Evaluating large language models (LLMs) in long-form, knowledge-grounded role-play dialogues remains challenging. This study compares LLM-generated and human-authored responses in multi-turn professional training simulations through human evaluation ($N=38$) and automated LLM-as-a-judge assessment. Human evaluation revealed significant degradation in LLM-generated response quality across turns, particularly in naturalness, context maintenance and overall quality, while human-authored responses progressively improved. In line with this finding, participants also indicated a consistent preference for human-authored dialogue. These human judgements were validated by our automated LLM-as-a-judge evaluation, where Gemini 2.0 Flash achieved strong alignment with human evaluators on both zero-shot pairwise preference and stochastic 6-shot construct ratings, confirming the widening quality gap between LLM and human responses over time. Our work contributes a multi-turn benchmark exposing LLM degradation in knowledge-grounded role-play dialogues and provides a validated hybrid evaluation framework to guide the reliable integration of LLMs in training simulations.

Diffusion-based large language models (DLLMs) have recently attracted growing interest as an alternative to autoregressive decoders. In this work, we present an empirical study on using the diffusion-based large language model LLaDA for automatic speech recognition (ASR). We first investigate its use as an external deliberation-based processing module for Whisper-LLaMA transcripts. By leveraging the bidirectional attention and denoising capabilities of LLaDA, we explore random masking, low-confidence masking, and semi-autoregressive strategies, showing that Whisper-LLaDA substantially reduces WER compared with the baseline. On LibriSpeech, the best cascade system achieves 2.25%/4.94% WER on test-clean/test-other, representing a 12.3% relative improvement over the Whisper-LLaMA baseline on the test-other split. In contrast, a plain-text LLaDA without acoustic features fails to improve accuracy, highlighting the importance of audio-conditioned embeddings. We further evaluate Whisper-LLaDA as a standalone decoder for ASR with diffusion-based and semi-autoregressive decoding. Most experimental configurations achieve faster inference than the Whisper-LLaMA baseline, although recognition accuracy is slightly lower. These findings offer an empirical view of diffusion-based LLMs for ASR and point to promising directions for improvements.

Human-Object Interaction Recognition (HOIR) and user identification play a crucial role in advancing augmented reality (AR)-based personalized assistive technologies. These systems are increasingly being deployed in high-stakes, human-centric environments such as aircraft cockpits, aerospace maintenance, and surgical procedures. This research introduces I2S (Interact2Sign), a multi stage framework designed for unobtrusive user identification through human object interaction recognition, leveraging 3D hand pose analysis in egocentric videos. I2S utilizes handcrafted features extracted from 3D hand poses and per forms sequential feature augmentation: first identifying the object class, followed by HOI recognition, and ultimately, user identification. A comprehensive feature extraction and description process was carried out for 3D hand poses, organizing the extracted features into semantically meaningful categories: Spatial, Frequency, Kinematic, Orientation, and a novel descriptor introduced in this work, the Inter-Hand Spatial Envelope (IHSE). Extensive ablation studies were conducted to determine the most effective combination of features. The optimal configuration achieved an impressive average F1-score of 97.52% for user identification, evaluated on a bimanual object manipulation dataset derived from the ARCTIC and H2O datasets. I2S demonstrates state-of-the-art performance while maintaining a lightweight model size of under 4 MB and a fast inference time of 0.1 seconds. These characteristics make the proposed framework highly suitable for real-time, on-device authentication in security-critical, AR-based systems.

The rapid advancement of large language models (LLMs) has blurred the line between AI-generated and human-written text. This progress brings societal risks such as misinformation, authorship ambiguity, and intellectual property concerns, highlighting the urgent need for reliable AI-generated text detection methods. However, recent advances in generative language modeling have resulted in significant overlap between the feature distributions of human-written and AI-generated text, blurring classification boundaries and making accurate detection increasingly challenging. To address the above challenges, we propose a DNA-inspired perspective, leveraging a repair-based process to directly and interpretably capture the intrinsic differences between human-written and AI-generated text. Building on this perspective, we introduce DNA-DetectLLM, a zero-shot detection method for distinguishing AI-generated and human-written text. The method constructs an ideal AI-generated sequence for each input, iteratively repairs non-optimal tokens, and quantifies the cumulative repair effort as an interpretable detection signal. Empirical evaluations demonstrate that our method achieves state-of-the-art detection performance and exhibits strong robustness against various adversarial attacks and input lengths. Specifically, DNA-DetectLLM achieves relative improvements of 5.55% in AUROC and 2.08% in F1 score across multiple public benchmark datasets. Code and data are available at https://github.com/Xiaoweizhu57/DNA-DetectLLM.

Bone health studies are crucial in medical practice for the early detection and treatment of Osteopenia and Osteoporosis. Clinicians usually make a diagnosis based on densitometry (DEXA scans) and other patient history. The applications of AI in this field are an ongoing research. Most of the successful methods for this task include Deep Learning models that rely on vision alone (DEXA / X-ray imagery) geared towards high prediction accuracy, where ex-plainability is disregarded and largely based on the post hoc assessment of input contributions. W e propose ProtoMedX, a multi-modal model that uses both DEXA scans of the lumbar spine and patient records. ProtoMedX's prototype-based architecture is explainable by design, crucial for medical applications, especially in the context of the upcoming EU AI Act, as it allows explicit analysis of the model's decisions, especially the ones that are incorrect. ProtoMedX demonstrates state-of-the-art performance in bone health classification while also providing explanations that can be visually understood by clinicians. Using our dataset of 4,160 real NHS patients, the proposed ProtoMedX achieves 87.58% accuracy in vision-only tasks and 89.8% in its multi-modal variant, both approaches surpassing existing published methods.

