Search: “reasoning”

arXiv:2605.09822v1 Announce Type: cross Abstract: We define Oracle Poisoning, an attack class in which an adversary corrupts a structured knowledge graph that AI agents query at runtime via tool-use p

arXiv:2605.09893v1 Announce Type: cross Abstract: Large language models (LLMs) are often evaluated based on their stated values, yet these do not reliably translate into their actions, a discrepancy t

arXiv:2605.08825v1 Announce Type: new Abstract: Event cameras provide microsecond-level temporal resolution, low latency, and high dynamic range, offering potential for perception under fast motion an

arXiv:2512.11470v2 Announce Type: replace-cross Abstract: Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) dominate the post-training landscape for mathematical reasoning, yet differ funda

arXiv:2605.10057v1 Announce Type: new Abstract: Compositional spatiotemporal reasoning often requires a system to invoke multiple heterogeneous specialists, such as geometric, temporal, topological, a

arXiv:2605.10327v1 Announce Type: cross Abstract: In this paper, we present SCALAR (Symbolic Conjecture and LLM-Assisted Reasoning), a neurosymbolic framework for automated conjecture generation in qu

arXiv:2605.08911v1 Announce Type: new Abstract: Autonomous vehicles need to perceive not only physical elements in the driving scene, such as lane lines and traffic lights, but also logical elements l

arXiv:2605.09860v1 Announce Type: new Abstract: Long-horizon reasoning requires deciding not only what actions to take, but how deeply to commit before the next observation. We formalize this as commi

arXiv:2605.07121v1 Announce Type: new Abstract: Temporal knowledge graphs (TKGs) represent time-stamped relational facts and support a wide range of reasoning tasks over evolving events. However, exis

arXiv:2605.08057v1 Announce Type: cross Abstract: While recent advancements in inference-time learning have improved LLM reasoning on Text-to-SQL tasks, current solutions still struggle to perform wel

DeepSeek V4 Pro brings long-context reasoning and SOTA coding performance to Together AI serverless. The next layer is serving it efficiently: KV cache, prefix reuse, hybrid attention, batching, kerne

arXiv:2602.14868v2 Announce Type: replace-cross Abstract: Reinforcement learning has emerged as a powerful paradigm for unlocking reasoning capabilities in language models. However, relying on sparse

arXiv:2605.07600v1 Announce Type: cross Abstract: Recent methods for improving LLM mathematical reasoning, whether through MCTS-based test-time search or causal graph-guided knowledge injection, canno

arXiv:2605.07140v1 Announce Type: cross Abstract: Skeleton-based human activity recognition has achieved strong empirical performance, yet most existing models remain black boxes and difficult to inte

arXiv:2605.07804v1 Announce Type: cross Abstract: On-policy distillation (OPD) leverages dense teacher rewards to enhance reasoning models. However, scaling OPD to long-horizon tasks exposes a critica

arXiv:2502.01941v3 Announce Type: replace-cross Abstract: While Key-Value (KV) cache compression is essential for efficient LLM inference, current evaluations disproportionately focus on sparse retrie

arXiv:2605.07182v1 Announce Type: new Abstract: Training a family of large language models (LLMs), either from scratch or via iterative compression, is prohibitively expensive and inefficient, requiri

BeeLlama.cpp is an optimized implementation featuring advanced DFlash and TurboQuant quantization techniques with support for reasoning and vision capabilities. The project demonstrates running Qwen 3

GPT-5.5 is now available in ComfyUI. OpenAI's latest frontier model — built for reasoning, structured output, and reliable single-pass results. → Prompt synthesis → Logic-heavy transformations → Clean

arXiv:2605.05121v1 Announce Type: new Abstract: Automated mental health prediction using textual data has shown promising results with deep learning and large language models. However, deploying these

arXiv:2605.04065v1 Announce Type: new Abstract: Unsupervised reinforcement learning (RL) has emerged as a promising paradigm for enabling self-improvement in large language models (LLMs). However, exi

