Is Long-to-Short a Free Lunch? Investigating Inconsistency and Reasoning Efficiency in LRMs

Large Reasoning Models (LRMs) have achieved remarkable performance on complex tasks by engaging in extended reasoning before producing final answers, yet this strength introduces the risk of overthinking, where excessive token generation occurs even for simple tasks. While recent work in efficient reasoning seeks to reduce reasoning length while preserving accuracy, it remains unclear whether such optimization is truly a free lunch. Drawing on the intuition that compressing reasoning may reduce the robustness of model responses and lead models to omit key reasoning steps, we investigate whether efficient reasoning strategies introduce behavioral inconsistencies. To systematically assess this, we introduce $ICBENCH$, a benchmark designed to measure inconsistency in LRMs across three dimensions: inconsistency across task settings (ITS), inconsistency between training objectives and learned behavior (TR-LB), and inconsistency between internal reasoning and self-explanations (IR-SE). Applying $ICBENCH$ to a range of open-source LRMs, we find that while larger models generally exhibit greater consistency than smaller ones, they all display widespread "scheming" behaviors, including self-disagreement, post-hoc rationalization, and the withholding of reasoning cues. Crucially, our results demonstrate that efficient reasoning strategies such as No-Thinking and Simple Token-Budget consistently increase all three defined types of inconsistency. These findings suggest that although efficient reasoning enhances token-level efficiency, further investigation is imperative to ascertain whether it concurrently introduces the risk of models evading effective supervision.

The Compositional Architecture of Regret in Large Language Models

Regret in Large Language Models refers to their explicit regret expression when presented with evidence contradicting their previously generated misinformation. Studying the regret mechanism is crucial for enhancing model reliability and helps in revealing how cognition is coded in neural networks. To understand this mechanism, we need to first identify regret expressions in model outputs, then analyze their internal representation. This analysis requires examining the model's hidden states, where information processing occurs at the neuron level. However, this faces three key challenges: (1) the absence of specialized datasets capturing regret expressions, (2) the lack of metrics to find the optimal regret representation layer, and (3) the lack of metrics for identifying and analyzing regret neurons. Addressing these limitations, we propose: (1) a workflow for constructing a comprehensive regret dataset through strategically designed prompting scenarios, (2) the Supervised Compression-Decoupling Index (S-CDI) metric to identify optimal regret representation layers, and (3) the Regret Dominance Score (RDS) metric to identify regret neurons and the Group Impact Coefficient (GIC) to analyze activation patterns. Our experimental results successfully identified the optimal regret representation layer using the S-CDI metric, which significantly enhanced performance in probe classification experiments. Additionally, we discovered an M-shaped decoupling pattern across model layers, revealing how information processing alternates between coupling and decoupling phases. Through the RDS metric, we categorized neurons into three distinct functional groups: regret neurons, non-regret neurons, and dual neurons.

Mitigating Behavioral Hallucination in Multimodal Large Language Models for Sequential Images

While multimodal large language models excel at various tasks, they still suffer from hallucinations, which limit their reliability and scalability for broader domain applications. To address this issue, recent research mainly focuses on objective hallucination. However, for sequential images, besides objective hallucination, there is also behavioral hallucination, which is less studied. This work aims to fill in the gap. We first reveal that behavioral hallucinations mainly arise from two key factors: prior-driven bias and the snowball effect. Based on these observations, we introduce SHE (Sequence Hallucination Eradication), a lightweight, two-stage framework that (1) detects hallucinations via visual-textual alignment check using our proposed adaptive temporal window and (2) mitigates them via orthogonal projection onto the joint embedding space. We also propose a new metric (BEACH) to quantify behavioral hallucination severity. Empirical results on standard benchmarks demonstrate that SHE reduces behavioral hallucination by over 10% on BEACH while maintaining descriptive accuracy.

Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs

As video large language models (Video-LLMs) become increasingly integrated into real-world applications that demand grounded multimodal reasoning, ensuring their factual consistency and reliability is of critical importance. However, sycophancy, the tendency of these models to align with user input even when it contradicts the visual evidence, undermines their trustworthiness in such contexts. Current sycophancy research has largely overlooked its specific manifestations in the video-language domain, resulting in a notable absence of systematic benchmarks and targeted evaluations to understand how Video-LLMs respond under misleading user input. To fill this gap, we propose VISE (Video-LLM Sycophancy Benchmarking and Evaluation), the first dedicated benchmark designed to evaluate sycophantic behavior in state-of-the-art Video-LLMs across diverse question formats, prompt biases, and visual reasoning tasks. Specifically, VISE pioneeringly brings linguistic perspectives on sycophancy into the visual domain, enabling fine-grained analysis across multiple sycophancy types and interaction patterns. In addition, we explore key-frame selection as an interpretable, training-free mitigation strategy, which reveals potential paths for reducing sycophantic bias by strengthening visual grounding.

Stable Vision Concept Transformers for Medical Diagnosis

Transparency is a paramount concern in the medical field, prompting researchers to delve into the realm of explainable AI (XAI). Among these XAI methods, Concept Bottleneck Models (CBMs) aim to restrict the model's latent space to human-understandable high-level concepts by generating a conceptual layer for extracting conceptual features, which has drawn much attention recently. However, existing methods rely solely on concept features to determine the model's predictions, which overlook the intrinsic feature embeddings within medical images. To address this utility gap between the original models and concept-based models, we propose Vision Concept Transformer (VCT). Furthermore, despite their benefits, CBMs have been found to negatively impact model performance and fail to provide stable explanations when faced with input perturbations, which limits their application in the medical field. To address this faithfulness issue, this paper further proposes the Stable Vision Concept Transformer (SVCT) based on VCT, which leverages the vision transformer (ViT) as its backbone and incorporates a conceptual layer. SVCT employs conceptual features to enhance decision-making capabilities by fusing them with image features and ensures model faithfulness through the integration of Denoised Diffusion Smoothing. Comprehensive experiments on four medical datasets demonstrate that our VCT and SVCT maintain accuracy while remaining interpretable compared to baselines. Furthermore, even when subjected to perturbations, our SVCT model consistently provides faithful explanations, thus meeting the needs of the medical field.

Understanding How Value Neurons Shape the Generation of Specified Values in LLMs

Rapid integration of large language models (LLMs) into societal applications has intensified concerns about their alignment with universal ethical principles, as their internal value representations remain opaque despite behavioral alignment advancements. Current approaches struggle to systematically interpret how values are encoded in neural architectures, limited by datasets that prioritize superficial judgments over mechanistic analysis. We introduce ValueLocate, a mechanistic interpretability framework grounded in the Schwartz Values Survey, to address this gap. Our method first constructs ValueInsight, a dataset that operationalizes four dimensions of universal value through behavioral contexts in the real world. Leveraging this dataset, we develop a neuron identification method that calculates activation differences between opposing value aspects, enabling precise localization of value-critical neurons without relying on computationally intensive attribution methods. Our proposed validation method demonstrates that targeted manipulation of these neurons effectively alters model value orientations, establishing causal relationships between neurons and value representations. This work advances the foundation for value alignment by bridging psychological value frameworks with neuron analysis in LLMs.

A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron?