Large Language Model agents excel at solving complex tasks through iterative reasoning and tool use, but typically depend on ultra-large, costly backbones. Existing distillation approaches train smaller students to imitate full teacher trajectories, yet reasoning and knowledge gaps between the teacher and student can cause compounding errors. We propose SCoRe, a student-centered framework in which the student generates training trajectories and the teacher corrects only the earliest error, producing training data matched to the student's ability and exposing specific weaknesses. The student is first fine-tuned on corrected trajectories. Subsequently, short-horizon reinforcement learning starts from the verified prefix preceding the earliest error, with target rewards assigned at that step. This design encourages autonomous problem-solving beyond imitation and enhances training stability. On 12 challenging benchmarks, a 7B-parameter student distilled with SCoRe matches the agentic performance of a 72B-parameter teacher. Recent advances in Large Language Models (LLMs) have led to the rise of "agents" (Xi et al., 2025). Unlike traditional single-pass generation, LLM agents solve complex problems through an iterative reasoning-action-observation loop, using frameworks such as ReAct (Y ao et al., 2023). Specifically, LLM agents decompose tasks into sub-goals (Reasoning), execute them via external tools such as code interpreters (Action) (Gao et al., 2023), and then refine their plans based on feedback from tool execution (Observation). By combining LLM planning with the precision of external tools, agents mitigate flaws of LLMs such as hallucinations, outdated knowledge, and weak numerical reasoning, achieving strong performance on real-world interactive tasks (Liu et al., 2023).

Negotiation is a powerful tool for modelling complex interactions between self - interested agents, which can be people, companies or increasingly, AI - enabled autonomous agents, that aim to reach the best agreement for their human owners. While negotiation is often thought as a competitive process, in which one part y wins and the other one l oses, in practice most real negotiations involve more complex, win - win scenarios ( Raif fa [20]), in which agreements can be found that maximize the utilities of both agents . S uch outcomes (agreements) are called Pareto - efficient, i.e. it is not possible to find another outcome that would increase one agent's utility, without making another agent worse off. Yet, finding agreements that are Pareto - efficient is a challenging computational problem, especially in complex negotiation domains, where issues negotiated upon are interdependent (i.e. the utility of the value chosen for one negotiation issue depends strongly on the choice for other one s). Consider, for example, the negotiations between parties in a logistic supply chain: producers want to have certain combinations of resources/quantities, delivered at certain times to be able to produce their goods, whil e suppliers may face similar constraints in their cost function for supplying different combinations of items . Or the peer - to - peer negotiations between prosumers in a decentralised power grid, that require certain amounts of energy at different times and locations, which involve non - linear constraints, especially if the capacity of the distribution network is limited .

Medical image classification requires not only high predictive performance but also interpretability to ensure clinical trust and adoption. Graph Neural Networks (GNNs) offer a powerful framework for modeling relational structures within datasets; however, standard GNNs often operate as black boxes, limiting transparency and usability, particularly in clinical settings. In this work, we present an interpretable graph-based learning framework named FireGNN that integrates trainable fuzzy rules into GNNs for medical image classification. These rules embed topological descriptors - node degree, clustering coefficient, and label agreement - using learnable thresholds and sharpness parameters to enable intrinsic symbolic reasoning. Additionally, we explore auxiliary self-supervised tasks (e.g., homophily prediction, similarity entropy) as a benchmark to evaluate the contribution of topological learning. Our fuzzy-rule-enhanced model achieves strong performance across five MedMNIST benchmarks and the synthetic dataset MorphoMNIST, while also generating interpretable rule-based explanations. To our knowledge, this is the first integration of trainable fuzzy rules within a GNN. Source Code: https://github.com/basiralab/FireGNN

We present TalkPlayData 2, a synthetic dataset for multimodal conversational music recommendation generated by an agentic data pipeline. In the proposed pipeline, multiple large language model (LLM) agents are created under various roles with specialized prompts and access to different parts of information, and the chat data is acquired by logging the conversation between the Listener LLM and the Recsys LLM. To cover various conversation scenarios, for each conversation, the Listener LLM is conditioned on a finetuned conversation goal. Finally, all the LLMs are multimodal with audio and images, allowing a simulation of multimodal recommendation and conversation. In the LLM-as-a-judge and subjective evaluation experiments, TalkPlayData 2 achieved the proposed goal in various aspects related to training a generative recommendation model for music. TalkPlayData 2 and its generation code are released at https://talkpl.ai/talkplaydata2.

In this paper, we survey recent advances in Reinforcement Learning (RL) for reasoning with Large Language Models (LLMs). RL has achieved remarkable success in advancing the frontier of LLM capabilities, particularly in addressing complex logical tasks such as mathematics and coding. As a result, RL has emerged as a foundational methodology for transforming LLMs into LRMs. With the rapid progress of the field, further scaling of RL for LRMs now faces foundational challenges not only in computational resources but also in algorithm design, training data, and infrastructure. To this end, it is timely to revisit the development of this domain, reassess its trajectory, and explore strategies to enhance the scalability of RL toward Artificial SuperIntelligence (ASI). In particular, we examine research applying RL to LLMs and LRMs for reasoning abilities, especially since the release of DeepSeek-R1, including foundational components, core problems, training resources, and downstream applications, to identify future opportunities and directions for this rapidly evolving area. We hope this review will promote future research on RL for broader reasoning models. Github: https://github.com/TsinghuaC3I/Awesome-RL-for-LRMs