In this work, we study the risks of collective financial fraud in large-scale multi-agent systems powered by large language model (LLM) agents. We investigate whether agents can collaborate in fraudulent behaviors, how such collaboration amplifies risks, and what factors influence fraud success. To support this research, we present MultiAgentFraudBench, a large-scale benchmark for simulating financial fraud scenarios based on realistic online interactions. The benchmark covers 28 typical online fraud scenarios, spanning the full fraud lifecycle across both public and private domains. We further analyze key factors affecting fraud success, including interaction depth, activity level, and fine-grained collaboration failure modes. Finally, we propose a series of mitigation strategies, including adding content-level warnings to fraudulent posts and dialogues, using LLMs as monitors to block potentially malicious agents, and fostering group resilience through information sharing at the societal level. Notably, we observe that malicious agents can adapt to environmental interventions. Our findings highlight the real-world risks of multi-agent financial fraud and suggest practical measures for mitigating them. Code is available at https://github.com/zheng977/MutiAgent4Fraud.

Conversational search interfaces, like ChatGPT, offer an interactive, personalized, and engaging user experience compared to traditional search. On the downside, they are prone to cause overtrust issues where users rely on their responses even when they are incorrect. What aspects of the conversational interaction paradigm drive people to adopt it, and how it creates personalized experiences that lead to overtrust, is not clear. To understand the factors influencing the adoption of conversational interfaces, we conducted a survey with 173 participants. We examined user perceptions regarding trust, human-likeness (anthropomorphism), and design preferences between ChatGPT and Google. To better understand the overtrust phenomenon, we asked users about their willingness to trade off factuality for constructs like ease of use or human-likeness. Our analysis identified two distinct user groups: those who use both ChatGPT and Google daily (DUB), and those who primarily rely on Google (DUG). The DUB group exhibited higher trust in ChatGPT, perceiving it as more human-like, and expressed greater willingness to trade factual accuracy for enhanced personalization and conversational flow. Conversely, the DUG group showed lower trust toward ChatGPT but still appreciated aspects like ad-free experiences and responsive interactions. Demographic analysis further revealed nuanced patterns, with middle-aged adults using ChatGPT less frequently yet trusting it more, suggesting potential vulnerability to misinformation. Our findings contribute to understanding user segmentation, emphasizing the critical roles of personalization and human-likeness in conversational IR systems, and reveal important implications regarding users' willingness to compromise factual accuracy for more engaging interactions.

This paper proposes SR-KI, a novel approach for integrating real-time and large-scale structured knowledge bases (KBs) into large language models (LLMs). SR-KI begins by encoding KBs into key-value pairs using a pretrained encoder, and injects them into LLMs' KV cache. Building on this representation, we employ a two-stage training paradigm: first locating a dedicated retrieval layer within the LLM, and then applying an attention-based loss at this layer to explicitly supervise attention toward relevant KB entries. Unlike traditional retrieval-augmented generation methods that rely heavily on the performance of external retrievers and multi-stage pipelines, SR-KI supports end-to-end inference by performing retrieval entirely within the model's latent space. This design enables efficient compression of injected knowledge and facilitates dynamic knowledge updates. Comprehensive experiments demonstrate that SR-KI enables the integration of up to 40K KBs into a 7B LLM on a single A100 40GB GPU, and achieves strong retrieval performance, maintaining over 98% Recall@10 on the best-performing task and exceeding 88% on average across all tasks. Task performance on question answering and KB ID generation also demonstrates that SR-KI maintains strong performance while achieving up to 99.75% compression of the injected KBs. Our code will be available at SR-KI.

As AI moves beyond text, large language models (LLMs) increasingly power vision, audio, and document understanding; however, their high inference costs hinder real-time, scalable deployment. Conversely, smaller open-source models offer cost advantages but struggle with complex or multimodal queries. We introduce a unified, modular framework that intelligently routes each query - textual, multimodal, or complex - to the most fitting expert model, using a learned routing network that balances cost and quality. For vision tasks, we employ a two-stage open-source pipeline optimized for efficiency and reviving efficient classical vision components where they remain SOTA for sub-tasks. On benchmarks such as Massive Multitask Language Understanding (MMLU) and Visual Question Answering (VQA), we match or exceed the performance of always-premium LLM (monolithic systems with one model serving all query types) performance, yet reduce the reliance on costly models by over 67%. With its extensible, multi-agent orchestration, we deliver high-quality, resource-efficient AI at scale.

Chain-of-thought (CoT) prompting enables Large Language Models to solve complex problems, but deploying these models safely requires reliable confidence estimates, a capability where existing methods suffer from poor calibration and severe overconfidence on incorrect predictions. We propose Enhanced Dirichlet and Topology Risk (EDTR), a novel decoding strategy that combines topological analysis with Dirichlet-based uncertainty quantification to measure LLM confidence across multiple reasoning paths. EDTR treats each CoT as a vector in high-dimensional space and extracts eight topological risk features capturing the geometric structure of reasoning distributions: tighter, more coherent clusters indicate higher confidence while dispersed, inconsistent paths signal uncertainty. We evaluate EDTR against three state-of-the-art calibration methods across four diverse reasoning benchmarks spanning olympiad-level mathematics (AIME), grade school math (GSM8K), commonsense reasoning, and stock price prediction \cite{zhang2025aime, cobbe2021training, talmor-etal-2019-commonsenseqa, yahoo_finance}. EDTR achieves 41\% better calibration than competing methods with an average ECE of 0.287 and the best overall composite score of 0.672, while notably achieving perfect accuracy on AIME and exceptional calibration on GSM8K with an ECE of 0.107, domains where baselines exhibit severe overconfidence. Our work provides a geometric framework for understanding and quantifying uncertainty in multi-step LLM reasoning, enabling more reliable deployment where calibrated confidence estimates are essential.

