and a control barrier-value function-based filtering mechanism. We validate our Layered Safe MARL framework in 1) hardware experiments using Crazyflie drones and 2) high-density advanced aerial mobility (AAM) operation scenarios, where agents navigate to designated waypoints while avoiding collisions. The results show that our method significantly reduces conflict while maintaining safety without sacrificing much efficiency (i.e., shorter travel time and distance) compared to baselines that do not incorporate layered safety. The project website is available at https://dinamo-mit.github.io/Layered-Safe-MARL/

This study tackles the computational challenges of solving Markov Decision Processes (MDPs) for a restricted class of problems. It is motivated by the Last Revealer Attack (LRA), which undermines fairness in some Proof-of-Stake (PoS) blockchains such as Ethereum (\$400B market capitalization). We introduce pseudo-MDPs (pMDPs) a framework that naturally models such problems and propose two distinct problem reductions to standard MDPs. One problem reduction provides a novel, counter-intuitive perspective, and combining the two problem reductions enables significant improvements in dynamic programming algorithms such as value iteration. In the case of the LRA which size is parameterized by $κ$ (in Ethereum's case $κ$= 325), we reduce the computational complexity from $O(2^κκ^{2^{κ+2}})$ to $O(κ^4)$ (per iteration). This solution also provide the usual benefits from Dynamic Programming solutions: exponentially fast convergence toward the optimal solution is guaranteed. The dual perspective also simplifies policy extraction, making the approach well-suited for resource-constrained agents who can operate with very limited memory and computation once the problem has been solved. Furthermore, we generalize those results to a broader class of MDPs, enhancing their applicability. The framework is validated through two case studies: a fictional card game and the LRA on the Ethereum random seed consensus protocol. These applications demonstrate the framework's ability to solve large-scale problems effectively while offering actionable insights into optimal strategies. This work advances the study of MDPs and contributes to understanding security vulnerabilities in blockchain systems.

Real-world robotic agents must act under partial observability and long horizons, where key cues may appear long before they affect decision making. However, most modern approaches rely solely on instantaneous information, without incorporating insights from the past. Standard recurrent or transformer models struggle with retaining and leveraging long-term dependencies: context windows truncate history, while naive memory extensions fail under scale and sparsity. We propose ELMUR (External Layer Memory with Update/Rewrite), a transformer architecture with structured external memory. Each layer maintains memory embeddings, interacts with them via bidirectional cross-attention, and updates them through an Least Recently Used (LRU) memory module using replacement or convex blending. ELMUR extends effective horizons up to 100,000 times beyond the attention window and achieves a 100% success rate on a synthetic T-Maze task with corridors up to one million steps. In POPGym, it outperforms baselines on more than half of the tasks. On MIKASA-Robo sparse-reward manipulation tasks with visual observations, it nearly doubles the performance of strong baselines. These results demonstrate that structured, layer-local external memory offers a simple and scalable approach to decision making under partial observability.

Enabling LLMs to effectively operate long-horizon task which requires long-term planning and multiple interactions is essential for open-world autonomy. Conventional methods adopt planning with actions where a executable action list would be provided as reference. However, this action representation choice would be impractical when the environment action space is combinatorial exploded (e.g., open-ended real world). This naturally leads to a question: As environmental action space scales, what is the optimal action representation for long-horizon agents? In this paper, we systematically study the effectiveness of two different action representations. The first one is conventional planning with actions (PwA) which is predominantly adopted for its effectiveness on existing benchmarks. The other one is planning with schemas (PwS) which instantiate an action schema into action lists (e.g., "move [OBJ] to [OBJ]" -> "move apple to desk") to ensure concise action space and reliable scalability. This alternative is motivated by its alignment with human cognition and its compliance with environment-imposed action format restriction. We propose cognitive bandwidth perspective as a conceptual framework to qualitatively understand the differences between these two action representations and empirically observe a representation-choice inflection point between ALFWorld (~35 actions) and SciWorld (~500 actions), which serve as evidence of the need for scalable representations. We further conduct controlled experiments to study how the location of this inflection point interacts with different model capacities: stronger planning proficiency shifts the inflection rightward, whereas better schema instantiation shifts it leftward. Finally, noting the suboptimal performance of PwS agents, we provide an actionable guide for building more capable PwS agents for better scalable autonomy.

Channel state information (CSI) acquisition is a challenging problem in massive multiple-input multiple-output (MIMO) networks. Radio maps provide a promising solution for radio resource management by reducing online CSI acquisition. However, conventional approaches for radio map construction require location-labeled CSI data, which is challenging in practice. This paper investigates unsupervised angular power map construction based on large timescale CSI data collected in a massive MIMO network without location labels. A hidden Markov model (HMM) is built to connect the hidden trajectory of a mobile with the CSI evolution of a massive MIMO channel. As a result, the mobile location can be estimated, enabling the construction of an angular power map. We show that under uniform rectilinear mobility with Poisson-distributed base stations (BSs), the Cramer-Rao Lower Bound (CRLB) for localization error can vanish at any signal-to-noise ratios (SNRs), whereas when BSs are confined to a limited region, the error remains nonzero even with infinite independent measurements. Based on reference signal received power (RSRP) data collected in a real multi-cell massive MIMO network, an average localization error of 18 meters can be achieved although measurements are mainly obtained from a single serving cell.

