Search: “reasoning”

arXiv:2607.28636v1 Announce Type: new Abstract: LLMs increasingly serve as automated judges, but their judgments remain vulnerable to cognitive biases. Existing mitigations mostly rely on prompt-drive

arXiv:2607.29009v1 Announce Type: new Abstract: Multi-robot systems, particularly heterogeneous robot swarms, can improve the efficiency of complex task execution through parallel collaboration and co

arXiv:2603.11872v3 Announce Type: replace-cross Abstract: Translating single-cell RNA sequencing (scRNA-seq) data into mechanistic biological hypotheses remains a critical bottleneck, as agentic AI sy

arXiv:2505.21736v2 Announce Type: replace Abstract: Translation equivariance is a central reason convolutional neural networks have been successful in computer vision. Other symmetries, such as rotati

Hey guys! After a LOT of good feedback on our previous models like Supra-50M-Instruct and -Reasoning, many community likes, follows and upvotes we saw many community requests asking for new models. We

arXiv:2607.28908v1 Announce Type: new Abstract: Reflection, the ability to revisit and revise prior reasoning, is central to how humans improve their answers. Large language models (LLMs) are increasi

arXiv:2603.21846v2 Announce Type: replace Abstract: Explainable AI is increasingly important to scientific discovery. However, existing methods largely ignore that explanation quality is not universal

arXiv:2601.22546v2 Announce Type: replace-cross Abstract: The recent advancements in Large Language Models (LLMs) have attracted interest in exploring their in-context learning abilities and chain-of-

Spent way too much time with V4-Flash-0731 this weekend and wanted to share my vibes as briefly as possible. I sent it through a bit of real-work and some of my personal benchmarks. My quick thoughts

Don’t think I have seen more misconceptions around one model (I count 8) since the fantasies people had before GPT-5 was released. That turned out to be a letdown; so will Astra, for people who are dr

DeepSeek V4 Flash got me thinking... We keep seeing smaller models get way better. A model at a certain parameter count today can be much smarter than a model of the same size from a year or two ago.

**Kimi K3 is Moonshot AI’s 2.8‑trillion‑parameter open‑weight language model—the largest ever released—designed for frontier tasks such as long‑horizon coding and deep reasoning.** Its architecture us

arXiv:2607.28037v1 Announce Type: new Abstract: As LLM-based agents are deployed in complex, multi-step workflows, a critical evaluation gap has emerged: most existing benchmarks judge only final outc

deepseek-ai/DeepSeek-V4-Flash-0731 The latest release in DeepSeek's V4 family, 'with substantially enhanced agentic capabilities'. It's 304 billion parameters - 167GB on Hugging Face - but it appears

arXiv:2607.27420v1 Announce Type: cross Abstract: Humanity's Last Exam (HLE) is widely used to evaluate frontier language models. HLE organizes its questions into eight subject-domain categories, whos

arXiv:2607.27263v1 Announce Type: new Abstract: Most benchmarks for causal inference over time series are observational, small, or domain-specific, leaving interventional and counterfactual estimation

arXiv:2607.27654v1 Announce Type: new Abstract: Event analysis is an essential and fundamental direction of information extraction, involving various event-centric tasks at different granularity of do

arXiv:2607.28135v1 Announce Type: new Abstract: Machine learning for combinatorial optimization typically relies on neural constructors trained via reinforcement learning on large offline datasets for

arXiv:2607.28434v1 Announce Type: cross Abstract: What do a language model's hidden states say about the organization of a single text? From one forward pass, without training, we score every token po

arXiv:2603.16140v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) has driven recent capability advances of large language models across various domains. Recent

arXiv:2607.28312v1 Announce Type: new Abstract: Streaming video understanding requires models to continuously retain useful visual evidence before future questions are known. Existing approaches prima

arXiv:2607.27902v1 Announce Type: new Abstract: Scene text spotting requires high-precision alignment between textual recognition and spatial localization. While visual-token grounding has emerged as

arXiv:2607.27278v1 Announce Type: new Abstract: Open-vocabulary Earth observation (EO) aims to localize geospatial concepts specified in natural language rather than a fixed label set. Existing benchm

arXiv:2607.28100v1 Announce Type: cross Abstract: Large language models (LLMs) offer powerful reasoning capabilities for network traffic analysis, but standard capture formats and their textual equiva

arXiv:2607.28624v1 Announce Type: new Abstract: We introduce PhiZero, a physical world model built around physical language, a compact discrete representation of world-state transitions. Existing phys

arXiv:2607.27826v1 Announce Type: cross Abstract: Recent advances in sign language (SL) understanding (SLU) have led to remarkable progress in tasks such as continuous SL recognition and SL translatio

