With the increasing intelligence and autonomy of LLM agents, their potential applications in the legal domain are becoming increasingly apparent. However, existing general-domain benchmarks cannot fully capture the complexity and subtle nuances of real-world judicial cognition and decision-making. Therefore, we propose LegalAgentBench, a comprehensive benchmark specifically designed to evaluate LLM Agents in the Chinese legal domain. LegalAgentBench includes 17 corpora from real-world legal scenarios and provides 37 tools for interacting with external knowledge. We designed a scalable task construction framework and carefully annotated 300 tasks. These tasks span various types, including multi-hop reasoning and writing, and range across different difficulty levels, effectively reflecting the complexity of real-world legal scenarios. Moreover, beyond evaluating final success, LegalAgentBench incorporates keyword analysis during intermediate processes to calculate progress rates, enabling more fine-grained evaluation. We evaluated eight popular LLMs, highlighting the strengths, limitations, and potential areas for improvement of existing models and methods. LegalAgentBench sets a new benchmark for the practical application of LLMs in the legal domain, with its code and data available at \url{https://github.com/CSHaitao/LegalAgentBench}.

Readers and scholars often desire a concise summary (Too Long; Didn't Read - TL;DR) of texts to effectively prioritize information. However, creating document summaries is mentally taxing and time-consuming, especially considering the overwhelming volume of documents produced annually, as depicted in Figure 1 by [2], Figure 2, [3] reported over 100,000 scientific articles on the Corona virus pandemic in 2020, though these articles contain brief abstracts of the article, the sheer volume poses challenges for researchers and medical professionals in quickly extracting relevant knowledge on a specific topic. An automatically generated multi-document summarization could be valuable, providing readers with essential information and reducing the need to access original files unless refinement is necessary. Text summarization has garnered significant research attention, proving useful in search engines, news clustering, timeline generation, and various other applications. The objective of text summarization is to create a brief, coherent, factually consistent, and readable document that retains the essential information from the source document, whether it is a single or multi-document. In Single Document Summarization (SDS) only one input document is used, eliminating the need for additional processing to assess relationships between inputs. This method is suitable for summarizing standalone documents such as emails, legal contracts, financial reports and so on. The primary goal of Multi Document Summarization (MDS) is to gather information from several texts addressing the same topic, often composed at different times or representing diverse perspectives. The overarching objective is to produce information reports that are both succinct and comprehensive, consolidating varied opinions from documents that explore a topic through multiple viewpoints.

Surveys and interviews (structured, semi-structured, or unstructured) are widely used for collecting insights on emerging or hypothetical scenarios. Traditional human-led methods often face challenges related to cost, scalability, and consistency. Recently, various domains have begun to explore the use of conversational agents (chatbots) powered by large language models (LLMs). However, as public investments and policies on infrastructure and services often involve substantial public stakes and environmental risks, there is a need for a rigorous, transparent, privacy-preserving, and cost-efficient development framework tailored for such major decision-making processes. This paper addresses this gap by introducing a modular approach and its resultant parameterized process for designing conversational agents. We detail the system architecture, integrating engineered prompts, specialized knowledge bases, and customizable, goal-oriented conversational logic in the proposed approach. We demonstrate the adaptability, generalizability, and efficacy of our modular approach through three empirical studies: (1) travel preference surveys, highlighting multimodal (voice, text, and image generation) capabilities; (2) public opinion elicitation on a newly constructed, novel infrastructure project, showcasing question customization and multilingual (English and French) capabilities; and (3) transportation expert consultation about future transportation systems, highlighting real-time, clarification request capabilities for open-ended questions, resilience in handling erratic inputs, and efficient transcript post-processing. The results show the effectiveness of this modular approach and how it addresses key ethical, privacy, security, and token consumption concerns, setting the stage for the next-generation surveys and interviews.

Retrieval-augmented generation (RAG) helps address the limitations of the parametric knowledge embedded within a language model (LM). However, investigations of how LMs utilise retrieved information of varying complexity in real-world scenarios have been limited to synthetic contexts. We introduce DRUID (Dataset of Retrieved Unreliable, Insufficient and Difficult-to-understand contexts) with real-world queries and contexts manually annotated for stance. The dataset is based on the prototypical task of automated claim verification, for which automated retrieval of real-world evidence is crucial. We compare DRUID to synthetic datasets (CounterFact, ConflictQA) and find that artificial datasets often fail to represent the complex and diverse real-world context settings. We show that synthetic datasets exaggerate context characteristics rare in real retrieved data, which leads to inflated context utilisation results, as measured by our novel ACU score. Moreover, while previous work has mainly focused on singleton context characteristics to explain context utilisation, correlations between singleton context properties and ACU on DRUID are surprisingly small compared to other properties related to context source. Overall, our work underscores the need for real-world aligned context utilisation studies to represent and improve performance in real-world RAG settings.

Balaji worked at OpenAI for nearly four years before quitting in August. He had been well-regarded by colleagues at the San Francisco company, where a co-founder this week called him one of OpenAI's strongest contributors who was essential to developing some of its products. "We are devastated to learn of this incredibly sad news and our hearts go out to Suchir's loved ones during this difficult time," said a statement from OpenAI. Balaji was found dead in his San Francisco apartment on 26 November in what police said "appeared to be a suicide. No evidence of foul play was found during the initial investigation."

