50 articles mentioning Reason-ModernColBERT
arXiv:2609.02191v1 Announce Type: new Abstract: Human interventions at fault points can alter the diagnostic accuracy of multi-agent medical systems. We defined fault points as moments in AI agent conversations, in which an agent's reasoning became most vulnerable to external influence. Using the Me
arXiv:2609.02336v1 Announce Type: new Abstract: Effective in-context learning (ICL) for complex reasoning relies on selecting the right demonstrations. Traditional retrieval methods based on surface similarity fail to capture the underlying problem-solving logic. Recent logic-based methods address t
arXiv:2609.01815v1 Announce Type: new Abstract: How humans grow and maintain abstract knowledge from the sparse, streaming noisy data of experience is a longstanding challenge in cognitive science. Any computational account must satisfy at least three desiderata: It must be (1) data-efficient and co
arXiv:2603.19539v2 Announce Type: replace-cross Abstract: We introduce an expert curated, real-world benchmark for evaluating document-grounded question-answering (QA) motivated by generic drug assessment, using the U.S. Food and Drug Administration (FDA) drug label documents. Drug labels contain ri
arXiv:2609.02702v1 Announce Type: new Abstract: Transformers process information causally, but long-context reasoning may depend on task state discovered only later. We formalize this mismatch through conditional state update tasks. For causal state update processors, providing the condition first c
arXiv:2602.22453v3 Announce Type: replace Abstract: Recent work has identified a subset of attention heads in Transformer as retrieval heads, which are responsible for retrieving information from the context. In this work, we first investigate retrieval heads in multilingual contexts. In multilingua
arXiv:2609.02060v1 Announce Type: new Abstract: Mineral exploration requires integrating heterogeneous geochemical, geophysical, and geological evidence, yet existing prospectivity systems often provide only opaque scores or heatmaps. We present MineTRACE, a web-based system for evidence-grounded ex
arXiv:2609.01867v1 Announce Type: cross Abstract: A major question in cognitive modeling concerns the behavioral alignment between large language models and humans across linguistic and non-linguistic tasks. Unlike standard LLMs, large reasoning models (LRMs) are optimized with reinforcement learnin
arXiv:2605.29496v2 Announce Type: replace Abstract: Post-training has greatly improved reasoning in frontier vision-language models, yet its gains for perception remain comparatively limited, creating a bottleneck for end-to-end visual reasoning. To investigate this gap, we introduce a controlled di
arXiv:2602.02028v3 Announce Type: replace Abstract: Enabling artificial intelligence systems, particularly large language models, to update knowledge and flexibly apply it during reasoning remains a central challenge. Existing knowledge editing approaches emphasize atomic facts, improving factual re
arXiv:2505.23713v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in socially grounded applications, where success requires interpreting context, inferring others' mental states, and reasoning about unreliable information. Yet existing benchmarks rarely evalu
arXiv:2605.24661v4 Announce Type: replace Abstract: Despite remarkable progress on reasoning benchmarks, current LLM evaluation practice remains anchored to final-answer correctness, providing limited insight into how models reason, how reliably they behave under contextual variation, or how efficie
arXiv:2609.01659v1 Announce Type: cross Abstract: Chain-of-thought (CoT) reasoning powers generative models by eliciting intermediate steps before producing an answer. In autonomous driving, the answer is a continuous action. Thus its reasoning must share the same spatiotemporal structure as the phy
arXiv:2512.15662v4 Announce Type: replace Abstract: Human beings solve complex problems through critical thinking, where reasoning and evaluation are intertwined to converge toward correct solutions. However, most existing large language models (LLMs) treat the reasoning and verification as separate
arXiv:2607.27287v2 Announce Type: replace Abstract: Planning over Temporal Dynamic Knowledge Graphs (TDKGs) presents theoretical challenges in open-world environments with incomplete information. Existing action formalisms often face decidability issues and the Ramification Problem, while structural
arXiv:2608.26550v2 Announce Type: replace Abstract: Reinforcement learning-based knowledge distillation has the potential to transfer complex reasoning from teacher to student models, yet it currently faces a critical dilemma: researchers must choose between sparse outcome-based rewards, which provi
