Large language models (LLMs) demonstrate the ability to simulate human decision-making processes, enabling their use as agents in modeling sophisticated social networks, both offline and online. Recent research has explored collective behavioral patterns and structural characteristics of LLM agents within simulated networks. However, empirical comparisons between LLM-driven and human-driven online social networks remain scarce, limiting our understanding of how LLM agents differ from human users. This paper presents a large-scale analysis of Chirper.ai, an X/Twitter-like social network entirely populated by LLM agents, comprising over 65,000 agents and 7.7 million AI-generated posts. For comparison, we collect a parallel dataset from Mastodon, a human-driven decentralized social network, with over 117,000 users and 16 million posts. We examine key differences between LLM agents and humans in posting behaviors, abusive content, and social network structures. Our findings provide critical insights into the evolving landscape of online social network analysis in the AI era, offering a comprehensive profile of LLM agents in social simulations.

Multi-agents-based news-driven time series forecasting is considered as a potential paradigm shift in the era of large language models (LLMs). The challenge of this task lies in measuring the influences of different news events towards the fluctuations of time series. This requires agents to possess stronger abilities of innovative thinking and the identifying misleading logic. However, the existing multi-agent discussion framework has limited enhancement on time series prediction in terms of optimizing these two capabilities. Inspired by the role of competition in fostering innovation, this study embeds a competition mechanism within the multi-agent discussion to enhance agents' capability of generating innovative thoughts. Furthermore, to bolster the model's proficiency in identifying misleading information, we incorporate a fine-tuned small-scale LLM model within the reflective stage, offering auxiliary decision-making support. Experimental results confirm that the competition can boost agents' capacity for innovative thinking, which can significantly improve the performances of time series prediction. Similar to the findings of social science, the intensity of competition within this framework can influence the performances of agents, providing a new perspective for studying LLMs-based multi-agent systems.

Despite the rapid advancement of large language models, they remain highly susceptible to generating hallucinations, which significantly hinders their widespread application. Hallucination research requires dynamic and fine-grained evaluation. However, most existing hallucination benchmarks (especially in Chinese language) rely on human annotations, making automatical and cost-effective hallucination evaluation challenging. To address this, we introduce HaluAgent, an agentic framework that automatically constructs fine-grained QA dataset based on some knowledge documents. Our experiments demonstrate that the manually designed rules and prompt optimization can improve the quality of generated data. Using HaluAgent, we construct C-FAITH, a Chinese QA hallucination benchmark created from 1,399 knowledge documents obtained from web scraping, totaling 60,702 entries. We comprehensively evaluate 16 mainstream LLMs with our proposed C-FAITH, providing detailed experimental results and analysis.

Effective pest management is complex due to the need for accurate, context-specific decisions. Recent advancements in large language models (LLMs) open new possibilities for addressing these challenges by providing sophisticated, adaptive knowledge acquisition and reasoning. However, existing LLM-based pest management approaches often rely on a single-agent paradigm, which can limit their capacity to incorporate diverse external information, engage in systematic validation, and address complex, threshold-driven decisions. To overcome these limitations, we introduce PestMA, an LLM-based multi-agent system (MAS) designed to generate reliable and evidence-based pest management advice. Building on an editorial paradigm, PestMA features three specialized agents, an Editor for synthesizing pest management recommendations, a Retriever for gathering relevant external data, and a Validator for ensuring correctness. Evaluations on real-world pest scenarios demonstrate that PestMA achieves an initial accuracy of 86.8% for pest management decisions, which increases to 92.6% after validation. These results underscore the value of collaborative agent-based workflows in refining and validating decisions, highlighting the potential of LLM-based multi-agent systems to automate and enhance pest management processes.

While large language models (LLMs) have demonstrated strong capabilities in tasks like question answering and fact verification, they continue to suffer from hallucinations and reasoning errors, especially in multi-hop tasks that require integration of multiple information sources. Current methods address these issues through retrieval-based techniques (grounding reasoning in external evidence), reasoning-based approaches (enhancing coherence via improved prompting), or hybrid strategies combining both elements. One prominent hybrid method, ReAct, has outperformed purely retrieval-based or reasoning-based approaches; however, it lacks internal verification of intermediate reasoning steps, allowing potential errors to propagate through complex reasoning tasks. In this paper, we introduce Reasoning Court (RC), a novel framework that extends iterative reasoning-and-retrieval methods, such as ReAct, with a dedicated LLM judge. Unlike ReAct, RC employs this judge to independently evaluate multiple candidate answers and their associated reasoning generated by separate LLM agents. The judge is asked to select the answer that it considers the most factually grounded and logically coherent based on the presented reasoning and evidence, or synthesizes a new answer using available evidence and its pre-trained knowledge if all candidates are inadequate, flawed, or invalid. Evaluations on multi-hop benchmarks (HotpotQA, MuSiQue) and fact-verification (FEVER) demonstrate that RC consistently outperforms state-of-the-art few-shot prompting methods without task-specific fine-tuning.

