Developing high-performance software is a complex task that requires specialized expertise. We introduce GSO, a benchmark for evaluating language models' capabilities in developing high-performance software. We develop an automated pipeline that generates and executes performance tests to analyze repository commit histories to identify 102 challenging optimization tasks across 10 codebases, spanning diverse domains and programming languages. An agent is provided with a codebase and performance test as a precise specification, and tasked to improve the runtime efficiency, which is measured against the expert developer optimization. Our quantitative evaluation reveals that leading SWE-Agents struggle significantly, achieving less than 5% success rate, with limited improvements even with inference-time scaling. Our qualitative analysis identifies key failure modes, including difficulties with low-level languages, practicing lazy optimization strategies, and challenges in accurately localizing bottlenecks. We release the code and artifacts of our benchmark along with agent trajectories to enable future research.

Graphical user interface (GUI) grounding, the ability to map natural language instructions to specific actions on graphical user interfaces, remains a critical bottleneck in computer use agent development. Current benchmarks oversimplify grounding tasks as short referring expressions, failing to capture the complexity of real-world interactions that require software commonsense, layout understanding, and fine-grained manipulation capabilities. To address these limitations, we introduce OSWorld-G, a comprehensive benchmark comprising 564 finely annotated samples across diverse task types including text matching, element recognition, layout understanding, and precise manipulation. Additionally, we synthesize and release the largest computer use grounding dataset Jedi, which contains 4 million examples through multi-perspective decoupling of tasks. Our multi-scale models trained on Jedi demonstrate its effectiveness by outperforming existing approaches on ScreenSpot-v2, ScreenSpot-Pro, and our OSWorld-G. Furthermore, we demonstrate that improved grounding with Jedi directly enhances agentic capabilities of general foundation models on complex computer tasks, improving from 5% to 27% on OSWorld. Through detailed ablation studies, we identify key factors contributing to grounding performance and verify that combining specialized data for different interface elements enables compositional generalization to novel interfaces. All benchmark, data, checkpoints, and code are open-sourced and available at https://osworld-grounding.github.io.

There is a growing need for social robots and intelligent agents that can effectively interact with and support users. For the interactions to be seamless, the agents need to analyse social scenes and behavioural cues from their (robot's) perspective. Works that model human-agent interactions in social situations are few; and even those existing ones are computationally too intensive to be deployed in real time or perform poorly in real-world scenarios when only limited information is available. We propose a knowledge distillation framework that models social interactions through various multimodal cues, and yet is robust against incomplete and noisy information during inference. We train a teacher model with multimodal input (body, face and hand gestures, gaze, raw images) that transfers knowledge to a student model which relies solely on body pose. Extensive experiments on two publicly available human-robot interaction datasets demonstrate that our student model achieves an average accuracy gain of 14.75% over competitive baselines on multiple downstream social understanding tasks, even with up to 51% of its input being corrupted. The student model is also highly efficient - less than 1% in size of the teacher model in terms of parameters and its latency is 11.9% of the teacher model. Our code and related data are available at github.com/biantongfei/SocialEgoMobile.

The growing spread of online misinformation has created an urgent need for scalable, reliable fact-checking solutions. Crowdsourced fact-checking - where non-experts evaluate claim veracity - offers a cost-effective alternative to expert verification, despite concerns about variability in quality and bias. Encouraged by promising results in certain contexts, major platforms such as X (formerly Twitter), Facebook, and Instagram have begun shifting from centralized moderation to decentralized, crowd-based approaches. In parallel, advances in Large Language Models (LLMs) have shown strong performance across core fact-checking tasks, including claim detection and evidence evaluation. However, their potential role in crowdsourced workflows remains unexplored. This paper investigates whether LLM-powered generative agents - autonomous entities that emulate human behavior and decision-making - can meaningfully contribute to fact-checking tasks traditionally reserved for human crowds. Using the protocol of La Barbera et al. (2024), we simulate crowds of generative agents with diverse demographic and ideological profiles. Agents retrieve evidence, assess claims along multiple quality dimensions, and issue final veracity judgments. Our results show that agent crowds outperform human crowds in truthfulness classification, exhibit higher internal consistency, and show reduced susceptibility to social and cognitive biases. Compared to humans, agents rely more systematically on informative criteria such as Accuracy, Precision, and Informativeness, suggesting a more structured decision-making process. Overall, our findings highlight the potential of generative agents as scalable, consistent, and less biased contributors to crowd-based fact-checking systems.