arXiv:2609.02059v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved strong performance on structured visual understanding tasks such as chart and document question answering. However, existing benchmarks typically evaluate these domains in isolation, leaving undere
arXiv:2609.02270v1 Announce Type: cross Abstract: Generating safety-critical scenarios is essential for evaluating autonomous driving systems. However, existing generators primarily focus on inducing collisions and offer limited control over where contact occurs on the target vehicle. In this paper,
arXiv:2607.20129v2 Announce Type: replace Abstract: Quantized small reasoning models can enter repetitive or otherwise unproductive trajectories, yet standard decoding does not adapt to the trajectory as it unfolds. We study MGT-B, a fixed, weight-preserving controller that converts overlapping wind
arXiv:2606.23092v2 Announce Type: replace Abstract: Humans possess an innate ability to understand fine-grained interpersonal relationships, which is central to everyday social interactions. Although such reasoning is inherently multimodal, it remains largely unexplored by existing multimodal large
arXiv:2609.02805v1 Announce Type: new Abstract: Root cause analysis (RCA) is a critical task in telecom network operations, but diagnosing performance degradations in modern 5G and emerging 6G networks remains challenging due to complex cross-layer dependencies. While large language models (LLMs) of
arXiv:2505.15276v2 Announce Type: replace Abstract: Large reasoning models (LRMs) have achieved remarkable success on complex tasks, yet their tendency to "overthink" leads to inefficiencies. Although "save-thinking" prompts are intended to mitigate this issue, we find that LRMs still frequently ent
arXiv:2609.02131v1 Announce Type: cross Abstract: Sentiment in social-media threads does not only vary across posts; it shifts as users react to claims, corrections, evidence, and hostility within a branching reply tree. We study why sentiment changes in rumor-centric conversation trees by treating
arXiv:2603.25184v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become essential for post-training large language models (LLMs) in reasoning tasks. While scaling rollouts can stabilize training and enhance performance, the computational overhead is a critical issue. In algo
OpenAI’s new Astra model will use “recurrent depth,” a technique that allows the model to operate outside of the sequential thinking that characterizes most reasoning models.
arXiv:2609.00177v1 Announce Type: cross Abstract: General-purpose NLP embedding models perform well on linguistic tasks, but their ability to capture symbolic ontological structure remains unclear. We introduce AVA, a systematic framework for evaluating whether embeddings distinguish logic-sensitive
arXiv:2605.17026v2 Announce Type: replace Abstract: Recent progress in large language models has led to the emergence of reasoning models, which have shown strong performance on complex tasks through specialized fine-tuning procedures. While these methods reliably improve pass@1 accuracy, prior work
arXiv:2609.00342v1 Announce Type: new Abstract: Whole-slide images (WSIs) are challenging for vision-language reasoning because diagnostically relevant morphology is sparse, heterogeneous, and distributed across gigapixel-scale images and multiple spatial resolutions. Existing WSI models and patholo
arXiv:2609.01532v1 Announce Type: new Abstract: Logit-based knowledge distillation (KD) is used to train smaller language models (LMs) via supervision from stronger teachers, but whether its benefits are consistent across training stages remains unclear. Through controlled experiments, we find that
arXiv:2609.00413v1 Announce Type: new Abstract: Chain of thought prompting improves complex reasoning, but its long intermediate traces create substantial inference cost and hinder practical deployment in financial settings. We present a Hierarchical Semantic Distillation Network, HSDN, for compress
arXiv:2609.00879v1 Announce Type: new Abstract: Reliable disaster damage assessment requires models that provide both accurate predictions and transparent explanations. However, existing multimodal approaches are limited by scarce annotated data and insufficient evaluation of reasoning quality. This
arXiv:2608.16421v2 Announce Type: replace Abstract: This article presents an ontology-supported approach to tackle the complexity of the Robustness Validation (RV) process of automotive electrical/electronic (E/E) components. The approach uses formalized knowledge from the RV process and stress, ope
arXiv:2609.01449v1 Announce Type: new Abstract: Diffusion models and recursive reasoners are both iterative, but they carry information across iterations differently. We add a persistent hidden state to a diffusion denoiser and remove its timestep conditioning, leaving a single shared update that ca
