50 articles mentioning Reasoning-Medical-27B
arXiv:2610.28176v1 Announce Type: cross Abstract: Large Language Models (LLMs) often struggle with temporally grounded reasoning because their static parametric memory is misaligned with the dynamic evolution of real-world knowledge. Although RAG and Parameter-Efficient Fine-Tuning (PEFT) provide pr
arXiv:2610.27202v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly operate across culturally diverse settings, yet existing evaluations largely measure cultural behavior at the output level. We introduce CultureLens, a reference-grounded benchmark and mechanistic study of how
arXiv:2610.28584v1 Announce Type: new Abstract: Autoregressive models (ARMs) face a "Sequentiality Bottleneck" in reasoning, while diffusion language models (DLMs) offer parallelism but lack semantic coherence. To addresses both limitations, we propose Collaborative Reasoning Asymmetric Learning (Co
arXiv:2610.28354v1 Announce Type: new Abstract: Spatial reasoning asks a model to work out where objects are in 3D space, how they relate to one another, and how they move. Agentic VLMs have recently brought large improvements on such tasks by letting the model actively gather evidence with 3D perce
arXiv:2610.28386v1 Announce Type: cross Abstract: Visual tool use enables vision-language models (VLMs) to acquire task-relevant evidence, but its effectiveness can be limited by predefined visual operations and the tool-use strategies learned during training. Representing these operations and strat
arXiv:2610.28184v1 Announce Type: cross Abstract: Reasoning-augmented vision-language-action (VLA) driving models can perceive and reason about safety-critical hazards yet fail to translate that evidence into safe actions. We characterize this failure as a perception-action binding gap: hazard infor
arXiv:2606.23687v3 Announce Type: replace Abstract: Large language models (LLMs) are typically pretrained on short sequences and then extended to work on longer sequences with additional training. However, such LLMs still struggle to further generalize to very long sequences. We propose Randomized Y
arXiv:2610.27256v1 Announce Type: new Abstract: Analyzing merchant transaction histories requires dynamic temporal filtering, entity resolution, and aggregation over irregular event streams--operations poorly captured by static tabular or time-series forecasting benchmarks. We introduce TxnQA, an an
arXiv:2610.00661v3 Announce Type: replace-cross Abstract: Diffusion large language models (dLLMs) generate text by denoising a sequence or successive blocks, allowing several tokens to be revealed in parallel. Reinforcement learning with verifiable rewards (RLVR) reuses terminal feedback across thes
arXiv:2610.26943v1 Announce Type: new Abstract: Mathematical reasoning is a fundamental capability for educational applications of Large Language Models (LLMs), where reliable problem solving requires not only correct answers but also coherent and verifiable reasoning processes. Multi-agent systems
arXiv:2603.00889v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have exhibited remarkable reasoning capabilities, largely enabled by supervised fine-tuning (SFT)- and reinforcement learning (RL)-based post-training on high-quality reasoning data. However, reproducing and exten
arXiv:2610.28282v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have substantially advanced chart understanding and reasoning, yet their performance remains highly uneven across chart types. While modern MLLMs perform well on common charts, their accuracy drops sharply on lo
arXiv:2609.35694v3 Announce Type: replace Abstract: We introduce the Continuous Embedding Diffusion Reasoner (CEDR), a training and inference pipeline for continuous latent diffusion models that achieves strong performance on mathematical reasoning and code generation. We learn compact answer repres
arXiv:2610.27567v1 Announce Type: cross Abstract: Depression assessment from counseling speech requires integrating textual and acoustic psychological evidence across turns, yet existing end-to-end classification approaches lack explicit multimodal evidence interpretation and context-aware reasoning
arXiv:2610.28381v1 Announce Type: cross Abstract: Reasoning about safety is essential for embodied agents powered by large language models (LLMs). We introduce the Contextual Action and Plan Safety benchmark (CAPSafe), designed to evaluate safety reasoning at two levels: (1) an action-level dataset
arXiv:2610.28498v1 Announce Type: cross Abstract: Probing studies of latent reasoning often read a model's state where the answer begins and take a failed probe as evidence that a value is absent. We test this with a digit copied from the question, in the looped model Ouro-1.4B and the standard tran
arXiv:2610.27119v1 Announce Type: new Abstract: LLM agents perform tasks over multiple steps and revise their actions based on feedback. As the total reasoning budget is often limited and must support future steps, the agent must choose between short and long reasoning before each action. Longer rea
