Large Language Models (LLMs) face a crucial challenge from fixed context windows and inadequate memory management, leading to a severe shortage of long-term memory capabilities and limited personalization in the interactive experience with AI agents. To overcome this challenge, we innovatively propose a Memory Operating System, i.e., MemoryOS, to achieve comprehensive and efficient memory management for AI agents. Inspired by the memory management principles in operating systems, MemoryOS designs a hierarchical storage architecture and consists of four key modules: Memory Storage, Updating, Retrieval, and Generation. Specifically, the architecture comprises three levels of storage units: short-term memory, mid-term memory, and long-term personal memory. Key operations within MemoryOS include dynamic updates between storage units: short-term to mid-term updates follow a dialogue-chain-based FIFO principle, while mid-term to long-term updates use a segmented page organization strategy. Our pioneering MemoryOS enables hierarchical memory integration and dynamic updating. Extensive experiments on the LoCoMo benchmark show an average improvement of 49.11% on F1 and 46.18% on BLEU-1 over the baselines on GPT-4o-mini, showing contextual coherence and personalized memory retention in long conversations. The implementation code is open-sourced at https://github.com/BAI-LAB/MemoryOS.

We aim at designing language agents with greater autonomy for crystal materials discovery. While most of existing studies restrict the agents to perform specific tasks within predefined workflows, we aim to automate workflow planning given high-level goals and scientist intuition. To this end, we propose Materials Agent unifying Planning, Physics, and Scientists, known as MAPPS. MAPPS consists of a Workflow Planner, a Tool Code Generator, and a Scientific Mediator. The Workflow Planner uses large language models (LLMs) to generate structured and multi-step workflows. The Tool Code Generator synthesizes executable Python code for various tasks, including invoking a force field foundation model that encodes physics. The Scientific Mediator coordinates communications, facilitates scientist feedback, and ensures robustness through error reflection and recovery. By unifying planning, physics, and scientists, MAPPS enables flexible and reliable materials discovery with greater autonomy, achieving a five-fold improvement in stability, uniqueness, and novelty rates compared with prior generative models when evaluated on the MP-20 data. We provide extensive experiments across diverse tasks to show that MAPPS is a promising framework for autonomous materials discovery.

Multi-agent reinforcement learning (MARL) methods have achieved state-of-the-art results on a range of multi-agent tasks. Yet, MARL algorithms typically require significantly more environment interactions than their single-agent counterparts to converge, a problem exacerbated by the difficulty in exploring over a large joint action space and the high variance intrinsic to MARL environments. To tackle these issues, we propose a novel algorithm that combines a decomposed centralized critic with decentralized ensemble learning, incorporating several key contributions. The main component in our scheme is a selective exploration method that leverages ensemble kurtosis. We extend the global decomposed critic with a diversity-regularized ensemble of individual critics and utilize its excess kurtosis to guide exploration toward high-uncertainty states and actions. To improve sample efficiency, we train the centralized critic with a novel truncated variation of the TD($λ$) algorithm, enabling efficient off-policy learning with reduced variance. On the actor side, our suggested algorithm adapts the mixed samples approach to MARL, mixing on-policy and off-policy loss functions for training the actors. This approach balances between stability and efficiency and outperforms purely off-policy learning. The evaluation shows our method outperforms state-of-the-art baselines on standard MARL benchmarks, including a variety of SMAC II maps.

The proliferation of Large Language Models (LLMs) has opened new frontiers in computing, yet controlling and orchestrating their capabilities beyond simple text generation remains a challenge. Current methods, such as function/tool calling and direct code generation, suffer from limitations in expressiveness, scalability, cost, security, and the ability to enforce fine-grained control. This paper introduces Pel, a novel programming language specifically designed to bridge this gap. Inspired by the strengths of Lisp, Elixir, Gleam, and Haskell, Pel provides a syntactically simple, homoiconic, and semantically rich platform for LLMs to express complex actions, control flow, and inter-agent communication safely and efficiently. Pel's design emphasizes a minimal, easily modifiable grammar suitable for constrained LLM generation, eliminating the need for complex sandboxing by enabling capability control at the syntax level. Key features include a powerful piping mechanism for linear composition, first-class closures enabling easy partial application and functional patterns, built-in support for natural language conditions evaluated by LLMs, and an advanced Read-Eval-Print-Loop (REPeL) with Common Lisp-style restarts and LLM-powered helper agents for automated error correction. Furthermore, Pel incorporates automatic parallelization of independent operations via static dependency analysis, crucial for performant agentic systems. We argue that Pel offers a more robust, secure, and expressive paradigm for LLM orchestration, paving the way for more sophisticated and reliable AI agentic frameworks.

Hardware security verification is a challenging and time-consuming task. For this purpose, design engineers may utilize tools such as formal verification, linters, and functional simulation tests, coupled with analysis and a deep understanding of the hardware design being inspected. Large Language Models (LLMs) have been used to assist during this task, either directly or in conjunction with existing tools. We improve the state of the art by proposing MARVEL, a multi-agent LLM framework for a unified approach to decision-making, tool use, and reasoning. MARVEL mimics the cognitive process of a designer looking for security vulnerabilities in RTL code. It consists of a supervisor agent that devises the security policy of the system-on-chips (SoCs) using its security documentation. It delegates tasks to validate the security policy to individual executor agents. Each executor agent carries out its assigned task using a particular strategy. Each executor agent may use one or more tools to identify potential security bugs in the design and send the results back to the supervisor agent for further analysis and confirmation. MARVEL includes executor agents that leverage formal tools, linters, simulation tests, LLM-based detection schemes, and static analysis-based checks. We test our approach on a known buggy SoC based on OpenTitan from the Hack@DATE competition. We find that 20 of the 48 issues reported by MARVEL pose security vulnerabilities.

