Recent advances in agent development have focused on scaling model size and raw interaction data, mirroring successes in large language models. However, for complex, long-horizon multi-agent tasks such as robotic soccer, this end-to-end approach often fails due to intractable exploration spaces and sparse rewards. We propose that an effective world model for decision-making must model the world's physics and also its task semantics. A systematic review of 2024 research in low-resource multi-agent soccer reveals a clear trend towards integrating symbolic and hierarchical methods, such as Hierarchical Task Networks (HTNs) and Bayesian Strategy Networks (BSNs), with multi-agent reinforcement learning (MARL). These methods decompose complex goals into manageable subgoals, creating an intrinsic curriculum that shapes agent learning. We formalize this trend into a framework for Hierarchical Task Environments (HTEs), which are essential for bridging the gap between simple, reactive behaviors and sophisticated, strategic team play. Our framework incorporates the use of Large Language Models (LLMs) as generative world models of tasks, capable of dynamically generating this scaffolding. We argue that HTEs provide a mechanism to guide exploration, generate meaningful learning signals, and train agents to internalize hierarchical structure, enabling the development of more capable and general-purpose agents with greater sample efficiency than purely end-to-end approaches.

The capacity of an embodied agent to understand, predict, and interact with its environment is fundamentally contingent on an internal world model. This paper introduces a novel framework for investigating the formation and adaptation of such world models within a biological substrate: human neural organoids. We present a curriculum of three scalable, closed-loop virtual environments designed to train these biological agents and probe the underlying synaptic mechanisms of learning, such as long-term potentiation (LTP) and long-term depression (LTD). We detail the design of three distinct task environments that demand progressively more sophisticated world models for successful decision-making: (1) a conditional avoidance task for learning static state-action contingencies, (2) a one-dimensional predator-prey scenario for goal-directed interaction, and (3) a replication of the classic Pong game for modeling dynamic, continuous-time systems. For each environment, we formalize the state and action spaces, the sensory encoding and motor decoding mechanisms, and the feedback protocols based on predictable (reward) and unpredictable (punishment) stimulation, which serve to drive model refinement. In a significant methodological advance, we propose a meta-learning approach where a Large Language Model automates the generative design and optimization of experimental protocols, thereby scaling the process of environment and curriculum design. Finally, we outline a multi-modal evaluation strategy that moves beyond task performance to directly measure the physical correlates of the learned world model by quantifying synaptic plasticity at electrophysiological, cellular, and molecular levels. This work bridges the gap between model-based reinforcement learning and computational neuroscience, offering a unique platform for studying embodiment, decision-making, and the physical basis of intelligence.

Lexical alignment, where speakers start to use similar words across conversation, is known to contribute to successful communication. However, its implementation in conversational agents remains underexplored, particularly considering the recent advancements in large language models (LLMs). As a first step towards enabling lexical alignment in human-agent dialogue, this study draws on strategies for personalising conversational agents and investigates the construction of stable, personalised lexical profiles as a basis for lexical alignment. Specifically, we varied the amounts of transcribed spoken data used for construction as well as the number of items included in the profiles per part-of-speech (POS) category and evaluated profile performance across time using recall, coverage, and cosine similarity metrics. It was shown that smaller and more compact profiles, created after 10 min of transcribed speech containing 5 items for adjectives, 5 items for conjunctions, and 10 items for adverbs, nouns, pronouns, and verbs each, offered the best balance in both performance and data efficiency. In conclusion, this study offers practical insights into constructing stable, personalised lexical profiles, taking into account minimal data requirements, serving as a foundational step toward lexical alignment strategies in conversational agents.

This paper introduces an algorithm to select demonstration examples for in-context learning of a query set. Given a set of $n$ examples, how can we quickly select $k$ out of $n$ to best serve as the conditioning for downstream inference? This problem has broad applications in prompt tuning and chain-of-thought reasoning. Since model weights remain fixed during in-context learning, previous work has sought to design methods based on the similarity of token embeddings. This work proposes a new approach based on gradients of the output taken in the input embedding space. Our approach estimates model outputs through a first-order approximation using the gradients. Then, we apply this estimation to multiple randomly sampled subsets. Finally, we aggregate the sampled subset outcomes to form an influence score for each demonstration, and select $k$ most relevant examples. This procedure only requires pre-computing model outputs and gradients once, resulting in a linear-time algorithm relative to model and training set sizes. Extensive experiments across various models and datasets validate the efficiency of our approach. We show that the gradient estimation procedure yields approximations of full inference with less than ${1}\%$ error across six datasets. This allows us to scale up subset selection that would otherwise run full inference by up to ${37.7}\times$ on models with up to $34$ billion parameters, and outperform existing selection methods based on input embeddings by ${11}\%$ on average.

Large Language Model (LLM)-based agents are increasingly deployed in multi-agent scenarios where coordination is crucial but not always assured. Research shows that the way strategic scenarios are framed linguistically can affect cooperation. This paper explores whether allowing agents to communicate amplifies these language-driven effects. Leveraging FAIRGAME, we simulate one-shot and repeated games across different languages and models, both with and without communication. Our experiments, conducted with two advanced LLMs-GPT-4o and Llama 4 Maverick-reveal that communication significantly influences agent behavior, though its impact varies by language, personality, and game structure. These findings underscore the dual role of communication in fostering coordination and reinforcing biases.