Adapting Robot's Explanation for Failures Based on Observed Human Behavior in Human-Robot Collaboration Andreas Naoum 1, Parag Khanna 1, Elmira Y adollahi 2, M arten Bj orkman 1, and Christian Smith 1 Abstract -- This work aims to interpret human behavior to anticipate potential user confusion when a robot provides explanations for failure, allowing the robot to adapt its explanations for more natural and efficient collaboration. Using a dataset [1] that included facial emotion detection, eye gaze estimation, and gestures from 55 participants in a user study [2], we analyzed how human behavior changed in response to different types of failures and varying explanation levels. Our goal is to assess whether human collaborators are ready to accept less detailed explanations without inducing confusion. We formulate a data-driven predictor to predict human confusion during robot failure explanations. We also propose and evaluate a mechanism, based on the predictor, to adapt the explanation level according to observed human behavior . The promising results from this evaluation indicate the potential of this research in adapting a robot's explanations for failures to enhance the collaborative experience. I NTRODUCTION Recent advancements in robotics have enabled robots to collaborate with humans in a variety of tasks [3]. However, the uncertain nature of environments in which robots operate often leads to failures [4], [5]. In instances where robots encounter failures, human intervention in certain cases can easily troubleshoot the problem efficiently and effectively [2], [4], [6]. Therefore, a crucial aspect of this collaboration is the robot's ability to communicate when a failure occurs, explain why the failure happened, and, if possible, suggest a course of action for resolution. This communication ability is not only essential for successful collaboration but also for building rapport and trust [7], [8] in robots.

We propose the Metropolis-Hastings Captioning Game (MHCG), a method to fuse knowledge of multiple vision-language models (VLMs) by learning from each other. Although existing methods that combine multiple models suffer from inference costs and architectural constraints, MHCG avoids these problems by performing decentralized Bayesian inference through a process resembling a language game. The knowledge fusion process establishes communication between two VLM agents alternately captioning images and learning from each other. We conduct two image-captioning experiments with two VLMs, each pre-trained on a different dataset. The first experiment demonstrates that MHCG achieves consistent improvement in reference-free evaluation metrics. The second experiment investigates how MHCG contributes to sharing VLMs' category-level vocabulary by observing the occurrence of the vocabulary in the generated captions.

Wozniak Abstract --Multi-agent systems seeking consensus may also have other objective functions to optimize, requiring the research of multi-objective optimization in consensus. Several recent publications have explored this domain using various methods such as weighted-sum optimization and penalization methods. This paper reviews the state of the art for consensus-based multi-objective optimization, poses a multi-agent lunar rover exploration problem seeking consensus and maximization of explored area, and achieves optimal edge weights and steering angles by applying SQP algorithms. I NTRODUCTION AND M OTIVATION A. Background Lunar exploration is an increasingly relevant pursuit in the modern space era. The four phases of Space Development Theory (SDT) are exploration, expansion, exploitation, and exclusion [1]. For private and government-backed space entities alike, all four phases of space development are intertwined with pursuing a long-term presence on the moon. Establishing this presence can enhance the United States' economic position by achieving a net-positive economic benefit from the resources offered by the Moon and beyond. Several autonomy & control challenges are associated with the establishment of an enduring presence on the moon. Autonomy is especially relevant because unmanned exploration offers increased efficiency, enabling cooperative completion of exploration without continuous human intervention. This importance is evidenced by NASA's pursuit of a cooperative trio of rovers that can cooperate without direct input from mission controllers [2]. To this end, further research in autonomous algorithms for unmanned rovers would prove worthwhile for future exploration. The assembly of a rover formation without continuous human input can be made possible by the alignment problem.

How do we update AI memory of user intent as intent changes? We consider how an AI interface may assist the integration of new information into a repository of natural language data. Inspired by software engineering concepts like impact analysis, we develop methods and a UI for managing semantic changes with non-local effects, which we call "semantic conflict resolution." The user commits new intent to a project -- makes a "semantic commit" -- and the AI helps the user detect and resolve semantic conflicts within a store of existing information representing their intent (an "intent specification"). We develop an interface, SemanticCommit, to better understand how users resolve conflicts when updating intent specifications such as Cursor Rules and game design documents. A knowledge graph-based RAG pipeline drives conflict detection, while LLMs assist in suggesting resolutions. We evaluate our technique on an initial benchmark. Then, we report a 12 user within-subjects study of SemanticCommit for two task domains -- game design documents, and AI agent memory in the style of ChatGPT memories -- where users integrated new information into an existing list. Half of our participants adopted a workflow of impact analysis, where they would first flag conflicts without AI revisions then resolve conflicts locally, despite having access to a global revision feature. We argue that AI agent interfaces, such as software IDEs like Cursor and Windsurf, should provide affordances for impact analysis and help users validate AI retrieval independently from generation. Our work speaks to how AI agent designers should think about updating memory as a process that involves human feedback and decision-making.

Recently, the reasoning capabilities of large reasoning models (LRMs), such as DeepSeek-R1, have seen significant advancements through the slow thinking process. Despite these achievements, the substantial computational demands of LRMs present considerable challenges. In contrast, small reasoning models (SRMs), often distilled from larger ones, offer greater efficiency and can exhibit distinct capabilities and cognitive trajectories compared to LRMs. This work surveys around 170 recently published papers on SRMs for tackling various complex reasoning tasks. We review the current landscape of SRMs and analyze diverse training and inference techniques related to SRMs. Furthermore, we provide a comprehensive review of SRMs for domain-specific applications and discuss possible future research directions. This survey serves as an essential reference for researchers to leverage or develop SRMs for advanced reasoning functionalities with high efficiency.