50 articles mentioning Reason-ModernColBERT
On Friday, Chinese AI firm DeepSeek released a preview of V4, its long-awaited new flagship model. Notably, the model can process much longer prompts than its last generation, thanks to a new design that helps it handle large amounts of text more efficiently. Like DeepSeek’s previous models, V4 is o
arXiv:2510.01857v3 Announce Type: replace Abstract: Current approaches to improving reasoning in large language models (LLMs) primarily rely on either supervised fine-tuning (SFT) over expert traces or reinforcement learning (RL) with outcome-level rewards. However, SFT is fundamentally imitative, w
arXiv:2604.21593v1 Announce Type: new Abstract: As LLMs reduce English-centric bias, a surprising trend emerges: non-English responses sometimes outperform English on reasoning tasks. We hypothesize that language functions as a latent variable that structurally modulates the model's internal inferen
arXiv:2604.20869v1 Announce Type: cross Abstract: Background: More than 80% of U.S. cancer care is delivered in community settings, where survival remains worse than at academic centers. Clinicians must integrate genomics, staging, radiology, pathology, and changing guidelines, creating cognitive bu
arXiv:2604.21357v1 Announce Type: new Abstract: This paper proposes ReaGeo, an end-to-end geocoding framework based on large language models, designed to overcome the limitations of traditional multi-stage approaches that rely on text or vector similarity retrieval over geographic databases, includi
arXiv:2604.21501v1 Announce Type: new Abstract: Lithology classification in well logs is a fundamental geoscience data mining task that aims to infer rock types from multi dimensional geophysical sequences. Despite recent progress, existing approaches typically formulate the problem as a static, sin
arXiv:2604.21444v1 Announce Type: new Abstract: Long-form video understanding remains fundamentally challenged by pervasive spatiotemporal redundancy and intricate narrative dependencies that span extended temporal horizons. While recent structured representations compress visual information effecti
arXiv:2604.21584v1 Announce Type: new Abstract: Feature discovery from complex unstructured data is fundamentally a reasoning problem: it requires identifying abstractions that are predictive of a target outcome while avoiding leakage, proxies, and post-outcome signals. With the introduction of ever
arXiv:2604.21632v1 Announce Type: new Abstract: We investigate the ability of decoder-only transformer models to perform abstract symbolic reasoning; specifically solving propositional logic reasoning problems given in-context. Previous work demonstrated that models fail to generalize to problems in
arXiv:2604.20891v1 Announce Type: cross Abstract: Memristive crossbars store numerical weights needing aggregation and decoding; a single junction means nothing alone. This paper presents a fundamentally different use: each junction stores a complete, domain-scoped logical assertion (holds/negated/u
arXiv:2604.21611v1 Announce Type: cross Abstract: Inference-time scaling for LLM reasoning has focused on three axes: chain depth, sample breadth, and learned step-scorers (PRMs). We introduce a fourth axis, granularity of external verbal supervision, via Verbal Process Supervision (VPS), a training
arXiv:2604.08016v2 Announce Type: replace Abstract: Regardless of its foundational role in human discovery and sense-making, abductive reasoning--the inference of the most plausible explanation for an observation--has been relatively underexplored in Large Language Models (LLMs). Despite the rapid a
arXiv:2512.19995v2 Announce Type: replace-cross Abstract: Large language models increasingly expose reasoning traces, yet their underlying cognitive structure and steps remain difficult to identify and analyze beyond surface-level statistics. We adopt Schoenfeld's Episode Theory as an inductive, int
arXiv:2604.21057v1 Announce Type: new Abstract: The field of Language Reasoning Models (LRMs) has been very active over the past few years with advances in training and inference techniques enabling LRMs to reason longer, and more accurately. However, a growing body of studies show that LRMs are sti
arXiv:2604.20917v1 Announce Type: cross Abstract: Large language models (LLMs) have shown remarkable capabilities across diverse coding tasks. However, their adoption requires a true understanding of program execution rather than relying on surface-level patterns. Existing benchmarks primarily focus
arXiv:2603.27820v2 Announce Type: replace Abstract: Clinical diagnosis is a complex reasoning process in which clinicians gather evidence, form hypotheses, and test them against alternative explanations. In medical training, this reasoning is explicitly developed through counterfactual questioning--
