Large vision-language models have recently demonstrated impressive performance in planning and control tasks, driving interest in their application to real-world robotics. However, deploying these models for reasoning in embodied contexts is limited by their ability to incorporate long-term experience collected across multiple days and represented by vast collections of images. Current VLMs typically struggle to process more than a few hundred images concurrently, highlighting the need for more efficient mechanisms to handle long-term memory in embodied settings. To effectively evaluate these models for long-horizon control, a benchmark must specifically target scenarios where memory is crucial for success. Existing long-video QA benchmarks overlook embodied challenges like object manipulation and navigation, which demand low-level skills and fine-grained reasoning over past interactions. Moreover, effective memory integration in embodied agents involves both recalling relevant historical information and executing actions based on that information, making it essential to study these aspects together rather than in isolation. In this work, we introduce a new benchmark for long-range embodied tasks in the Habitat simulator. This benchmark evaluates memory-based capabilities across 60 tasks requiring sustained engagement and contextual awareness in an environment. The tasks can also be procedurally extended to longer and more challenging versions, enabling scalable evaluation of memory and reasoning. We also present baselines that integrate state-of-the-art VLMs with low level navigation policies, assessing their performance on these memory-intensive tasks and highlight areas for improvement.

Every individual carries a unique and personal life story shaped by their memories and experiences. However, these memories are often scattered and difficult to organize into a coherent narrative, a challenge that defines the task of autobiography writing. Existing conversational writing assistants tend to rely on generic user interactions and pre-defined guidelines, making it difficult for these systems to capture personal memories and develop a complete biography over time. We introduce StorySage, a user-driven software system designed to meet the needs of a diverse group of users that supports a flexible conversation and a structured approach to autobiography writing. Powered by a multi-agent framework composed of an Interviewer, Session Scribe, Planner, Section Writer, and Session Coordinator, our system iteratively collects user memories, updates their autobiography, and plans for future conversations. In experimental simulations, StorySage demonstrates its ability to navigate multiple sessions and capture user memories across many conversations. User studies (N=28) highlight how StorySage maintains improved conversational flow, narrative completeness, and higher user satisfaction when compared to a baseline. In summary, StorySage contributes both a novel architecture for autobiography writing and insights into how multi-agent systems can enhance human-AI creative partnerships.

This paper introduces the Shepherd Test, a new conceptual test for assessing the moral and relational dimensions of superintelligent artificial agents. The test is inspired by human interactions with animals, where ethical considerations about care, manipulation, and consumption arise in contexts of asymmetric power and self-preservation. We argue that AI crosses an important, and potentially dangerous, threshold of intelligence when it exhibits the ability to manipulate, nurture, and instrumentally use less intelligent agents, while also managing its own survival and expansion goals. This includes the ability to weigh moral trade-offs between self-interest and the well-being of subordinate agents. The Shepherd Test thus challenges traditional AI evaluation paradigms by emphasizing moral agency, hierarchical behavior, and complex decision-making under existential stakes. We argue that this shift is critical for advancing AI governance, particularly as AI systems become increasingly integrated into multi-agent environments. We conclude by identifying key research directions, including the development of simulation environments for testing moral behavior in AI, and the formalization of ethical manipulation within multi-agent systems.

In group decision-making (GDM) scenarios, uncertainty, dynamic social structures, and vague information present major challenges for traditional opinion dynamics models. To address these issues, this study proposes a novel social network group decision-making (SNGDM) framework that integrates three-way decision (3WD) theory, dynamic network reconstruction, and linguistic opinion representation. First, the 3WD mechanism is introduced to explicitly model hesitation and ambiguity in agent judgments, thereby preventing irrational decisions. Second, a connection adjustment rule based on opinion similarity is developed, enabling agents to adaptively update their communication links and better reflect the evolving nature of social relationships. Third, linguistic terms are used to describe agent opinions, allowing the model to handle subjective, vague, or incomplete information more effectively. Finally, an integrated multi-agent decision-making framework is constructed, which simultaneously considers individual uncertainty, opinion evolution, and network dynamics. The proposed model is applied to a multi-UAV cooperative decision-making scenario, where simulation results and consensus analysis demonstrate its effectiveness. Experimental comparisons further verify the advantages of the algorithm in enhancing system stability and representing realistic decision-making behaviors.

Large Language Model (LLM)-based multi-agent systems (MAS) demonstrate remarkable potential for scientific discovery. Existing approaches, however, often automate scientific discovery using predefined workflows that lack rationality constraints. This often leads to aimless hypothesizing and a failure to consistently link hypotheses with evidence, thereby hindering the systematic reduction of uncertainty. Overcoming these limitations fundamentally requires a principled approach to exploration. We introduce PiFlow, an information-theoretical framework, treating automated scientific discovery as a structured uncertainty reduction problem guided by principles (e.g., scientific laws). In evaluations across three distinct scientific domains -- discovering nanomaterial structures, bio-molecules, and superconductor candidates with targeted properties -- our method significantly improves discovery efficiency, reflected by a 73.55\% increase in the Area Under the Curve (AUC) of property values versus exploration steps, and enhances solution quality by 94.06\% compared to a vanilla agent system. Overall, PiFlow serves as a Plug-and-Play method, establishing a novel paradigm shift in highly efficient automated scientific discovery, paving the way for more robust and accelerated AI-driven research. Code is publicly available at our \href{https://github.com/amair-lab/PiFlow}{GitHub}.

