49 articles mentioning reasoning-summarizer-800m-pre-gguf
arXiv:2610.12927v1 Announce Type: new Abstract: Large language models (LLMs) excel across diverse tasks, benefiting from knowledge priors, in-context reasoning, and test-time computation. Despite these strengths, single-model reasoning remains vulnerable to error propagation, as later steps depend o
arXiv:2606.15419v2 Announce Type: replace-cross Abstract: Objective: To enhance the accuracy, interpretability, and robustness of large language models (LLMs) in medical question answering (MedQA). Method: We designed a multi-agent peer-reviewed reasoning method in which multiple LLM agents independ
arXiv:2610.12769v1 Announce Type: cross Abstract: Unlearning in large reasoning models (LRMs) requires removing forget-set information from both the reasoning trace and the final answer. Existing approaches achieve this objective at the cost of reasoning collapse, where the model fails to produce a
arXiv:2609.24066v2 Announce Type: replace Abstract: Best-of-$N$ is a widely used inference strategy for complex reasoning, whose effectiveness depends on whether sampled candidates can cover diverse and high-quality reasoning paths. However, post-trained reasoning models often suffer from \emph{expl
arXiv:2610.10405v2 Announce Type: replace Abstract: Monitoring the chain-of-thought of reasoning artificial intelligence (AI) models remains a key approach to detecting deception and other forms of misbehavior in such models. However, semantic chain-of-thought monitoring depends on reasoning traces
arXiv:2610.13672v1 Announce Type: cross Abstract: Large language models struggle to reliably identify and correct errors in their own reasoning. Unlike prior training-based approaches that fine-tune an LLM to generate revisions or feedback, we learn where to intervene in failed rollouts and determin
arXiv:2606.09365v4 Announce Type: replace Abstract: Medical agent systems are increasingly expected to support interactive clinical decision making rather than only static question answering. In such settings, effective agents must reuse prior experience across evolving cases, yet existing memory me
arXiv:2610.02626v2 Announce Type: cross Abstract: Vision-language-action (VLA) models increasingly incorporate intermediate reasoning to improve robotic manipulation, yet existing approaches primarily reason about observed states without explicitly anticipating future scene evolution. Extending such
arXiv:2610.00661v2 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:2605.07251v2 Announce Type: replace Abstract: Large Language Models (LLMs) have become increasingly capable as tool-using agents, with benchmarks spanning diverse general agentic tasks. Yet rigorous evaluation of scientific tool use remains limited. In chemistry, recent agents can plan synthes
arXiv:2610.13285v1 Announce Type: new Abstract: Distilling long-chain reasoning trajectories from large teacher models provides an effective way to improve the reasoning ability of small language models. However, existing methods typically select a fixed training set before distillation, overlooking
arXiv:2609.01216v2 Announce Type: replace Abstract: Tables are ubiquitous across diverse domains, yet reasoning over them remains a significant challenge for modern large language models (LLMs). Current approaches typically linearize tables into sequences, inherently overlooking their intrinsic two-
arXiv:2610.12933v1 Announce Type: new Abstract: Large language models have achieved remarkable advances in complex reasoning. However, scaling reasoning post-training with ever-larger corpora can substantially increase training cost without proportional performance gains. In this study, we therefore
arXiv:2610.13330v1 Announce Type: new Abstract: Designing tool-integrated reasoning agent systems for complex chemical tasks remains a fundamental challenge. Although recent chemical agents have demonstrated promising performance through the integration of external tools, they are still built on the
arXiv:2610.10455v2 Announce Type: replace-cross Abstract: Hallucinated information can propagate through multi-stage LLM systems and become part of the context for subsequent reasoning. Existing studies of post-hallucination reasoning (PHR) mainly characterize changes in final outcomes and aggregate
arXiv:2610.13098v1 Announce Type: new Abstract: Visual agents for symbolic graphics reasoning depend on executable world representations, yet continued improvement remains bottlenecked by ambiguous supervision from final renders. Recent agentic systems refine scenes through repeated interaction, but
arXiv:2610.13695v1 Announce Type: new Abstract: Any automation within reliability-critical contexts such as medicine or law has to be transparent and verifiable. Despite their advantages, current LLM-based systems do not meet these requirements due to their inherent black-box nature. Retrieval Augme