arXiv:2604.21137v1 Announce Type: cross Abstract: Analyzing the reasoning patterns of students in science classrooms is critical for understanding knowledge construction mechanism and improving instructional practice to maximize cognitive engagement, yet manual coding of classroom discourse at scale
arXiv:2604.21253v1 Announce Type: cross Abstract: While LLMs demonstrate remarkable fluency in narrative generation, existing methods struggle to maintain global narrative coherence, contextual logical consistency, and smooth character development, often producing monotonous scripts with structural
arXiv:2604.20659v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has advanced the reasoning capabilities of Large Language Models (LLMs) by leveraging direct outcome verification instead of learned reward models. Building on this paradigm, Group Relative Policy O
arXiv:2604.21396v1 Announce Type: cross Abstract: The advancement of Large Vision-Language Models (LVLMs) requires precise local region-based reasoning that faithfully grounds the model's logic in actual visual evidence. However, existing datasets face limitations in scalability due to extensive man
arXiv:2604.20098v1 Announce Type: new Abstract: Large Language Models (LLMs) frequently hallucinate, limiting their reliability in critical applications. Conformal Prediction (CP) addresses this by calibrating error rates on held-out data to provide statistically valid confidence guarantees. Recent
arXiv:2604.20904v1 Announce Type: cross Abstract: Information handling practices of LLM agents are broadly misaligned with the contextual privacy expectations of their users. Contextual Integrity (CI) provides a principled framework, defining privacy as the appropriate flow of information within con
arXiv:2604.20254v1 Announce Type: cross Abstract: Text-guided molecular design is a key capability for AI-driven drug discovery, yet it remains challenging to map sequential natural-language instructions with non-linear molecular structures under strict chemical constraints. Most existing approaches
arXiv:2604.20755v1 Announce Type: cross Abstract: We introduce V-tableR1, a process-supervised reinforcement learning framework that elicits rigorous, verifiable reasoning from multimodal large language models (MLLMs). Current MLLMs trained solely on final outcomes often treat visual reasoning as a
arXiv:2511.06209v5 Announce Type: replace Abstract: LLMs can solve complex tasks by generating long, multi-step reasoning chains. Test-time scaling (TTS) can further improve performance by sampling multiple variants of intermediate reasoning steps, verifying their correctness, and selecting the best
arXiv:2601.05019v2 Announce Type: replace-cross Abstract: Recent Large Reasoning Models trained via reinforcement learning exhibit a "natural" alignment with human cognitive costs. However, we show that the prevailing paradigm of reasoning distillation -- training student models to mimic these trace
arXiv:2506.21546v4 Announce Type: replace-cross Abstract: Segmentation Vision-Language Models (VLMs) have significantly advanced grounded visual understanding, yet they remain prone to pixel-grounding hallucinations, producing masks for incorrect objects or for objects that are entirely absent. Exis
arXiv:2601.13690v2 Announce Type: replace Abstract: Clinical Decision Support Systems (CDSSs) provide reasoning and inquiry guidance for physicians, yet they face notable challenges, including high maintenance costs and low generalization capability. Recently, Large Language Models (LLMs) have been
arXiv:2507.04023v3 Announce Type: replace Abstract: Large language models (LLMs) achieve impressive performance on complex mathematical benchmarks yet sometimes fail on basic math reasoning while generating unnecessarily verbose responses. In this paper, we present LLMThinkBench, a systematic benchm
arXiv:2604.16565v2 Announce Type: replace-cross Abstract: While Diffusion Large Language Models (dLLMs) offer structural advantages for global planning, efficiently verifying that they arrive at correct answers via valid reasoning traces remains a critical challenge. In this work, we propose a geome
arXiv:2604.20263v1 Announce Type: cross Abstract: Virtual cell modeling predicts molecular state changes under genetic perturbations in silico, which is essential for biological mechanism studies. However, existing approaches suffer from unconstrained reasoning, uninterpretable predictions, and retr
arXiv:2604.20140v1 Announce Type: cross Abstract: Direct Preference Optimization (DPO) is an effective framework for aligning large language models with human preferences, but it struggles with complex reasoning tasks. DPO optimizes for the likelihood of generating preferred over dispreferred respon
arXiv:2604.19758v1 Announce Type: cross Abstract: We present ThermoQA, a benchmark of 293 open-ended engineering thermodynamics problems in three tiers: property lookups (110 Q), component analysis (101 Q), and full cycle analysis (82 Q). Ground truth is computed programmatically from CoolProp 7.2.0
