Related papers: Beyond the Attention Stability Boundary: Agentic S…

While reasoning-augmented large language models (RLLMs) significantly enhance complex task performance through extended reasoning chains, they inevitably introduce substantial unnecessary token consumption, particularly for simpler problems…

Retrieval-augmented generation (RAG) has been extensively employed to mitigate hallucinations in large language models (LLMs). However, existing methods for multi-hop reasoning tasks often lack global planning, increasing the risk of…

Large Language Models (LLMs), such as OpenAI-o1 and DeepSeek-R1, have demonstrated strong reasoning capabilities. To further enhance LLM capabilities, recent agentic systems, such as Deep Research, incorporate web interactions into LLM…

The rapid proliferation of large language model (LLM)-based agentic systems raises critical concerns regarding digital sovereignty, environmental sustainability, regulatory compliance, and ethical alignment. Whilst existing frameworks…

The inherent non-deterministic nature of autonomous agents, particularly within low-code/no-code (LCNC) environments, presents significant reliability challenges. Agents can become trapped in unforeseen loops, generate inaccurate outputs,…

Large Reasoning Models (LRMs) demonstrate remarkable capabilities on complex tasks, exhibiting emergent, human-like thinking patterns. Despite their advances, we identify a fundamental limitation: current LRMs lack a dedicated meta-level…

Recent advances in LLM-based Text-to-SQL have achieved remarkable gains on public benchmarks such as BIRD and Spider. Yet, these systems struggle to scale in realistic enterprise settings with large, complex schemas, diverse SQL dialects,…

LLMs have demonstrated remarkable proficiency in understanding tasks but continue to struggle with long-context comprehension, particularly with content located in the middle of extensive inputs. This limitation, known as the…

Human cognition operates through two complementary modes: fast intuitive thinking and slow deliberate thinking. Vanilla large language models (LLMs) predominantly follow the fast-thinking paradigm, producing immediate responses; while…

Latent reasoning represents a new development in Transformer language models that has shown potential in compressing reasoning lengths compared to chain-of-thought reasoning. By directly passing the information-rich previous final latent…

Despite the remarkable proficiency of \textit{Large Reasoning Models} (LRMs) in handling complex reasoning tasks, their reliability in safety-critical scenarios remains uncertain. Existing evaluations primarily assess response-level safety,…

Long-horizon robotic manipulation poses significant challenges for autonomous systems, requiring extended reasoning, precise execution, and robust error recovery across complex sequential tasks. Current approaches, whether based on static…

Current large-language models (LLMs) typically adopt a fixed reasoning strategy, either simple or complex, for all questions, regardless of their difficulty. This neglect of variation in task and reasoning process complexity leads to an…

As LLMs achieved breakthroughs in general reasoning, their proficiency in specialized scientific domains reveals pronounced gaps in existing benchmarks due to data contamination, insufficient complexity, and prohibitive human labor costs.…

Large language models (LLMs) fail on over one-third of multi-hop questions with counterfactual premises and remain vulnerable to adversarial prompts that trigger biased or factually incorrect responses, which exposes a fundamental deficit…

Large language models are increasingly deployed as *deep agents* that plan, maintain persistent state, and invoke external tools, shifting safety failures from unsafe text to unsafe *trajectories*. We introduce **AgentFence**, an…

In enterprise operations, the context required for an AI agent task is scattered across systems of record, static information stores, and communication channels. What is stored is system state, a lossy representation of the work that…

Sequence parallelism (SP) serves as a prevalent strategy to handle long sequences that exceed the memory limit of a single device. However, for linear sequence modeling methods like linear attention, existing SP approaches do not take…

Modern large language models (LLMs) have demonstrated impressive capabilities at sophisticated tasks, often through step-by-step reasoning similar to humans. This is made possible by their strong few and zero-shot abilities -- they can…

Semantic communication (SemCom) has emerged as a promising paradigm for next-generation networks. However, its typical end-to-end joint source--channel coding (JSCC) architecture also raises serious privacy concerns. To guide future secure…