arXiv:2610.27220v1 Announce Type: new Abstract: Recent work has explored continuous representations in place of discrete tokens during Chain-of-Thought (CoT) reasoning, often referred to as soft CoT. This is motivated by the idea that a mixture of token embeddings can represent a superposition of mu
arXiv:2510.03223v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) tend to generate a long reasoning chain when solving complex tasks. However, as the reasoning chain extends, critical intermediate steps and the original prompt will be buried in the context, receiving insufficien
arXiv:2609.37976v2 Announce Type: replace-cross Abstract: LLMs trained with Chain-of-thought excel in reasoning capability, but often come with excessive token cost. We find that the core of reasoning capacity lies in the Thinking model's weight component within the null space of a projection define
arXiv:2610.26986v1 Announce Type: new Abstract: Contextual automatic speech recognition (ASR) improves rare-entity recognition by supplying candidate hotwords, but retrieved candidates may be incomplete or incorrect. A reliable system must therefore exploit a relevant candidate without allowing unsu
arXiv:2610.27981v1 Announce Type: new Abstract: Reasoning-enabled language model agents can incur substantial computation before acting, although the reasoning needed varies across decisions. Existing stopping signals, such as confidence and intermediate-answer stability, can vary in effectiveness a
arXiv:2610.17544v2 Announce Type: replace-cross Abstract: Thought templates, skill libraries, agent memories and caches turn many reasoning steps into one. We call this reasoning contraction. A contracted memory saves reasoning steps and errors until its facts change, then quietly answers wrong. Mos
arXiv:2610.27439v1 Announce Type: cross Abstract: Solving reasoning tasks supported on graphs typically requires providing a Language Reasoning Model (LRM) with a serialized description of the graph. This approach results in the input length growing with the number of edges, which limits the size of
arXiv:2604.19444v2 Announce Type: replace Abstract: Reasoning language models often lack the calibrated confidence needed for reliable deployment, particularly when correctness labels are unavailable and sampling budgets are limited. We introduce Binary Agreement for Self-consistency Calibration (BA
arXiv:2610.27662v1 Announce Type: new Abstract: Sampling complete solutions gives large language models more chances to solve a problem, but each attempt starts again. For tasks with several subproblems, all required answers must be correct in the same attempt. Retaining intermediate results can avo
arXiv:2610.27245v1 Announce Type: new Abstract: Reasoning structures (e.g., chains and graphs) are increasingly used for probabilistic inference, factuality verification, and uncertainty estimation, but their structural reliability is rarely evaluated directly. We test whether this reliability holds
arXiv:2610.27043v1 Announce Type: cross Abstract: Financial institutions increasingly deploy large language models (LLMs) in multilingual markets, raising a practical question: can pipelines developed and validated in English be reused across languages, or must they be rebuilt per locale? We test cr
arXiv:2610.23245v1 Announce Type: cross Abstract: GRPO assigns the same group-relative advantage to equally rewarded responses within a question, leaving their generation uncertainty unused. We introduce MGE-PO, centered on four-quadrant (4Q) advantage shaping that combines verified correctness with
arXiv:2610.23307v1 Announce Type: cross Abstract: Multimodal large language model (MLLM)-based mobile agents are rapidly evolving from conversational assistants into autonomous systems that perceive, reason over, and act on smartphone environments. This capability also exposes a new security risk: a
arXiv:2606.09449v2 Announce Type: replace Abstract: Autoformalization (AF) requires both prover acceptance and fidelity to an informal source, but prover acceptance alone cannot establish fidelity, and expert-validated reference formalizations are costly to obtain. We introduce a reference-free prox
arXiv:2610.22067v1 Announce Type: new Abstract: Long-context language models support ever longer context windows, and evaluations typically treat context length as the main indicator of difficulty. However, context length alone cannot explain why models fail on long-context tasks that require reason
arXiv:2610.21347v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly operate in multi-turn interactions that require maintaining latent conversational states, not only explicit facts. We study affective state as an implicit state inferred from sparse contextual cues that remain