We present a novel, open-source social network simulation framework, MOSAIC, where generative language agents predict user behaviors such as liking, sharing, and flagging content. This simulation combines LLM agents with a directed social graph to analyze emergent deception behaviors and gain a better understanding of how users determine the veracity of online social content. By constructing user representations from diverse fine-grained personas, our system enables multi-agent simulations that model content dissemination and engagement dynamics at scale. Within this framework, we evaluate three different content moderation strategies with simulated misinformation dissemination, and we find that they not only mitigate the spread of non-factual content but also increase user engagement. In addition, we analyze the trajectories of popular content in our simulations, and explore whether simulation agents' articulated reasoning for their social interactions truly aligns with their collective engagement patterns. We open-source our simulation software to encourage further research within AI and social sciences.

Humans and other animals often follow the decisions made by others because these are indicative of the quality of possible choices, resulting in `social response rules': observed relationships between the probability that an agent will make a specific choice and the decisions other individuals have made. The form of social responses can be understood by considering the behaviour of rational agents that seek to maximise their expected utility using both social and private information. Previous derivations of social responses assume that agents observe all others within a group, but real interaction networks are often characterised by sparse connectivity. Here I analyse the observable behaviour of rational agents that attend to the decisions made by a subset of others in the group. This reveals an adaptive strategy in sparsely-connected networks based on highly-simplified social information: the difference in the observed number of agents choosing each option. Where agents employ this strategy, collective outcomes and decision-making efficacy are controlled by the social connectivity at the time of the decision, rather than that to which the agents are accustomed, providing an important caveat for sociality observed in the laboratory and suggesting a basis for the social dynamics of highly-connected online communities.

Large language models (LLMs) have been shown to perform better when scaffolded into agents with memory, tools, and feedback. Beyond this, self-evolving agents have emerged, but current work largely limits adaptation to prompt rewriting or failure retries. Therefore, we present ALITA-G, a self-evolution framework that transforms a general-purpose agent into a domain expert by systematically generating, abstracting, and curating Model Context Protocol (MCP) tools. In this framework, a generalist agent executes a curated suite of target-domain tasks and synthesizes candidate MCPs from successful trajectories. These are then abstracted to parameterized primitives and consolidated into an MCP Box. At inference time, ALITA-G performs retrieval-augmented MCP selection with the help of each tool's descriptions and use cases, before executing an agent equipped with the MCP Executor. Across several benchmarks GAIA, PathVQA, and Humanity's Last Exam, ALITA-G attains strong gains while reducing computation costs. On GAIA validation, it achieves 83.03% pass@1 and 89.09% pass@3, establishing a new state-of-the-art result while reducing mean tokens per example by approximately 15% relative to a strong baseline agent. ALITA-G thus provides a principled pathway from generalist capability to reusable, domain-specific competence, improving both accuracy and efficiency on complex reasoning tasks.

To understand and collaborate with humans, robots must account for individual human traits, habits, and activities over time. However, most robotic assistants lack these abilities, as they primarily focus on predefined tasks in structured environments and lack a human model to learn from. This work introduces COOPERA, a novel framework for COntinual, OPen-Ended human-Robot Assistance, where simulated humans, driven by psychological traits and long-term intentions, interact with robots in complex environments. By integrating continuous human feedback, our framework, for the first time, enables the study of long-term, open-ended human-robot collaboration (HRC) in different collaborative tasks across various time-scales. Within COOPERA, we introduce a benchmark and an approach to personalize the robot's collaborative actions by learning human traits and context-dependent intents. Experiments validate the extent to which our simulated humans reflect realistic human behaviors and demonstrate the value of inferring and personalizing to human intents for open-ended and long-term HRC. Project Page: https://dannymcy.github.io/coopera/

Autonomous agents are increasingly deployed in dynamic environments where their ability to perform a given task depends on both individual and team-level proficiency. While proficiency self-assessment (PSA) has been studied for single agents, its extension to a team of agents remains underexplored. This letter addresses this gap by presenting a framework for team PSA in centralized settings. We investigate three metrics for centralized team PSA: the measurement prediction bound (MPB), the Kolmogorov-Smirnov (KS) statistic, and the Kullback-Leibler (KL) divergence. These metrics quantify the discrepancy between predicted and actual measurements. We use the KL divergence as a reference metric since it compares the true and predictive distributions, whereas the MPB and KS provide efficient indicators for in situ assessment. Simulation results in a target tracking scenario demonstrate that both MPB and KS metrics accurately capture model mismatches, align with the KL divergence reference, and enable real-time proficiency assessment.

The growing intersection of cybersecurity and law creates a complex information space where traditional legal research tools struggle to deal with nuanced connections between cases, statutes, and technical vulnerabilities. This knowledge divide hinders collaboration between legal experts and cybersecurity professionals. To address this important gap, this work provides a first step towards intelligent systems capable of navigating the increasingly intricate cyber-legal domain. We demonstrate promising initial results on multilingual tasks.