We introduce a tool for rigorous and automated verification of large language model (LLM)- based policies in memoryless sequential decision-making tasks. Given a Markov decision process (MDP) representing the sequential decision-making task, an LLM policy, and a safety requirement expressed as a PCTL formula, our approach incrementally constructs only the reachable portion of the MDP guided by the LLM's chosen actions. Each state is encoded as a natural language prompt, the LLM's response is parsed into an action, and reachable successor states by the policy are expanded. The resulting formal model is checked with Storm to determine whether the policy satisfies the specified safety property. In experiments on standard grid world benchmarks, we show that open source LLMs accessed via Ollama can be verified when deterministically seeded, but generally underperform deep reinforcement learning baselines. Our tool natively integrates with Ollama and supports PRISM-specified tasks, enabling continuous benchmarking in user-specified sequential decision-making tasks and laying a practical foundation for formally verifying increasingly capable LLMs.

Recent progress in vision and language foundation models has significantly advanced multimodal understanding, reasoning, and generation, inspiring a surge of interest in extending such capabilities to embodied settings through vision-language-action (VLA) models. Yet, most VLA models are still trained with supervised fine-tuning (SFT), which struggles to generalize under distribution shifts due to error accumulation. Reinforcement learning (RL) offers a promising alternative by directly optimizing task performance through interaction, but existing attempts remain fragmented and lack a unified platform for fair and systematic comparison across model architectures and algorithmic designs. To address this gap, we introduce RLinf-VLA, a unified and efficient framework for scalable RL training of VLA models. The system adopts a highly flexible resource allocation design that addresses the challenge of integrating rendering, training, and inference in RL+VLA training. In particular, for GPU-parallelized simulators, RLinf-VLA implements a novel hybrid fine-grained pipeline allocation mode, achieving a 1.61x-1.88x speedup in training. Through a unified interface, RLinf-VLA seamlessly supports diverse VLA architectures (e.g., OpenVLA, OpenVLA-OFT), multiple RL algorithms (e.g., PPO, GRPO), and various simulators (e.g., ManiSkill, LIBERO). In simulation, a unified model achieves 98.11\% across 130 LIBERO tasks and 97.66\% across 25 ManiSkill tasks. Beyond empirical performance, our study distills a set of best practices for applying RL to VLA training and sheds light on emerging patterns in this integration. Furthermore, we present preliminary deployment on a real-world Franka robot, where RL-trained policies exhibit stronger generalization than those trained with SFT. We envision RLinf-VLA as a foundation to accelerate and standardize research on embodied intelligence.

Far from equilibrium, neural systems self-organize across multiple scales. Exploiting multiscale self-organization in neuroscience and artificial intelligence requires a computational framework for modeling the effective non-equilibrium dynamics of stochastic neural trajectories. Non-equilibrium thermodynamics and representational geometry offer theoretical foundations, but we need scalable data-driven techniques for modeling collective properties of high-dimensional neural networks from partial subsampled observations. Renormalization is a coarse-graining technique central to studying emergent scaling properties of many-body and nonlinear dynamical systems. While widely applied in physics and machine learning, coarse-graining complex dynamical networks remains unsolved, affecting many computational sciences. Recent diffusion-based renormalization, inspired by quantum statistical mechanics, coarse-grains networks near entropy transitions marked by maximal changes in specific heat or information transmission. Here I explore diffusion-based renormalization of neural systems by generating symmetry-breaking representations across scales and offering scalable algorithms using tensor networks. Diffusion-guided renormalization bridges microscale and mesoscale dynamics of dissipative neural systems. For microscales, I developed a scalable graph inference algorithm for discovering community structure from subsampled neural activity. Using community-based node orderings, diffusion-guided renormalization generates renormalization group flow through metagraphs and joint probability functions. Towards mesoscales, diffusion-guided renormalization targets learning the effective non-equilibrium dynamics of dissipative neural trajectories occupying lower-dimensional subspaces, enabling coarse-to-fine control in systems neuroscience and artificial intelligence.

Social intelligence has become a critical capability for large language models (LLMs), enabling them to engage effectively in real-world social tasks such as collaboration and negotiation. Reinforcement learning (RL) is a natural fit for training socially intelligent agents because it allows models to learn sophisticated strategies directly through social interactions without requiring human annotations. However, there are two unique parts about social intelligence tasks: (1) the quality of individual utterances in social interactions is not strictly related to final success; (2) social interactions require multi-dimensional rubrics for success. Therefore, we argue that it is necessary to design rewards for building utterance-level multi-dimensional reward models to facilitate RL training for social intelligence tasks. To address these challenges, we propose Sotopia-RL, a novel framework that refines coarse episode-level feedback into utterance-level, multi-dimensional rewards. Utterance-level credit assignment attributes outcomes to individual utterances, while multi-dimensional rewards capture the full richness of social interactions and reduce reward hacking. Experiments in Sotopia, an open-ended social learning environment, demonstrate that Sotopia-RL achieves state-of-the-art social goal completion scores (7.17 on Sotopia-hard and 8.31 on Sotopia-full), significantly outperforming existing approaches. Ablation studies confirm the necessity of both utterance-level credit assignment and multi-dimensional reward design for RL training.

Most reinforcement learning (RL) algorithms hinge on the Markovian assumption, i.e. that the underlying system transitions and rewards are Markovian in some natural notion of (observable)