arXiv:2610.12881v1 Announce Type: new Abstract: Understanding and manipulating spatial relations is fundamental to AI systems that reason about physical environments and construct grounded world models. However, existing evaluations of multimodal large language models (MLLMs) for spatial reasoning r
arXiv:2607.21552v2 Announce Type: replace Abstract: Vision-language models (VLMs) can behave very differently depending on whether the same underlying problem is presented textually or visually. This inconsistency suggests that different views expose different reasoning paths and failure modes that
arXiv:2610.01892v2 Announce Type: replace-cross Abstract: Multimodal agents commonly generate free-form reasoning before each action. For small models, limited model capacity can result in lengthy reasoning that provides little useful guidance for action generation while incurring substantial infere
arXiv:2610.13570v1 Announce Type: new Abstract: Reasoning models can benefit from test-time scaling, but continued reasoning may become ineffective or harmful, a phenomenon termed overthinking. Evaluations against full thinking compare accuracy and token usage but lack references for overthinking se
arXiv:2610.13722v1 Announce Type: new Abstract: Legal language understanding requires reasoning over semi-structured regulatory documents, yet standard pre-training objectives do not explicitly target this structural capability. Because current legal language models rely solely on masked language mo
arXiv:2603.05911v2 Announce Type: replace-cross Abstract: Medical image segmentation is undergoing a paradigm shift from conventional visual pattern matching to cognitive reasoning analysis. Although Multimodal Large Language Models (MLLMs) have shown promise in integrating linguistic and visual kno
arXiv:2505.17244v3 Announce Type: replace-cross Abstract: Large Reasoning Models (LRMs) leverage explicit reasoning traces, known as Chain-of-Thought (CoT) reasoning, to decompose complex problems into intermediate steps before deriving final answers. However, these reasoning traces introduce unique
arXiv:2610.13075v1 Announce Type: new Abstract: Corpus-level long-context reasoning requires agents to acquire and integrate evidence across document collections that exceed their context windows. Existing agent harnesses enable incremental access to these corpora, but acquired evidence and evolving
arXiv:2610.13744v1 Announce Type: new Abstract: On-policy self-distillation promises to replace the sparse outcome signal of verifiable-reward RL with dense token-level credit: a teacher conditioned on the reference solution scores the student's own rollout, and the resulting distributional shift is
arXiv:2605.10268v2 Announce Type: replace-cross Abstract: Long-context reasoning tasks have motivated agent-memory approaches that process document chunks sequentially while maintaining a dynamically updated memory, avoiding the quadratic complexity of standard attention. Existing methods often rely
arXiv:2606.00726v4 Announce Type: replace Abstract: Strong reasoning depends not only on model knowledge but also on how effectively cognitive behaviors are deployed during generation. Existing methods often rely on explicit behavior-level control, making them insufficiently adaptive when failures a
arXiv:2610.13081v1 Announce Type: new Abstract: Recent work on large audio-language models (LALMs) explores adaptive reasoning to balance accuracy and efficiency. However, existing approaches often rely on coarse-grained difficulty estimation, overlooking the diverse factors that determine reasoning
arXiv:2605.28422v2 Announce Type: replace-cross Abstract: Latent reasoning enables reasoning over continuous hidden states rather than explicit tokens, avoiding the language bottleneck and inference overhead of chain-of-thought for medical VQA. However, existing methods suffer from modality collapse
arXiv:2610.11724v1 Announce Type: new Abstract: Multimodal meme understanding is increasingly used to analyze socially sensitive content, yet existing models often exhibit biased behavior when interpreting economic dependence and social roles under ambiguity. Many memes express economic relationship
arXiv:2610.12333v1 Announce Type: cross Abstract: Accurate simulation of rigid-body interactions is essential for predictive physical world models. Despite recent progress in modeling object dynamics, capturing how local contacts between surfaces shape object motion remains challenging. While end-to
arXiv:2607.17575v3 Announce Type: replace Abstract: We propose ARBITER, a novel LLM guardrail framework that introduces two key ideas: (i) dual-hypothesis reasoning, a reasoning method for LLM guardrails that explicitly considers both safe and unsafe interpretations of a prompt before making a safet