Event cameras offer microsecond-level latency and robustness to motion blur, making them ideal for understanding dynamic environments. Yet, connecting these asynchronous streams to human language remains an open challenge. We introduce Talk2Event, the first large-scale benchmark for language-driven object grounding in event-based perception. Built from real-world driving data, we provide over 30,000 validated referring expressions, each enriched with four grounding attributes -- appearance, status, relation to viewer, and relation to other objects -- bridging spatial, temporal, and relational reasoning. To fully exploit these cues, we propose EventRefer, an attribute-aware grounding framework that dynamically fuses multi-attribute representations through a Mixture of Event-Attribute Experts (MoEE). Our method adapts to different modalities and scene dynamics, achieving consistent gains over state-of-the-art baselines in event-only, frame-only, and event-frame fusion settings. We hope our dataset and approach will establish a foundation for advancing multimodal, temporally-aware, and language-driven perception in real-world robotics and autonomy.

The rapid adoption of Large Language Model (LLM) agents and multi-agent systems enables remarkable capabilities in natural language processing and generation. However, these systems introduce security vulnerabilities that extend beyond traditional content generation to system-level compromises. This paper presents a comprehensive evaluation of the LLMs security used as reasoning engines within autonomous agents, highlighting how they can be exploited as attack vectors capable of achieving computer takeovers. We focus on how different attack surfaces and trust boundaries can be leveraged to orchestrate such takeovers. We demonstrate that adversaries can effectively coerce popular LLMs into autonomously installing and executing malware on victim machines. Our evaluation of 18 state-of-the-art LLMs reveals an alarming scenario: 94.4% of models succumb to Direct Prompt Injection, and 83.3% are vulnerable to the more stealthy and evasive RAG Backdoor Attack. Notably, we tested trust boundaries within multi-agent systems, where LLM agents interact and influence each other, and we revealed that LLMs which successfully resist direct injection or RAG backdoor attacks will execute identical payloads when requested by peer agents. We found that 100.0% of tested LLMs can be compromised through Inter-Agent Trust Exploitation attacks, and that every model exhibits context-dependent security behaviors that create exploitable blind spots.

Sequence generation and prediction form a cornerstone of modern machine learning, with applications spanning natural language processing, program synthesis, and time-series forecasting. These tasks are typically modeled in an autoregressive fashion, where each token is generated conditional on the preceding ones, and beam search is commonly used to balance exploration and fluency during decoding. While deep learning models and Large Language Models (LLMs) excel at capturing statistical patterns in this setting, they remain ill-equipped to guarantee compliance with formal constraints. In this paper, we introduce ABS: a general and model-agnostic inference-time algorithm that guarantees compliance with any constraint that can be compiled into a Deterministic Finite Automaton (DFA), without requiring retraining. ABS leverages the DFA to guide a constrained variant of beam search: at each decoding step, transitions leading to violations are masked, while remaining paths are dynamically re-ranked according to both the model's probabilities and the automaton's acceptance structure. We formally prove that the resulting sequences are guaranteed to satisfy the given constraints, and we empirically demonstrate that ABS also improves output quality. We validate our approach on three distinct tasks: constrained image-stream classification, controlled text generation, and text infilling. In all settings, ABS achieves perfect constraint satisfaction, while outperforming or matching state-of-the-art baselines on standard quality metrics and efficiency.

Large Language Models (LLMs) have achieved impressive performance in diverse natural language processing tasks, but specialized domains such as Web3 present new challenges and require more tailored evaluation. Despite the significant user base and capital flows in Web3, encompassing smart contracts, decentralized finance (DeFi), non-fungible tokens (NFTs), decentralized autonomous organizations (DAOs), on-chain governance, and novel token-economics, no comprehensive benchmark has systematically assessed LLM performance in this domain. To address this gap, we introduce the DMind Benchmark, a holistic Web3-oriented evaluation suite covering nine critical subfields: fundamental blockchain concepts, blockchain infrastructure, smart contract, DeFi mechanisms, DAOs, NFTs, token economics, meme concept, and security vulnerabilities. Beyond multiple-choice questions, DMind Benchmark features domain-specific tasks such as contract debugging and on-chain numeric reasoning, mirroring real-world scenarios. We evaluated 26 models, including ChatGPT, Claude, DeepSeek, Gemini, Grok, and Qwen, uncovering notable performance gaps in specialized areas like token economics and security-critical contract analysis. While some models excel in blockchain infrastructure tasks, advanced subfields remain challenging. Our benchmark dataset and evaluation pipeline are open-sourced on https://huggingface.co/datasets/DMindAI/DMind_Benchmark, reaching number one in Hugging Face's trending dataset charts within a week of release.

Mixture of Experts (MoE) pretraining is more scalable than dense Transformer pretraining, because MoEs learn to route inputs to a sparse set of their feedforward parameters. However, this means that MoEs only receive a sparse backward update, leading to training instability and suboptimal performance. We present a lightweight approximation method that gives the MoE router a dense gradient update while continuing to sparsely activate its parameters. Our method, which we refer to as Default MoE, substitutes missing expert activations with default outputs consisting of an exponential moving average of expert outputs previously seen over the course of training. This allows the router to receive signals from every expert for each token, leading to significant improvements in training performance. Our Default MoE outperforms standard TopK routing in a variety of settings without requiring significant computational overhead. Code: https://github.com/vatsal0/default-moe.