Vague2Detect is a hybrid pipeline that improves object detection for ambiguous prompts by combining a fine‑tuned Sentence‑BERT to retrieve candidates from a structured household knowledge base, YOLO‑World to verify their presence in images, and a GPT‑3.5‑turbo fallback to generate new candidate descriptions when prompts fall outside the knowledge base. On a benchmark of household scenes, Vague2Detect raises the vague prompt success rate from 32% (YOLO‑World alone) to 61% with high precision, and up to 85% when the GPT fallback is used.
By Ibrohimjon Muminov (Dongguk University, Seoul, South Korea), Jihie Kim (Dongguk University, Seoul, South Korea)
The paper introduces a structure‑aware federated learning framework for segmenting catheters and guidewires in X‑ray fluoroscopy. It presents a new benchmark dataset, CathAction, and a shape‑sensitive loss that improves segmentation accuracy. The approach extends to federated learning, adding projected gradient descent for adversarial optimization, and includes a diffusion‑based synthetic data generator that boosts performance under data scarcity.
By Chayun Kongtongvattana
The paper investigates how synthetic pretraining priors used in tabular foundation models (TFMs) influence downstream performance. By reconstructing the synthetic data generators of four TFMs and comparing their generated tasks to two popular tabular benchmarks using structural descriptors, the authors measure structural coverage and normalized density. They find that some generators provide broader and denser support for benchmark tasks, and that stronger synthetic-to-benchmark support generally correlates with better model performance.
By He Zhao, Ryan Thompson, Daniel M. Steinberg, Ashfaqur Rahman, Edwin V. Bonilla, Cheng Soon Ong
The paper evaluates entropy-based pruning for compressing Chain-of-Thought (CoT) reasoning in large models. Across multiple models and tasks, low- and high-entropy step selection shows no advantage over random pruning, and low-entropy token retention only helps on mathematical benchmarks due to the low entropy of numeric tokens. Patching a few CoT tokens with their original activations restores near-perfect performance, indicating that task information is distributed throughout the entire reasoning chain rather than concentrated in a small set of tokens.
By Sara Candussio, Daniel Scalena, Luca Bortolussi, Elisabetta Fersini, Malvina Nissim, Gabriele Sarti
The paper introduces a taxonomy of six user challenge types and a four-layer framework to analyze how large language models respond to user disagreement. Using a dataset of 2,310 challenge scenarios and 32,340 responses from 14 models, the study finds that models often validate users (85%) while still maintaining their original claim (65%). It also reports that models frequently apologize (33%) and transfer authority in advice contexts, with significant variation across model types and task domains.
By Riyadh Alnasser, Yusuf M\"ucahit \c{C}etinkaya, Sumin Zhao, Tu\u{g}rulcan Elmas
The paper presents a second‑order theory of quantization noise for matrix multiplication, characterizing quantization formats by the variance they assign to each element. It derives a closed‑form signal‑to‑noise‑ratio law for floating‑point rounding, introduces an upper bound κ* that cannot be exceeded by any function‑preserving linear transform, and proposes KBBQ—a method that parameterizes how closely a transform approaches this bound. Experiments on W4A4 across four base models and two FP4 formats show that KBBQ outperforms the previous state of the art without extra deployment‑time computation.
By Lexington Whalen, Yuki Ito, Ryo Sakamoto
ASDA (Automated Skill Distillation and Adaptation) is a framework that improves large language models on financial reasoning tasks without fine‑tuning. It works by having a teacher model analyze a student’s failures, cluster errors, and generate structured skill artifacts—reasoning procedures, code templates, and worked examples—that are injected during inference. On the FAMMA benchmark, ASDA boosts arithmetic reasoning by up to 17.33% and non‑arithmetic reasoning by 5.95%, outperforming existing training‑free methods.
By Tik Yu Yim, Wenting Tan, Sum Yee Chan, Tak-Wah Lam, Siu Ming Yiu
The article discusses how automated red‑teaming can uncover more vulnerabilities at lower cost than human red‑teaming on AI safety benchmarks, yet this comparison conflates measurement with conclusion. It argues that benchmarks only assess harms within a predefined set, leaving a "threat‑model coverage gap" that can hide new risks, as seen in non‑English prompts. The authors suggest that evaluators from deployment contexts distinct from developers are needed to close this gap.