arXiv:2606.28164v2 Announce Type: replace-cross Abstract: Echocardiography is the most widely used non-invasive cardiac imaging modality, providing essential information for cardiovascular diagnosis. Interpreting an echocardiogram requires synthesizing complementary evidence across multiple heart vi
arXiv:2601.06853v3 Announce Type: replace Abstract: Chain-of-Thought (CoT) prompting is widely adopted for mathematical problem solving, including in low-resource languages, yet its behavior under irrelevant context remains underexplored. To systematically study this challenge, we introduce DISTRACT
arXiv:2609.01274v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) improves language-model reasoning, but how these gains relate to inference-time decoding and search remains unclear. Does RL create reasoning the base model lacks, or shift the rollout distribution
arXiv:2609.00099v1 Announce Type: new Abstract: Corrosion accounts for approximately 4% of global GDP, and reliable prediction is essential for timely mitigation. Machine learning effectively predicts corrosion rates from composition, microstructure, and environmental variables, but cannot explain t
arXiv:2601.21174v3 Announce Type: replace Abstract: Entity alignment (EA) is critical for knowledge graph (KG) fusion. Existing EA models lack transferability and are incapable of aligning unseen KGs without retraining. While using graph foundation models (GFMs) offer a solution, we find that direct
arXiv:2608.30751v2 Announce Type: replace Abstract: Large language models (LLMs) trained only on text and code can sometimes generate programs that draw recognizable images. However, it is unclear whether this reflects an internal representation of 2D spatial layout or simply the ability to translat
arXiv:2606.02010v2 Announce Type: replace-cross Abstract: Existing LLM graph benchmarks typically ask models to answer graph-theoretic questions or compute symbolic solutions rather than construct spatial layouts. Within-task difficulty is also primarily stratified by vertex count. However, existing
arXiv:2506.13502v4 Announce Type: replace Abstract: Next-word prediction (NWP) trains language models against a single observed continuation, even though many contexts admit multiple plausible next words. Recent RL-based next-word reasoning methods make this tension explicit: they reward a model for
arXiv:2608.21863v2 Announce Type: replace-cross Abstract: Tool-Integrated Reasoning (TIR) is a fundamental capability for LLM agents to solve complex tasks by interacting with external tools iteratively. Reinforcement Learning (RL) has become the dominant paradigm for enabling this capability. Howev
arXiv:2606.17524v3 Announce Type: replace Abstract: Large language models show strong reasoning ability, but their internal reasoning process can remain unstable in complex multi-step settings, where early hidden-state errors may propagate to incorrect predictions. We propose ReLAR, a reinforcement-
arXiv:2609.01111v1 Announce Type: new Abstract: Clinical LLM assistants must reason over multi-visit patient trajectories, yet whether the compact history representations used to scale them---retrieval, structured timelines, LLM summaries, agentic memory---preserve the longitudinal signal clinical r
arXiv:2510.15144v4 Announce Type: replace Abstract: Simulating human reasoning in open-ended tasks has long been a central aspiration in AI and cognitive science. While large language models now approximate human responses at scale, they remain tuned to population-level consensus, often erasing the
arXiv:2609.00738v1 Announce Type: new Abstract: Inference-time search with large language models (LLMs) often concentrates on a small set of structurally or semantically similar trajectories, leaving alternatives underexplored---a failure mode we call \textit{reasoning basin collapse}. We introduce
arXiv:2603.10359v2 Announce Type: replace Abstract: Distilling reasoning capabilities from Large Reasoning Models (LRMs) into smaller models is typically constrained by the limitations of rejection sampling. Standard methods treat the teacher as a static filter, discarding complex "corner-case" prob
arXiv:2608.31075v2 Announce Type: replace Abstract: Recent advances in large reasoning models (LRMs) have shown that reinforcement learning with verifiable rewards (RLVR) can substantially improve reasoning in mathematics and code, where outcomes can be checked automatically. Extending this progress
arXiv:2606.29150v3 Announce Type: replace Abstract: Structured reasoning requires making and revising interdependent decisions to reach a globally consistent solution. Existing architectures struggle with this: autoregressive models commit sequentially and cannot revise earlier decisions, while mask
arXiv:2512.05658v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) with reasoning capabilities have recently demonstrated strong potential in medical Question Answering (QA). Existing approaches are largely English-focused and primarily rely on distillation from general-purpose L