arXiv:2610.10996v1 Announce Type: new Abstract: Latent reasoning models repeatedly update a latent state using the same recurrent block. As the recurrent depth increases, the sequence of latent states may converge to a compact subset of the state space without necessarily converging to a fixed point
arXiv:2609.29102v3 Announce Type: replace Abstract: Fully continuous diffusion language models (dLMs) denoise continuous representations without intermediate discretization, then decode all response tokens in parallel at the final step. Their performance on challenging reasoning tasks remains less e
arXiv:2610.12022v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in sociotechnical systems where social attribution, the reasoning process attributing external events to the causes and reasons of agents' social behaviors, plays a critical role. These processes
arXiv:2606.05315v2 Announce Type: replace-cross Abstract: Implicit chain-of-thought (iCoT) methods aim to internalize reasoning in large language models, but often underperform explicit CoT prompting. We empirically find that hidden-state reasoning trajectories exhibit low-rank structure. Motivated
arXiv:2610.11025v1 Announce Type: cross Abstract: Exploratory data analysis (EDA) is rarely open-ended in practice: analysts work from high-level domain questions toward the concrete analyses that can answer them, prioritizing directions with domain knowledge and prior hypotheses. Large language mod
arXiv:2609.34181v2 Announce Type: replace Abstract: Large Reasoning Models (LRMs) have shown remarkable reasoning capabilities, yet they still suffer from overthinking, generating redundant reasoning steps which incur substantial token consumption. Existing methods, such as suppressing reflective ke
arXiv:2610.10641v1 Announce Type: cross Abstract: Large language models (LLMs) offer promising potential for next-visit diagnosis prediction, owing to their ability to integrate longitudinal clinical evidence and reason over it in natural language. However, reinforcement learning for LLM reasoning c
arXiv:2610.10782v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a standard recipe for post-training vision-language models (VLMs), but it typically assumes a static training environment. As the actor improves, fixed tasks drift out of its learning f
arXiv:2610.01780v3 Announce Type: replace Abstract: An AI companion that talks with someone for months should come to understand them. It should know who they are, remember what they said, and recognize when something from the past matters now. Testing this needs real conversations, but real convers
arXiv:2610.12061v1 Announce Type: new Abstract: Large language model (LLM)-based agents have demonstrated strong capabilities on complex tasks. They typically perform reasoning before each action throughout an interaction trajectory. However, reasoning may not be necessary at every turn, as reasonin
arXiv:2610.11592v1 Announce Type: new Abstract: Current frontier LLMs can theoretically process long contexts with 1M tokens or more. But to what extent can they go beyond simple retrieval and perform deeper reasoning over such long contexts? We empirically investigate long-horizon reasoning capabil
arXiv:2610.11111v1 Announce Type: new Abstract: Time Series Language Models (TSLMs) offer a promising path toward time series understanding by reasoning over temporal signals and producing natural language answers and explanations. A common approach is Chain-of-Thought (CoT), which generates step-by
arXiv:2610.12402v1 Announce Type: cross Abstract: Existing spatial reasoning benchmarks mainly test spatial perception: reading off relations already visible in the input. Yet real-world spatial intelligence demands predictive spatial reasoning: constructing a scene from observations, anticipating h
arXiv:2610.10639v1 Announce Type: cross Abstract: Visible Chain-of-Thought (CoT) is often treated as a broadly useful reasoning instruction, yet analytics code generation combines natural-language ambiguity, schema grounding, target-language constraints, and model-specific inference behavior. Becaus
arXiv:2610.11472v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning often improves language-model performance by giving models additional computation before answering. However, explicit CoT expresses this computation as a sequence of autoregressively generated tokens. Latent reasoning r
arXiv:2610.11171v1 Announce Type: cross Abstract: Long-form video understanding often involves multiple questions about different aspects of the same recording. Yet existing video agents typically process each question through an isolated tool-use trajectory. This repeatedly restarts video explorati