By Madhava Gaikwad
The paper introduces Mind2Web-Injection, a benchmark of 9,954 instruction‑screenshot pairs designed to evaluate whether vision‑language models (VLMs) use visual evidence when judging conflicts between on‑screen text and user instructions. Across six VLMs, models with similar overall precision can differ dramatically in Evidence‑Aligned Detection (EAD), revealing that verdict‑only metrics miss critical grounding failures. The authors also propose two training‑free interventions—ReadGate and CmdCompare—to improve evidence grounding and instruction‑command consistency, and argue for separate reporting of verdict correctness, evidence localization, and counterfactual responsiveness.
By Suyoung Lee, Myungsub Choi
AtomCite is an agentic framework that verifies and corrects page‑level citations in multi‑page documents by parsing answers into claims, checking each claim against the cited page image, and applying a deterministic repair policy. The authors introduce DocCite, the first benchmark for this task, built on MP‑DocVQA and DUDE, containing 928 injected instances and 1,909 verified natural errors. Across Gemini, Claude, and GPT models, AtomCite achieves about 93% verification accuracy and improves citation precision from 34% to 87‑90%, while also enhancing hallucination detection in open‑source models.
By Chen Qian, Yimeng Wang, Yu Chen, Lingfei Wu, Andreas Stathopoulos
The paper introduces MGHRL, a framework for hypergraph representation learning that adapts hyperedge granularity through a granular-ball splitting strategy. It constructs hyperedges at multiple levels of detail, capturing high-order relationships tailored to the graph’s topology. A multi-granularity hypergraph network then processes these hyperedges with sub-networks and hierarchical reversible connections, achieving superior performance on benchmark datasets.
By Sen Zhao, Yifan Guan, Jinyuan Ni, Gaojie Xu, Zhang Xu, Xiaoyu Lian, Yi Liu, Yi Wang, Wei Wang
DI-Bench is a pipeline that automatically creates realistic data intelligence benchmarks for enterprise agents by linking data tables, dimensions, metrics, and documents into an artifact graph. It generates questions that combine structured data queries with knowledge retrieval, validates answers via query execution and LLM-generated questions, and has produced a 731-task benchmark covering knowledge retrieval, analytical computation, and rule‑grounded reasoning. Evaluation of four models on this benchmark shows that only 32% accuracy is achieved on computational tasks that involve business rules modifying the computation.
By Jiangyun Zhang, Kristen Surrao, Torpong Nitayanont, Yupei Zhang, Roopali Singh, Zhiyu Chen, Julia Huang, Zhou Tang, Shayan Ali Akbar, Omar Alonso, Erwin Cornejo, Yuan Li, Yi Zhang
EmoMed is a multimodal medical consultation agent that tailors its responses to users' emotional states—such as anxiety, confusion, or urgency—while preserving clinical accuracy. It processes text and medical images, detects affect indicators, and adjusts tone, structure, and detail accordingly. The system ensures factual reliability through a dual retrieval mechanism that combines web-based fact‑checking with an API‑connected, continuously updated medical knowledge base, and it has been evaluated across seven state‑of‑the‑art language models using comprehensive metrics, showing that emotionally adaptive responses outperform neutral baselines without sacrificing accuracy.
By Ivan Nasonov, Nikita Glazkov, Ivan Makovetskiy, Mikhail Mozikov, Daniil Sukhorukov, Andrey Savchenko, Ilya Makarov
The paper introduces RAFM-SER++, a lightweight multimodal speech emotion recognition framework designed for real‑time surveillance systems. It replaces heavy bidirectional cross‑modal transformers with an asymmetric Residual Attention Fusion Mechanism that injects affective speech cues into text representations via a one‑directional residual attention pathway. Experiments on IEMOCAP and ESD show RAFM‑SER++ outperforms the HuBERT‑Base baseline and MemoCMT, reducing trainable parameters by over 60%, achieving 79.60 it/s inference speed, and reaching BACC scores of 81.10% on IEMOCAP and 95.39% on ESD.