arXiv:2610.21308v1 Announce Type: cross Abstract: Consumer phones and wearables increasingly collect physiological time-series data, yet most mobile systems treat these streams as summaries or text rather than as temporal evidence. This representation is poorly matched to personal health systems tha
arXiv:2605.23074v2 Announce Type: replace Abstract: Large Reasoning Language Models (LRMs) tackle complex tasks through test-time scaling, generating long-form Chain-of-Thought (CoT) trajectories during inference. These trajectories contain reflection markers such as wait, but, and alternatively, ac
arXiv:2509.26226v3 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Reward (RLVR) effectively solves complex tasks but demands extremely long context lengths during training, leading to substantial computational costs. While multi-stage training can partially mitigate th
arXiv:2610.20832v1 Announce Type: cross Abstract: Despite their extensive pretraining knowledge and strong reasoning capabilities, large language models (LLMs) struggle to adaptively gather information in experimental design tasks. We study how to amortize sequential Bayesian experimental design (BE
arXiv:2610.20867v1 Announce Type: new Abstract: We present a general declarative framework for anticipatory reasoning about interactive motion in complex dynamic environments. Our focus is on (explainable) anticipatory space-time mental model formation at a semantic level to heuristically guide low-
arXiv:2610.20805v1 Announce Type: new Abstract: A reasoning trace retained at answer time plays two roles: it can raise accuracy, and it can compete with the current evidence when the two disagree. We disentangle these roles by crossing verified evidence versions with the traces generated from each
arXiv:2610.21393v1 Announce Type: new Abstract: Vehicle Routing Problems (VRPs) are fundamental to many real-world applications. Recent advances in large language models (LLMs) have spurred progress in solving these NP-hard problems. However, most existing approaches assume that input instances are
arXiv:2610.22324v1 Announce Type: new Abstract: One of the first steps of a research pipeline is generating ideas. Large Language Models (LLMs) are increasingly used to automate this step, but most of this work optimizes the quality of individual ideas, while overlooking diversity. In our work, we s
arXiv:2610.21151v1 Announce Type: cross Abstract: Cybersecurity interviews uncover critical security experiences, behaviors, and privacy concerns often not fully captured by conventional technical assessments. Consequently, identifying genuine self-disclosures is challenging because statements are c
arXiv:2607.18915v2 Announce Type: replace Abstract: With the rapid advancement of large language models (LLMs), modern systems not only possess strong foundational capabilities and extensive knowledge, but can also solve complex problems via long, multi-step reasoning. However, as reasoning traces b
arXiv:2504.05607v2 Announce Type: replace-cross Abstract: Despite the success of Large Language Models (LLMs) in long-context tasks, their reliability in recognizing unanswerable questions remains a critical challenge. In information-seeking scenarios, models often suffer from overconfidence and hal
arXiv:2610.20459v1 Announce Type: new Abstract: Chemical chain-of-thought can contain hallucinated structural and property claims. We thereby introduce MolLean, a process-verifiable language that grounds chemical reasoning in an explicit molecular state. A layered Lean-based kernel checks state tran
arXiv:2610.15091v1 Announce Type: cross Abstract: Argument structures represent how individual arguments interact within a discourse. However, leveraging these structures to infer meaningful knowledge remains challenging, as it requires a formal representation of how argumentative influence propagat
arXiv:2610.19108v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have been widely applied in embodied agents and robotics for vision tasks. However, MLLMs suffer from limitations in spatial reasoning and perception. Post-training techniques have shown promise for improving
arXiv:2609.23038v2 Announce Type: replace Abstract: Spatial reasoning is essential for vision-language models (VLMs) to understand and act in the physical world. Reasoning in dynamic environments requires VLMs to perceive local state transitions caused by object motion and viewpoint changes and inte
arXiv:2610.18025v1 Announce Type: new Abstract: Test-time scaling has enabled LLMs to solve increasingly complex reasoning, discovery, and optimization tasks. However, existing approaches often gather observations while seeking evidence for current hypotheses, then generate new hypotheses conditione
arXiv:2610.16713v1 Announce Type: cross Abstract: Teacher rationales can help a smaller model answer health professions questions, but they can also reinforce errors. We examined when they help and how this evidence can guide training using Brazilian Portuguese questions from medical and multiprofes