47 articles mentioning Intern-S1-Pro
arXiv:2603.25040v2 Announce Type: replace-cross Abstract: We introduce Intern-S1-Pro, the first one-trillion-parameter scientific multimodal foundation model. Scaling to this unprecedented size, the model delivers a comprehensive enhancement across both general and scientific domains. Beyond stronge
arXiv:2604.20930v1 Announce Type: cross Abstract: Internal Safety Collapse (ISC) is a failure mode in which frontier LLMs, when executing legitimate professional tasks whose correct completion structurally requires harmful content, spontaneously generate that content with safety failure rates exceed
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:2604.21554v1 Announce Type: new Abstract: Under the EU AI Act, translating AI governance requirements into software development practice remains challenging. While AI governance frameworks exist at industry and organizational levels, empirical evidence of team-level implementation is scarce. W
arXiv:2506.02132v5 Announce Type: replace-cross Abstract: Large transformer-based language models dominate modern NLP, yet our understanding of how they encode linguistic information relies primarily on studies of early models like BERT and GPT-2. We systematically probe 25 models from BERT Base to
arXiv:2604.20783v1 Announce Type: new Abstract: Internal ice layers imaged by radar provide key evidence of snow accumulation and ice dynamics, but radar-derived layer boundary observations are often incomplete, with discontinuous traces and sometimes entirely missing layers, due to limited resoluti
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:2604.18951v2 Announce Type: replace-cross Abstract: Adaptive multi-agent systems (MAS) are increasingly adopted to tackle complex problems. However, the narrow task coverage of their optimization raises the question of whether they can function as general-purpose systems. To address this gap,
arXiv:2604.20043v1 Announce Type: cross Abstract: Explainability for Large Language Model (LLM) agents is especially challenging in interactive, partially observable settings, where decisions depend on evolving beliefs and other agents. We present \textbf{TriEx}, a tri-view explainability framework
arXiv:2511.06209v4 Announce Type: replace Abstract: LLMs can solve complex tasks by generating long, multi-step reasoning chains. Test-time scaling (TTS) can further improve LLM performance by sampling multiple variants of intermediate reasoning steps, verifying their correctness, and strategically
arXiv:2604.20771v1 Announce Type: cross Abstract: The Internet of Vehicles (IoV) is advancing modern transportation by improving safety, efficiency, and intelligence. However, the reliance on the Controller Area Network (CAN) introduces critical security risks, as CAN-based communication is highly v
arXiv:2604.19749v1 Announce Type: new Abstract: Equipping LLMs with external tools effectively addresses internal reasoning limitations. However, it introduces a critical yet under-explored phenomenon: tool overuse, the unnecessary tool-use during reasoning. In this paper, we first reveal this pheno
Google has introduced a host of new automated functions into Workspace, all of which are driven by Workspace Intelligence, its new AI system.
arXiv:2604.19144v1 Announce Type: new Abstract: Recent years have witnessed growing interest in applying Large Reasoning Models (LRMs) to Machine Translation (MT). Existing approaches predominantly adopt a "think-first-then-translate" paradigm. Although explicit reasoning trajectories significantly
arXiv:2604.16217v1 Announce Type: cross Abstract: Large language models are increasingly deployed in settings where reliability matters, yet output-level uncertainty signals such as token probabilities, entropy, and self-consistency can become brittle under calibration--deployment mismatch. Conforma
arXiv:2510.09474v2 Announce Type: replace Abstract: Modern conversational agents like ChatGPT and Alexa+ rely on predefined policies specifying metadata, response styles, and tool-usage rules. As these LLM-based systems expand to support diverse business and user queries, such policies, often implem
arXiv:2604.16890v1 Announce Type: new Abstract: Large reasoning models that use long chain-of-thought excel at problem-solving yet waste compute on redundant checks. Curbing this overthinking is hard: training-time length penalties can cripple ability, while inference-time early-exit adds system ove
arXiv:2604.18519v1 Announce Type: new Abstract: Guard models are widely used to detect harmful content in user prompts and LLM responses. However, state-of-the-art guard models rely solely on terminal-layer representations and overlook the rich safety-relevant features distributed across internal la
arXiv:2604.15741v1 Announce Type: cross Abstract: Uncertainty estimation is a promising approach to detect hallucinations in large language models (LLMs). Recent approaches commonly depend on model internal states to estimate uncertainty. However, they suffer from strict assumptions on how hidden st
arXiv:2604.15842v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated impressive capabilities, yet their internal mechanisms for handling reasoning-intensive tasks remain underexplored. To advance the understanding of model-internal processing mechanisms, we present an inves
arXiv:2510.09033v3 Announce Type: replace Abstract: Recent work suggests that LLMs "know what they don't know", positing that hallucinated and factually correct outputs arise from distinct internal processes and can therefore be distinguished using internal signals. However, hallucinations have mult
arXiv:2604.14180v1 Announce Type: new Abstract: We train a 318M-parameter Transformer language model from scratch on a curated corpus of 1.56 billion tokens of pure Classical Chinese, with zero English characters or Arabic numerals. Through systematic out-of-distribution (OOD) testing, we investigat
arXiv:2602.20091v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) enhances large language models (LLMs) by conditioning generation on retrieved external documents, but the effect of retrieved context is often non-trivial. In realistic retrieval settings, the retrieved document
arXiv:2604.12190v1 Announce Type: cross Abstract: Many malicious actors responsible for disseminating synthetic non-consensual intimate imagery (SNCII) operate within internet forums to exchange resources, strategies, and generated content across multiple platforms. Technically-sophisticated actors
arXiv:2601.19917v2 Announce Type: replace Abstract: Strategic planning is critical for multi-step reasoning, yet compact Large Language Models (LLMs) often lack the capacity to formulate global strategies, leading to error propagation in long-horizon tasks. Our analysis reveals that LLMs possess lat