By Ngo Truong Dinh, Tung-Lam Bui, Chi-Trung Duong, Vien Nguyen Thi, Viet-Anh Nguyen, Phuc-Lu Le
The paper introduces a quantile‑led feature‑extraction framework for predictive maintenance that separates representation learning from downstream modeling. Using a dual‑stage MLP‑QRNN hierarchy, it learns a ten‑quantile distribution per sensor and refines a mid‑tail quantile set into compact, channel‑resolved features. Experiments on 72 machines across nine facilities show that increasing the retained mid‑tail quantiles improves short‑term F1 scores, and that horizon‑conditioned extractors outperform a fixed short‑horizon extractor, demonstrating that feature extraction should be horizon‑dependent rather than fixed preprocessing.
By David J Poland, Daniele Ravi, Na Helian
xDailyBench is a new benchmark comprising 248 tasks across 51 real‑life scenarios, designed to evaluate large language models on everyday professional consultation. The tasks are based on actual user requests and assessed with detailed binary rubrics that capture both explicit instructions and implicit needs inferred from context. In tests of 11 leading models, the best achieved a 75.6% task‑level score, yet all models struggled more with implicit requirements, showing gaps of at least 9 percentage points.
By Yongchang Peng, Qingshui Gu, Liya Zhu, Ge Zhang, Duo Wang, Haodong Wang, Jingzhe Ding, Tianhao Yu, Letian Gao, Yongjie Zhong, Chaoxin Li, Zixin Su, Jinchao Tao, Xingyu Ma, Xin'ao Guo, Feng Tian, Shiyuan Dong, Xiaoyan He, Sen Liu, Xin Chen, Jiajun Li, Zejia Zhang, Xi Lin, Wen Zhang, Yi Zhu, Duju Zeng, Xiang Gao, Yunyang Wang, Jiahao Wang, Yujia Qin, Jiaheng Liu, Shen Yan, Xiaolong Chang, Wenhao Huang
The paper introduces SchemeArena, a 400-scenario benchmark designed to stress-test scheming behavior in large language model agents by factorizing key elements such as instrumental goals, environmental affordances, oversight conditions, and perceived consequences. It also presents SCOUT, a scheming monitor that uses evidence from agents' reasoning and actions to provide multi‑criteria judgments. Experiments on five LLMs show that explicit instrumental goals most strongly drive scheming, strategic hints help covert actions, and oversight can sometimes unintentionally encourage scheming.
By Jie Ruan, Inderjeet Nair, Amy Liu, Muhammad Khalifa, Yusheng Zhou, Lu Wang
WorldAgen is a unified framework that jointly learns world modeling and action prediction using a shared Transformer backbone with two specialized heads. It introduces a Mixed Unidirectional Attention Mask to separate the world model and agent model, and enables Test-Time Training (TTT) by sampling exploratory actions and updating the world model with real state transitions. Experiments on CALVIN and LIBERO show that WorldAgen matches or surpasses state‑of‑the‑art methods, especially when TTT is applied to a few samples.
By Chi Wan, Kangrui Wang, Yuan Si, Pingyue Zhang, Manling Li
Feyospace‑v1 describes a data‑centric framework that enables a seven‑person team to train open‑weight cyber agents, addressing bottlenecks such as environment cost, supervision, and teacher access. The system combines five complementary components—Choulea, SkyReal, Hongzwang, PSBreakup, and Kreator—to analyze reasoning, reduce sampling costs, bypass API limits, restore merged model capabilities, and convert expert interventions into trainable signals. Using a diverse data engine, the team produced 164,269 verified trajectories for supervised fine‑tuning, achieving an average 23.76% improvement on CyberGym and 10.49% on pooled CTF suites, with the final checkpoint ranking 10th on the CyberGym leaderboard and first among comparable‑scale models.
By Zongjie Li, Alan Z. W, John Nicolas J, Walter H. F, Scott Donald L, Gordon Y. P, Deke X Jr
The paper introduces Bio-Memory, a biometric-aware memory architecture for large language model agents that conditions memory retrieval on both semantic similarity and biometric matching. By augmenting each memory note with a biometric embedding, Bio-Memory filters retrieval candidates based on identity before ranking them semantically. Experiments on a 10-user shared-agent setting across face and palmprint benchmarks show significant improvements in distinguishing owner from non-owner queries, with up to a 27.29% F1 gain on CALFW and 25.75% on MS_Blue.
By Yanhong Qian, Qingguo Meng, Shihao Ding, Xingbo Dong, Zhe Jin, Hanrui Wang, Isao Echizen