Tuesday was Stateless MCP day - the rollout of MCP 2.0, or the 2026-07-28 Model Context Protocol specification to use the more formal but less memorable name. This is the most significant change to th

arXiv:2511.23310v3 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as an effective paradigm for post-training large language models, yet the de

arXiv:2603.07131v4 Announce Type: replace Abstract: Large Vision Language Models (LVLMs) show immense potential for automated ophthalmic diagnosis. However, their clinical deployment is severely hinde

In today’s agentic era, modern cloud applications are evolving from a set of passive tools to fleets of autonomous digital workers that reason, plan, and take action across a wide range of tasks. For

arXiv:2607.26504v1 Announce Type: new Abstract: Many discrete reasoning tasks, such as code generation, are inherently non-causal: programmers move between high-level structure and local details, a pr

goblin-level blog post Turns out GPT-5.6 Sol is actually SoTA on ARC-AGI-3. Just took two setting changes. You just have to allow it to reason and work over multiple context windows with the help of o

arXiv:2607.26115v1 Announce Type: cross Abstract: We introduce extbf{GPT-Red}, an automated red-teaming agent that is trained to discover novel prompt injection attacks against frontier LLMs. The goal

arXiv:2607.26886v1 Announce Type: cross Abstract: When asked to describe a medical image that was never attached, frontier vision-language models do not abstain: they confabulate a diagnosis. We show

arXiv:2603.08286v2 Announce Type: replace Abstract: Legal argument mining aims to identify and classify the functional components of judicial reasoning, such as facts, issues, rules, analysis, and con

arXiv:2607.26862v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) has become a standard reinforcement learning method for post-training language models. Recent work shows that

arXiv:2607.26922v1 Announce Type: new Abstract: Multi-agent LLM pipeline systems break down the task among multiple roles for better reasoning, but are benchmarked mainly with large-scale commercial m

arXiv:2510.08543v2 Announce Type: replace-cross Abstract: As Video Large Language Models (VideoLLMs) are deployed globally, it is important to assess their ability to reason across cultural contexts.

arXiv:2607.25066v1 Announce Type: new Abstract: Long-horizon LLM agents accumulate reasoning traces, actions, and tool observations that can eventually exceed a model's fixed context window. Existing

server : add trace logging for slot similarity checking (#26271) Adds trace logging in server-context.cpp for slot similarity checking during prompt cache slot selection, including skip reasons and si

arXiv:2607.25397v1 Announce Type: new Abstract: Successfully automating dexterous, long-horizon robotic manipulation requires frameworks capable of both high-level reasoning and fine-grained execution

Impressive paper! It's on one of the hardest tasks for coding agents today. Of course, I am talking about kernel optimization. Coding agents are usually not so great at this. Reasons: Unfamiliar low-l

arXiv:2607.25992v1 Announce Type: cross Abstract: Recently, memory management has become a key infrastructure for LLM-based agents, as it directly affects long-horizon reasoning, personalized response

arXiv:2607.24768v1 Announce Type: new Abstract: Prenatal care is an important preventive service designed to improve outcomes for pregnant individuals. The American College of Obstetricians and Gyneco

arXiv:2607.25485v1 Announce Type: new Abstract: Health AI is evolving from answering questions to agentic systems that converse with patients, reason about health records, and act on their behalf. Pri

arXiv:2512.17351v2 Announce Type: replace Abstract: Understanding architectural differences in language models is challenging, especially at academic-scale pretraining (e.g., 1.3B parameters, 100B tok