Several papers have delved into the challenges of human-AI-robot co-learning and co-adaptation. It has been noted that the terminology used to describe this collaborative relationship in existing studies needs to be more consistent. For example, the prefix "co" is used interchangeably to represent both "collaborative" and "mutual," and the terms "co-learning" and "co-adaptation" are sometimes used interchangeably. However, they can reflect subtle differences in the focus of the studies. The current scoping review's primary research question (RQ1) aims to gather existing papers discussing this collaboration pattern and examine the terms researchers use to describe this human-agent relationship. Given the relative newness of this area of study, we are also keen on exploring the specific types of intelligent agents and task domains that have been considered in existing research (RQ2). This exploration is significant as it can shed light on the diversity of human-agent interactions, from one-time to continuous learning/adaptation scenarios. It can also help us understand the dynamics of human-agent interactions in different task domains, guiding our expectations towards research situated in dynamic, complex domains. Our third objective (RQ3) is to investigate the cognitive theories and frameworks that have been utilized in existing studies to measure human-agent co-learning and co-adaptation. This investigation is crucial as it can help us understand the theoretical underpinnings of human-agent collaboration and adaptation, and it can also guide us in identifying any new frameworks proposed specifically for this type of relationship.

Self-attention has emerged as a core component of modern neural architectures, yet its theoretical underpinnings remain elusive. In this paper, we study self-attention through the lens of interacting entities, ranging from agents in multi-agent reinforcement learning to alleles in genetic sequences, and show that a single layer linear self-attention can efficiently represent, learn, and generalize functions capturing pairwise interactions, including out-of-distribution scenarios. Our analysis reveals that self-attention acts as a mutual interaction learner under minimal assumptions on the diversity of interaction patterns observed during training, thereby encompassing a wide variety of real-world domains. In addition, we validate our theoretical insights through experiments demonstrating that self-attention learns interaction functions and generalizes across both population distributions and out-of-distribution scenarios. Building on our theories, we introduce HyperFeatureAttention, a novel neural network module designed to learn couplings of different feature-level interactions between entities. Furthermore, we propose HyperAttention, a new module that extends beyond pairwise interactions to capture multi-entity dependencies, such as three-way, four-way, or general n-way interactions.

Large language models can translate natural-language chart descriptions into runnable code, yet approximately 15\% of the generated scripts still fail to execute, even after supervised fine-tuning and reinforcement learning. We investigate whether this persistent error rate stems from model limitations or from reliance on a single-prompt design. To explore this, we propose a lightweight multi-agent pipeline that separates drafting, execution, repair, and judgment, using only an off-the-shelf GPT-4o-mini model. On the \textsc{Text2Chart31} benchmark, our system reduces execution errors to 4.5\% within three repair iterations, outperforming the strongest fine-tuned baseline by nearly 5 percentage points while requiring significantly less compute. Similar performance is observed on the \textsc{ChartX} benchmark, with an error rate of 4.6\%, demonstrating strong generalization. Under current benchmarks, execution success appears largely solved. However, manual review reveals that 6 out of 100 sampled charts contain hallucinations, and an LLM-based accessibility audit shows that only 33.3\% (\textsc{Text2Chart31}) and 7.2\% (\textsc{ChartX}) of generated charts satisfy basic colorblindness guidelines. These findings suggest that future work should shift focus from execution reliability toward improving chart aesthetics, semantic fidelity, and accessibility.

Multi-agent reinforcement learning algorithms are useful for simulating social behavior in settings that are too complex for other theoretical approaches like game theory. However, they have not yet been empirically supported by laboratory experiments with real human participants. In this work we demonstrate how multi-agent reinforcement learning can model group behavior in a spatially and temporally complex public good provision game called Clean Up. We show that human groups succeed in Clean Up when they can see who is who and track reputations over time but fail under conditions of anonymity. A new multi-agent reinforcement learning model of reputation-based cooperation demonstrates the same difference between identifiable and anonymous conditions. Furthermore, both human groups and artificial agent groups solve the problem via turn-taking despite other options being available. Our results highlight the benefits of using multi-agent reinforcement learning to model human social behavior in complex environments.

Multi-agent reinforcement learning, despite its popularity and empirical success, faces significant scalability challenges in large-population dynamic games. Graphon mean field games (GMFGs) offer a principled framework for approximating such games while capturing heterogeneity among players. In this paper, we propose and analyze a policy optimization framework for continuous-time, finite-horizon linear-quadratic GMFGs. Exploiting the structural properties of GMFGs, we design an efficient policy parameterization in which each player's policy is represented as an affine function of their private state, with a shared slope function and player-specific intercepts. We develop a bilevel optimization algorithm that alternates between policy gradient updates for best-response computation under a fixed population distribution, and distribution updates using the resulting policies. We prove linear convergence of the policy gradient steps to best-response policies and establish global convergence of the overall algorithm to the Nash equilibrium. The analysis relies on novel landscape characterizations over infinite-dimensional policy spaces. Numerical experiments demonstrate the convergence and robustness of the proposed algorithm under varying graphon structures, noise levels, and action frequencies.