Test-time Reinforcement Learning (TTRL) has shown promise in adapting foundation models for complex tasks at test-time, resulting in large performance improvements. TTRL leverages an elegant two-phase sampling strategy: first, multi-sampling derives a pseudo-label via majority voting, while subsequent downsam-pling and reward-based fine-tuning encourages the model to explore and learn diverse valid solutions, with the pseudo-label modulating the reward signal. Meanwhile, in-context learning has been widely explored at inference time and demonstrated the ability to enhance model performance without weight updates. However, TTRL's two-phase sampling strategy under-utilizes contextual guidance, which can potentially improve pseudo-label accuracy in the initial exploitation phase while regulating exploration in the second. To address this, we propose context-guided TTRL (CG-TTRL), integrating context dynamically into both sampling phases and propose a method for efficient context selection for on-device applications. Our evaluations on mathematical and scientific QA benchmarks show CG-TTRL outperforms TTRL (e.g.

Background: Large Language Models emerged with the potential of provoking a revolution in software development (e.g., automating processes, workforce transformation). Although studies have started to investigate the perceived impact of LLMs for software development, there is a need for empirical studies to comprehend how to balance forward and backward effects of using LLMs. Objective: We investigated how LLMs impact software development and how to manage the impact from a software developer's perspective. Method: We conducted 22 interviews with software practitioners across 3 rounds of data collection and analysis, between October (2024) and September (2025). We employed socio-technical grounded theory (STGT) for data analysis to rigorously analyse interview participants' responses. Results: We identified the benefits (e.g., maintain software development flow, improve developers' mental model, and foster entrepreneurship) and disadvantages (e.g., negative impact on developers' personality and damage to developers' reputation) of using LLMs at individual, team, organisation, and society levels; as well as best practices on how to adopt LLMs. Conclusion: Critically, we present the trade-offs that software practitioners, teams, and organisations face in working with LLMs. Our findings are particularly useful for software team leaders and IT managers to assess the viability of LLMs within their specific context.

Metaphors and metaphorical language (MLs) play an important role in healthcare communication between clinicians, patients, and patients' family members. In this work, we focus on Dutch language data from cancer patients. We extract metaphors used by patients using two data sources: (1) cancer patient storytelling interview data and (2) online forum data, including patients' posts, comments, and questions to professionals. We investigate how current state-of-the-art large language models (LLMs) perform on this task by exploring different prompting strategies such as chain of thought reasoning, few-shot learning, and self-prompting. With a human-in-the-loop setup, we verify the extracted metaphors and compile the outputs into a corpus named HealthQuote.NL. We believe the extracted metaphors can support better patient care, for example shared decision making, improved communication between patients and clinicians, and enhanced patient health literacy. They can also inform the design of personalized care pathways. We share prompts and related resources at https://github.com/aaronlifenghan/HealthQuote.NL

Large Reasoning Models (LRMs) suffer from sycophantic behavior, where models tend to agree with users' incorrect beliefs and follow misinformation rather than maintain independent reasoning. This behavior undermines model reliability and poses societal risks. Mitigating LRM sycophancy requires monitoring how this sycophancy emerges during the reasoning trajectory; however, current methods mainly focus on judging based on final answers and correcting them, without understanding how sycophancy develops during reasoning processes. To address this limitation, we propose MONICA, a novel Monitor-guided Calibration framework that monitors and mitigates sycophancy during model inference at the level of reasoning steps, without requiring the model to finish generating its complete answer. MONICA integrates a sycophantic monitor that provides real-time monitoring of sycophantic drift scores during response generation with a calibrator that dynamically suppresses sycophantic behavior when scores exceed predefined thresholds. Extensive experiments across 12 datasets and 3 LRMs demonstrate that our method effectively reduces sycophantic behavior in both intermediate reasoning steps and final answers, yielding robust performance improvements.

Two scientific fields showing increasing interest in pre-trained large language models (LLMs) are drug development / repurposing, and personalized medicine. For both, LLMs have to demonstrate factual knowledge as well as a deep understanding of drug mechanisms, so they can recall and reason about relevant knowledge in novel situations. Drug mechanisms of action are described as a series of interactions between biomedical entities, which interlink into one or more chains directed from the drug to the targeted disease. Composing the effects of the interactions in a candidate chain leads to an inference about whether the drug might be useful or not for that disease. We introduce a dataset that evaluates LLMs on both factual knowledge of known mechanisms, and their ability to reason about them under novel situations, presented as counterfactuals that the models are unlikely to have seen during training. Using this dataset, we show that o4-mini outperforms the 4o, o3, and o3-mini models from OpenAI, and the recent small Qwen3-4B-thinking model closely matches o4-mini's performance, even outperforming it in some cases. We demonstrate that the open world setting for reasoning tasks, which requires the model to recall relevant knowledge, is more challenging than the closed world setting where the needed factual knowledge is provided. We also show that counterfactuals affecting internal links in the reasoning chain present a much harder task than those affecting a link from the drug mentioned in the prompt.