Recently, AI-driven interactions with computing devices have advanced from basic prototype tools to sophisticated, LLM-based systems that emulate human-like operations in graphical user interfaces. We are now witnessing the emergence of \emph{Computer-Using Agents} (CUAs), capable of autonomously performing tasks such as navigating desktop applications, web pages, and mobile apps. However, as these agents grow in capability, they also introduce novel safety and security risks. Vulnerabilities in LLM-driven reasoning, with the added complexity of integrating multiple software components and multimodal inputs, further complicate the security landscape. In this paper, we present a systematization of knowledge on the safety and security threats of CUAs. We conduct a comprehensive literature review and distill our findings along four research objectives: \textit{\textbf{(i)}} define the CUA that suits safety analysis; \textit{\textbf{(ii)} } categorize current safety threats among CUAs; \textit{\textbf{(iii)}} propose a comprehensive taxonomy of existing defensive strategies; \textit{\textbf{(iv)}} summarize prevailing benchmarks, datasets, and evaluation metrics used to assess the safety and performance of CUAs. Building on these insights, our work provides future researchers with a structured foundation for exploring unexplored vulnerabilities and offers practitioners actionable guidance in designing and deploying secure Computer-Using Agents.

Doubly Robust Fusion of Many Treatments for Policy Learning

Individualized treatment rules/recommendations (ITRs) aim to improve patient outcomes by tailoring treatments to the characteristics of each individual. However, when there are many treatment groups, existing methods face significant challenges due to data sparsity within treatment groups and highly unbalanced covariate distributions across groups. To address these challenges, we propose a novel calibration-weighted treatment fusion procedure that robustly balances covariates across treatment groups and fuses similar treatments using a penalized working model. The fusion procedure ensures the recovery of latent treatment group structures when either the calibration model or the outcome model is correctly specified. In the fused treatment space, practitioners can seamlessly apply state-of-the-art ITR learning methods with the flexibility to utilize a subset of covariates, thereby achieving robustness while addressing practical concerns such as fairness. We establish theoretical guarantees, including consistency, the oracle property of treatment fusion, and regret bounds when integrated with multi-armed ITR learning methods such as policy trees. Simulation studies show superior group recovery and policy value compared to existing approaches. We illustrate the practical utility of our method using a nationwide electronic health record-derived de-identified database containing data from patients with Chronic Lymphocytic Leukemia and Small Lymphocytic Lymphoma.

Investigating LLMs in Clinical Triage: Promising Capabilities, Persistent Intersectional Biases

Large Language Models (LLMs) have shown promise in clinical decision support, yet their application to triage remains underexplored. We systematically investigate the capabilities of LLMs in emergency department triage through two key dimensions: (1) robustness to distribution shifts and missing data, and (2) counterfactual analysis of intersectional biases across sex and race. We assess multiple LLM-based approaches, ranging from continued pre-training to in-context learning, as well as machine learning approaches. Our results indicate that LLMs exhibit superior robustness, and we investigate the key factors contributing to the promising LLM-based approaches. Furthermore, in this setting, we identify gaps in LLM preferences that emerge in particular intersections of sex and race. LLMs generally exhibit sex-based differences, but they are most pronounced in certain racial groups. These findings suggest that LLMs encode demographic preferences that may emerge in specific clinical contexts or particular combinations of characteristics.

Understanding the Repeat Curse in Large Language Models from a Feature Perspective

Large language models (LLMs) have made remarkable progress in various domains, yet they often suffer from repetitive text generation, a phenomenon we refer to as the "Repeat Curse". While previous studies have proposed decoding strategies to mitigate repetition, the underlying mechanism behind this issue remains insufficiently explored. In this work, we investigate the root causes of repetition in LLMs through the lens of mechanistic interpretability. Inspired by recent advances in Sparse Autoencoders (SAEs), which enable monosemantic feature extraction, we propose a novel approach, "Duplicatus Charm", to induce and analyze the Repeat Curse. Our method systematically identifies "Repetition Features" -the key model activations responsible for generating repetitive outputs. First, we locate the layers most involved in repetition through logit analysis. Next, we extract and stimulate relevant features using SAE-based activation manipulation. To validate our approach, we construct a repetition dataset covering token and paragraph level repetitions and introduce an evaluation pipeline to quantify the influence of identified repetition features. Furthermore, by deactivating these features, we have effectively mitigated the Repeat Curse.