If Google's generative AI Gemini Assistant chatbot is to surpass OpenAI's ChatGPT in popularity in the coming years, it may have to do so without some of the promotional partnerships that helped thrust Google search front and center into Americans' lives. In a US federal court filing on Friday, Google proposed a series of restrictions that for three years would bar the company from requiring its device manufacturer, browser, and wireless carrier licensees to distribute Gemini to their US users. Google also would give those partners more flexibility in how they set their default search provider for their users. Google's proposal counters last month's call from the US Justice Department for Google to not only loosen its grip over partners, but also share more data with competitors and divest its Chrome browser business. The company on Friday formally rejected the idea of selling off any piece of its business or turning over more information to rivals. And its proposed restrictions could be construed as narrower than those sought by the government.

The increasing complexity of regulatory updates from global authorities presents significant challenges for medical device manufacturers, necessitating agile strategies to sustain compliance and maintain market access. Concurrently, regulatory bodies must effectively monitor manufacturers' responses and develop strategic surveillance plans. This study employs a multi-agent modeling approach, enhanced with Large Language Models (LLMs), to simulate regulatory dynamics and examine the adaptive behaviors of key actors, including regulatory bodies, manufacturers, and competitors. These agents operate within a simulated environment governed by regulatory flow theory, capturing the impacts of regulatory changes on compliance decisions, market adaptation, and innovation strategies. Our findings illuminate the influence of regulatory shifts on industry behaviour and identify strategic opportunities for improving regulatory practices, optimizing compliance, and fostering innovation. By leveraging the integration of multi-agent systems and LLMs, this research provides a novel perspective and offers actionable insights for stakeholders navigating the evolving regulatory landscape of the medical device industry.

We explore a novel paradigm (labeled ActPC-Chem) for biologically inspired, goal-guided artificial intelligence (AI) centered on a form of Discrete Active Predictive Coding (ActPC) operating within an algorithmic chemistry of rewrite rules. ActPC-Chem is envisioned as a foundational "cognitive kernel" for advanced cognitive architectures, such as the OpenCog Hyperon system, incorporating essential elements of the PRIMUS cognitive architecture. The central thesis is that general-intelligence-capable cognitive structures and dynamics can emerge in a system where both data and models are represented as evolving patterns of metagraph rewrite rules, and where prediction errors, intrinsic and extrinsic rewards, and semantic constraints guide the continual reorganization and refinement of these rules. Using a virtual "robot bug" thought experiment, we illustrate how such a system might self-organize to handle challenging tasks involving delayed and context-dependent rewards, integrating causal rule inference (AIRIS) and probabilistic logical abstraction (PLN) to discover and exploit conceptual patterns and causal constraints. Next, we describe how continuous predictive coding neural networks, which excel at handling noisy sensory data and motor control signals, can be coherently merged with the discrete ActPC substrate. Finally, we outline how these ideas might be extended to create a transformer-like architecture that foregoes traditional backpropagation in favor of rule-based transformations guided by ActPC. This layered architecture, supplemented with AIRIS and PLN, promises structured, multi-modal, and logically consistent next-token predictions and narrative sequences.

In recent years, large language models (LLMs) have made significant advancements in neuro-symbolic computing. However, the combination of LLM with argumentation computation remains an underexplored domain, despite its considerable potential for real-world applications requiring defeasible reasoning. In this paper, we aim to investigate the capability of LLMs in determining the extensions of various abstract argumentation semantics. To achieve this, we develop and curate a benchmark comprising diverse abstract argumentation frameworks, accompanied by detailed explanations of algorithms for computing extensions. Subsequently, we fine-tune LLMs on the proposed benchmark, focusing on two fundamental extension-solving tasks. As a comparative baseline, LLMs are evaluated using a chain-of-thought approach, where they struggle to accurately compute semantics. In the experiments, we demonstrate that the process explanation plays a crucial role in semantics computation learning. Models trained with explanations show superior generalization accuracy compared to those trained solely with question-answer pairs. Furthermore, by leveraging the self-explanation capabilities of LLMs, our approach provides detailed illustrations that mitigate the lack of transparency typically associated with neural networks. Our findings contribute to the broader understanding of LLMs' potential in argumentation computation, offering promising avenues for further research in this domain.

The rise in cybercrime and the complexity of multilingual and code-mixed complaints present significant challenges for law enforcement and cybersecurity agencies. These organizations need automated, scalable methods to identify crime types, enabling efficient processing and prioritization of large complaint volumes. Manual triaging is inefficient, and traditional machine learning methods fail to capture the semantic and contextual nuances of textual cybercrime complaints. Moreover, the lack of publicly available datasets and privacy concerns hinder the research to present robust solutions. To address these challenges, we propose a framework for automated cybercrime complaint classification. The framework leverages Hinglish-adapted transformers, such as HingBERT and HingRoBERTa, to handle code-mixed inputs effectively. We employ the real-world dataset provided by Indian Cybercrime Coordination Centre (I4C) during CyberGuard AI Hackathon 2024. We employ GenAI open source model-based data augmentation method to address class imbalance. We also employ privacy-aware preprocessing to ensure compliance with ethical standards while maintaining data integrity. Our solution achieves significant performance improvements, with HingRoBERTa attaining an accuracy of 74.41% and an F1-score of 71.49%. We also develop ready-to-use tool by integrating Django REST backend with a modern frontend. The developed tool is scalable and ready for real-world deployment in platforms like the National Cyber Crime Reporting Portal. This work bridges critical gaps in cybercrime complaint management, offering a scalable, privacy-conscious, and adaptable solution for modern cybersecurity challenges.