arXiv:2604.21346v1 Announce Type: new Abstract: Vision--language models (VLMs) often fail on abstract visual reasoning benchmarks such as Bongard problems, raising the question of whether the main bottleneck lies in reasoning or representation. We study this on Bongard-LOGO, a synthetic benchmark of
arXiv:2601.03248v3 Announce Type: replace Abstract: Spatio-temporal reasoning in time series involves the explicit synthesis of temporal dynamics, spatial dependencies, and textual context. This capability is vital for high-stakes decision-making in systems such as traffic networks, power grids, and
arXiv:2604.21068v1 Announce Type: cross Abstract: The most technologically consequential materials are often the rarest: they occupy narrow regions of chemical space, obey competing physical constraints, and appear only sparsely in existing databases. High-kappa dielectrics, high-Tc superconductors,
arXiv:2604.20039v1 Announce Type: cross Abstract: Causal discovery through experimentation and intervention is fundamental to robust problem solving. It requires not just updating beliefs within a fixed framework but revising the hypothesis space itself, a capacity current AI agents lack when eviden
arXiv:2604.10072v3 Announce Type: replace Abstract: Recent advancements in the Generative Reward Model (GRM) have demonstrated its potential to enhance the reasoning abilities of LLMs through Chain-of-Thought (CoT) prompting. Despite these gains, existing implementations of GRM suffer from two criti
arXiv:2604.10516v2 Announce Type: replace Abstract: Selecting the right knowledge is critical when using large language models (LLMs) to solve domain-specific data analysis tasks. However, most retrieval-augmented approaches rely primarily on lexical or embedding similarity, which is often a weak pr
arXiv:2510.15096v2 Announce Type: replace Abstract: Real-world settings where language models (LMs) are deployed -- in domains spanning healthcare, finance, and other forms of knowledge work -- require models to grapple with incomplete information and reason under uncertainty. Yet most LM evaluation
arXiv:2509.23744v3 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) promise enhanced reasoning by integrating diverse inputs such as text, vision, and audio. Yet cross-modal reasoning remains underexplored, with conflicting reports on whether added modalities help or h
arXiv:2604.21334v1 Announce Type: new Abstract: Do large language models (LLMs) exhibit systematic ideological bias when reasoning about economic causal effects? As LLMs are increasingly used in policy analysis and economic reporting, where directionally correct causal judgments are essential, this
arXiv:2510.20505v4 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) remains brittle on multi-step questions and heterogeneous evidence sources, trading accuracy against latency and token/tool budgets. This paper introduces RELOOP, a structure aware framework using Hierarch
arXiv:2505.07527v5 Announce Type: replace Abstract: The advantage function is a central concept in RL that helps reduce variance in policy gradient estimates. For language modeling, Group Relative Policy Optimization (GRPO) was proposed to use the within-group sample mean as a baseline for advantage
arXiv:2604.21454v1 Announce Type: cross Abstract: Reasoning in large language models is often treated as a monolithic capability, but its observed gains may arise from more basic operations. We study reasoning through two such primitives, recall and state-tracking, and ask whether hybrid architectur
arXiv:2604.21495v1 Announce Type: cross Abstract: Numerical reasoning over expert-domain tables often exhibits high in-domain accuracy but limited robustness to domain shift. Models trained with supervised fine-tuning (SFT) on specific datasets tend to rely on header-operation shortcuts rather than
arXiv:2604.21327v1 Announce Type: cross Abstract: Test-time reinforcement learning (TTRL) always adapts models at inference time via pseudo-labeling, leaving it vulnerable to spurious optimization signals from label noise. Through an empirical study, we observe that responses with medium consistency
arXiv:2604.21764v1 Announce Type: new Abstract: Reasoning LLMs often spend substantial tokens on long intermediate reasoning traces (e.g., chain-of-thought) when solving new problems. We propose to summarize and store reusable reasoning skills distilled from extensive deliberation and trial-and-erro
arXiv:2604.20316v1 Announce Type: new Abstract: Function calling empowers large language models (LLMs) to interface with external tools, yet existing RL-based approaches suffer from misalignment between reasoning processes and tool-call decisions. We propose R2IF, a reasoning-aware RL framework for
arXiv:2509.24239v4 Announce Type: replace-cross Abstract: Recent large language models (LLMs) have shown strong reasoning capabilities. However, a critical question remains: do these models possess genuine strategic reasoning, or do they primarily excel at pattern recognition? To address this, we pr