Jeremy Howard proposes three key enhancements for large language models: incorporating latent space diffusion-like reasoning processes, adding a persistent recurrent state mechanism, and implementing

arXiv:2605.03485v1 Announce Type: new Abstract: Multidimensional human understanding is essential for real-world applications such as film analysis and virtual digital humans, yet current LVLM benchma

arXiv:2605.02269v1 Announce Type: new Abstract: Specification gaming is a critical failure mode of LLM agents. Despite this, there has been little systematic research into when it arises and what driv

arXiv:2605.02525v1 Announce Type: new Abstract: Autonomous indoor mobile robots can navigate reliably to metric coordinates using established frameworks such as ROS 2 Navigation 2, yet they lack the a

arXiv:2505.08392v3 Announce Type: replace Abstract: Chain-of-Thought (CoT) prompting trades inference speed for reasoning accuracy. Existing compressors force a compromise as static gradient technique

arXiv:2605.01448v1 Announce Type: cross Abstract: Cross-task generalization is a core challenge in open-world robotic manipulation, and the key lies in extracting transferable manipulation knowledge f

Luma Uni-1 just landed in ComfyUI. Most image models: prompt → pixels. Uni-1: prompt → reasoning → pixels. Autoregressive, not diffusion. Decomposes instructions, resolves constraints, plans compositi

arXiv:2511.07372v3 Announce Type: replace Abstract: Recent curriculum techniques in the post-training stage of LLMs have been empirically observed to outperform non-curriculum approaches in improving

arXiv:2605.01191v1 Announce Type: new Abstract: Vision-language-action (VLA) models have advanced the field of embodied manipulation by harnessing broad world knowledge and strong generalization. Howe

arXiv:2605.01399v1 Announce Type: new Abstract: The conventional Retrieval-Augmented Generation (RAG) paradigm of injecting raw retrieved texts into the Large Language Model (LLM)'s context often resu

arXiv:2605.00434v1 Announce Type: new Abstract: Real-world multimodal learning is often hindered by missing modalities. While Incomplete Multimodal Learning (IML) has gained traction, existing methods

arXiv:2508.21762v3 Announce Type: replace Abstract: AI researchers and practitioners increasingly apply large language models (LLMs) to what we call reasoning-intensive regression (RiR), i.e., deducin

Cool paper from Meta FAIR. It's on self-improving LLMs but on the pretraining side. (bookmark it) Most LLM safety, factuality, and reasoning fixes get bolted on at post-training. By then, the patterns

arXiv:2604.27201v1 Announce Type: cross Abstract: Hybrid-thinking language models expose explicit think and no-think modes, but current designs do not separate them cleanly. Even in no-think mode, mod

arXiv:2602.07408v2 Announce Type: replace Abstract: Predicting gene regulation responses to biological perturbations requires reasoning about underlying biological causalities. While large language mo

arXiv:2604.27472v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models advance robotic control via strong visual-linguistic priors. However, existing VLAs predominantly frame pretraining

arXiv:2604.28076v1 Announce Type: cross Abstract: Large Language Models (LLMs) have advanced Table Question Answering, where most queries can be answered by extracting information or simple aggregatio

Carl Franzen / VentureBeat: xAI launches Grok 4.3, featuring “always-on reasoning”, 1M token context window, and low API pricing, and releases a voice cloning suite called Custom Voices — While Elon M

arXiv:2604.26106v1 Announce Type: new Abstract: Forecasting benchmarks produce accuracy leaderboards but little insight into why some forecasters are more accurate than others. We introduce Bench to t

arXiv:2603.06635v2 Announce Type: replace Abstract: Recent progress in language modeling has expanded the range of tasks that can be approached through natural language interfaces, including problems

Introducing Qwen3.6-Plus from @Alibaba_Qwen, a 1M-context model built for real-world agents, agentic coding, and multimodal reasoning. AI natives can now use Qwen3.6-Plus on Together AI and benefit fr

arXiv:2603.17729v3 Announce Type: replace Abstract: Recent advances in Large Vision-Language Models (LVLMs) have enabled training-free Fine-Grained Visual Recognition (FGVR). However, effectively expl

arXiv:2510.07499v2 Announce Type: replace Abstract: Recent Long-Context Language Models (LCLMs) can process hundreds of thousands of tokens in a single prompt, enabling new opportunities for knowledge

arXiv:2604.23054v1 Announce Type: cross Abstract: Predicting the outcomes of prospective clinical trials remains a major challenge for large language models. Prior work has shown that both traditional

arXiv:2601.16046v2 Announce Type: replace-cross Abstract: Language-driven dexterous grasp generation requires the models to understand task semantics, 3D geometry, and complex hand-object interactions