arXiv:2604.09870v1 Announce Type: cross Abstract: We investigate how looped transformers encode human preference in their internal iteration states. Using Ouro-2.6B-Thinking, a 2.6B-parameter looped transformer with iterative refinement, we extract hidden states from each loop iteration and train li
arXiv:2604.10697v1 Announce Type: new Abstract: Large language models frequently exhibit hallucinations: fluent and confident outputs that are factually incorrect or unsupported by the input context. While recent hallucination detection methods have explored various features derived from attention m
arXiv:2604.11337v1 Announce Type: cross Abstract: The dominant paradigm of local multi-agent systems -- orchestrated, enterprise-bounded pipelines -- is being superseded by internet-wide agent societies in which autonomous agents discover each other through open registries, interact without central
arXiv:2604.10788v1 Announce Type: cross Abstract: Tool-Integrated Reasoning (TIR) has emerged as a promising direction by extending Large Language Models' (LLMs) capabilities with external tools during reasoning. Existing TIR methods typically rely on external tool documentation during reasoning. Ho
OpenAI's chief revenue officer, Denise Dresser, sent a four-page memo to employees on Sunday about the company's strategic direction, emphasizing the need to lock in users and grow its enterprise business. The memo, which was viewed by The Verge, repeatedly underlines the importance of building a mo
arXiv:2604.09446v1 Announce Type: cross Abstract: The Tactile Internet demands sub-millisecond latency and ultra-high reliability, as high latency or packet loss could lead to haptic control instability. To address this, we propose the Mode-Domain Architecture (MDA), a bilateral predictive neural ne
arXiv:2604.07659v1 Announce Type: new Abstract: Large language models (LLMs) hold significant promise for healthcare, yet their reliability in high-stakes clinical settings is often compromised by hallucinations and a lack of granular medical context. While Retrieval Augmented Generation (RAG) can m
arXiv:2604.06696v1 Announce Type: new Abstract: The rapid development of AI agent systems is leading to an emerging Internet of Agents, where specialized agents operate across local devices, edge nodes, private services, and cloud platforms. Although recent efforts have improved agent naming, discov
arXiv:2604.08271v1 Announce Type: new Abstract: While numerous machine unlearning (MU) methods have recently been developed with promising results in erasing the influence of forgotten data, classes, or concepts, they are also highly vulnerable-for example, simple fine-tuning can inadvertently reint
arXiv:2604.06262v1 Announce Type: cross Abstract: Contextual clinical reasoning demands robust inference grounded in complex, heterogeneous clinical records. While state-of-the-art fine-tuning, in-context learning (ICL), and retrieval-augmented generation (RAG) enable knowledge exposure, they often
Anthropic said this week that it limited the release of its newest model, dubbed Mythos, because it is too capable of finding security exploits in software relied upon by users around the world. Are real cybersecurity concerns a cover for a bigger problem at the frontier lab?
arXiv:2511.07176v3 Announce Type: replace-cross Abstract: Internet of Agents (IoA) envisions a unified, agent-centric paradigm where heterogeneous large language model (LLM) agents can interconnect and collaborate at scale. Within this paradigm, federated fine-tuning (FFT) serves as a key enabler th
arXiv:2604.04411v1 Announce Type: cross Abstract: Visual document understanding (VDU) is a challenging task for large vision language models (LVLMs), requiring the integration of visual perception, text recognition, and reasoning over structured layouts. Although recent LVLMs have shown progress on
arXiv:2604.03587v1 Announce Type: cross Abstract: Reasoning language models (RLMs) are increasingly used in programming. Yet, even state-of-the-art RLMs frequently introduce critical security vulnerabilities in generated code. Prior training-based approaches for secure code generation face a critica
arXiv:2604.04262v1 Announce Type: cross Abstract: Autonomous underwater vehicles (AUVs) and sensor nodes increasingly support decentralized sensing and coordination in the Internet of Underwater Things (IoUT), yet most deployments rely on static trust once authentication is established, leaving long
arXiv:2604.03233v1 Announce Type: new Abstract: The conservation of cultural heritage increasingly relies on integrating technological innovation with domain expertise to ensure effective monitoring and predictive maintenance. This paper presents a novel framework to support the preservation of cult
arXiv:2603.17837v2 Announce Type: replace-cross Abstract: During conversational interactions, humans subconsciously engage in concurrent thinking while listening to a speaker. Although this internal cognitive processing may not always manifest as explicit linguistic structures, it is instrumental in
arXiv:2604.02361v1 Announce Type: cross Abstract: Detecting Internet routing instability is a critical yet challenging task, particularly when relying solely on endpoint active measurements. This study introduces TRACE, a MachineLearning (ML)pipeline designed to identify route changes using only tra
arXiv:2604.03098v1 Announce Type: new Abstract: Large language model (LLM) agents learn by interacting with environments, but long-horizon training remains fundamentally bottlenecked by sparse and delayed rewards. Existing methods typically address this challenge through post-hoc credit assignment o
arXiv:2604.02371v1 Announce Type: cross Abstract: Visual long-document understanding is critical for enterprise, legal, and scientific applications, yet the best performing open recipes have not explored reasoning, a capability which has driven leaps in math and code performance. We introduce a synt
arXiv:2604.02784v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) excel at multimodal tasks, but they remain vulnerable to hallucinations that are factually incorrect or ungrounded in the input image. Recent work suggests that hallucination detection using internal representations is m
arXiv:2604.02268v1 Announce Type: new Abstract: Agent skills, structured packages of procedural knowledge and executable resources that agents dynamically load at inference time, have become a reliable mechanism for augmenting LLM agents. Yet inference-time skill augmentation is fundamentally limite