The Chain of Action-Planning Thoughts (CoaT) paradigm has been shown to improve the reasoning performance of VLM-based mobile agents in GUI tasks. However, the scarcity of diverse CoaT trajectories limits the expressiveness and generalization ability of such agents. While self-training is commonly employed to address data scarcity, existing approaches either overlook the correctness of intermediate reasoning steps or depend on expensive process-level annotations to construct process reward models (PRM). To address the above problems, we propose an Iterative Preference Learning (IPL) that constructs a CoaT-tree through interative sampling, scores leaf nodes using rule-based reward, and backpropagates feedback to derive Thinking-level Direct Preference Optimization (T-DPO) pairs. To prevent overfitting during warm-up supervised fine-tuning, we further introduce a three-stage instruction evolution, which leverages GPT-4o to generate diverse Q\&A pairs based on real mobile UI screenshots, enhancing both generality and layout understanding. Experiments on three standard Mobile GUI-agent benchmarks demonstrate that our agent MobileIPL outperforms strong baselines, including continual pretraining models such as OS-ATLAS and UI-TARS. It achieves state-of-the-art performance across three standard Mobile GUI-Agents benchmarks and shows strong generalization to out-of-domain scenarios.

The rapid development of Internet of Things (IoT) technologies has not only enabled new applications, but also presented new challenges for reliable communication with limited resources. In this work, we define a novel problem that can arise in these scenarios, in which a set of sensors need to communicate a joint observation. This observation is shared by a random subset of the nodes, which need to propagate it to the rest of the network, but coordination is complex: as signaling constraints require the use of random access schemes over shared channels, sensors need to implicitly coordinate, so that at least one transmission gets through without collisions. Unlike the majority of existing medium access schemes, the goal is to make sure that the shared message gets through, regardless of the sender. We analyze this coordination problem theoretically and provide low-complexity solutions. While a clustering-based approach is near-optimal if the sensors have prior knowledge, we provide a distributed multi-armed bandit (MAB) solution for the more general case and validate it by simulation.

Multi-agent systems (MAS) are increasingly capable of tackling complex real-world tasks, yet their reliance on inter-agent coordination, tool use, and long-horizon reasoning makes error recognition particularly challenging. Minor errors can propagate across agents, escalating into task failures while producing long, intertwined execution trajectories that impose significant costs for both human developers and automated systems to debug and analyze. Our key insight is that, despite surface differences in failure trajectories (e.g., logs), MAS errors often recur with similar structural patterns. This paper presents CORRECT, the first lightweight, training-free framework that leverages an online cache of distilled error schemata to recognize and transfer knowledge of failure structures across new requests. This cache-based reuse allows LLMs to perform targeted error localization at inference time, avoiding the need for expensive retraining while adapting to dynamic MAS deployments in subseconds. To support rigorous study in this domain, we also introduce CORRECT-Error, a large-scale dataset of over 2,000 annotated trajectories collected through a novel error-injection pipeline guided by real-world distributions, and further validated through human evaluation to ensure alignment with natural failure patterns. Experiments across seven diverse MAS applications show that CORRECT improves step-level error localization up to 19.8% over existing advances while at near-zero overhead, substantially narrowing the gap between automated and human-level error recognition.

Agent-based simulation is an indispensable paradigm for studying complex systems. These systems can comprise billions of agents, requiring the computing resources of multiple servers to simulate. Unfortunately, the state-of-the-art platform, BioDynaMo, does not scale out across servers due to its shared-memory-based implementation. To overcome this key limitation, we introduce TeraAgent, a distributed agent-based simulation engine. A critical challenge in distributed execution is the exchange of agent information across servers, which we identify as a major performance bottleneck. We propose two solutions: 1) a tailored serialization mechanism that allows agents to be accessed and mutated directly from the receive buffer, and 2) leveraging the iterative nature of agent-based simulations to reduce data transfer with delta encoding. Built on our solutions, TeraAgent enables extreme-scale simulations with half a trillion agents (an 84x improvement), reduces time-to-result with additional compute nodes, improves interoperability with third-party tools, and provides users with more hardware flexibility.

Scalable and realistic simulation of multi-agent traffic behavior is critical for advancing autonomous driving technologies. Although existing data-driven simulators have made significant strides in this domain, they predominantly rely on supervised learning to align simulated distributions with real-world driving scenarios. A persistent challenge, however, lies in the distributional shift that arises between training and testing, which often undermines model generalization in unseen environments. To address this limitation, we propose SMART -R1, a novel R1-style reinforcement fine-tuning paradigm tailored for next-token prediction models to better align agent behavior with human preferences and evaluation metrics. Our approach introduces a metric-oriented policy optimization algorithm to improve distribution alignment and an iterative "SFT -RFT -SFT" training strategy that alternates between Supervised Fine-Tuning (SFT) and Reinforcement Fine-Tuning (RFT) to maximize performance gains. The results on the Waymo Open Sim Agents Challenge (WOSAC) showcase that SMART -R1 achieves state-of-the-art performance with an overall realism meta score of 0.7858, ranking first on the leaderboard at the time of submission. Simulating multi-agent traffic behaviors plays a pivotal role in ensuring the safety and reliability of autonomous driving systems. However, modeling realistic and scalable traffic behaviors remains highly challenging due to the inherent uncertainty and multi-modality of human driving. Traditional simulators that simply replay logged data lack reactive capability, while rule-based methods, such as the Intelligent Driver Model (IDM) (Treiber et al., 2000), depend on handcrafted heuristics and fail to capture the diversity and realism of human behavior.