Search: “llm”

Hey everyone — I’m building TensorSharp, an open-source LLM inference engine. Here are the latest DeepSeek V4.1 Flash GGUF results using its native ggml_cuda backend. Setup: 8× NVIDIA A40, layer split

arXiv:2609.11008v1 Announce Type: cross Abstract: Decentralized Finance (DeFi) has emerged as a rapidly growing blockchain-based financial service, where market transaction dynamics and underlying sma

I'm a teacher looking into running an LLM locally. I've been using ChatGPT for a lot of this work, so I started looking at Ollama because I understand it's designed to run LLMs locally. That said, I'm

arXiv:2609.10854v1 Announce Type: cross Abstract: Conventional vulnerability analysis relies on either system access or dynamic interaction, all of which may be unavailable to third-party analysts aud

arXiv:2609.11030v1 Announce Type: new Abstract: AI agents increasingly act through tools and delegated authority, but general incident repositories rarely capture the mechanisms needed to compare publ

arXiv:2609.11231v1 Announce Type: cross Abstract: This paper presents SurgicalRoomAgent, a voice-interactive multi-agent system for smart operating rooms based on large language models (LLMs). The sys

arXiv:2609.10922v1 Announce Type: new Abstract: Auto-research agents have shown the potential to automate hypothesis generation, experiment execution, and iterative refinement. However, scaling this p

arXiv:2609.10893v1 Announce Type: new Abstract: Recent advances in large language models have transformed human-computer interaction. Despite their fluency, these models often produce texts that are g

arXiv:2603.27771v3 Announce Type: replace-cross Abstract: Multi-agent systems composed of large generative models are rapidly moving from laboratory prototypes to real-world deployments, where they jo

arXiv:2609.11192v1 Announce Type: new Abstract: Soft context compression condenses a context into a few memory tokens that a frozen LLM consumes in place of the raw text, but existing compressors fix

arXiv:2609.10810v1 Announce Type: new Abstract: Minimal-edit Grammatical Error Correction (GEC) is a challenging task for zero- and few-shot prompted Large Language Models (LLMs), which systematically

arXiv:2609.11699v1 Announce Type: new Abstract: On-Policy Self-Distillation (OPSD) has emerged as a popular paradigm for large language model (LLM) self-improvement, allowing models to act as their ow

arXiv:2609.11737v1 Announce Type: cross Abstract: Collective intelligence depends not only on the capabilities of individual members, but also on how those members are organized. Yet artificial multi-

arXiv:2609.11209v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) improves knowledge-intensive large language model (LLM) applications by conditioning generation on retrieved docu

I’ve been building 'Spomin', a router that replaces context with summaries directly in the KV cache. The goal is to keep long running sessions going without repeatedly stopping for full compaction and

arXiv:2609.10824v1 Announce Type: cross Abstract: Before an LLM agent tackles tasks in a new environment, it can inspect available corpora and tools and construct reusable resources such as indices, s

Astra's launch has produced a strange discourse. The reporting that broke the story framed the model's use of recurrent depth primarily as a safety regression, because it means the model reveals less

Looking for tools to build/run an engine to do STT-LLM-TTS basically. I know how to run all of them separately, and if need be I can build one myself, but I was curious if there is already an open sou

arXiv:2609.08592v1 Announce Type: new Abstract: Evaluating tool-augmented LLM agents requires diverse, realistic user inputs yet most evaluation frameworks use flat role descriptions ('you are an angr

arXiv:2609.05837v1 Announce Type: new Abstract: LLM-based agents are increasingly deployed in real-world applications through tool-use APIs, yet training them for specific environments remains fundame

arXiv:2606.19795v2 Announce Type: replace-cross Abstract: Electronic design automation (EDA) is multi-stage and handoff-heavy, relying on transfers among humans, design artifacts, and multiple tools.

arXiv:2609.08861v1 Announce Type: new Abstract: Benchmark scores are a central currency in model releases: they inform purchasing decisions, shape public trust, and influence policy. Yet, a key assump

arXiv:2609.07102v1 Announce Type: cross Abstract: Astronomical spectra encode rich physical information, but drawing scientific conclusions from spectral features typically requires expert interpretat

arXiv:2609.05437v1 Announce Type: new Abstract: Previous AI alignment efforts have focused primarily on first-order social norms -- teaching models what is socially acceptable or unacceptable (e.g., `

arXiv:2609.05776v1 Announce Type: new Abstract: Evaluating enterprise agents on domain-specific benchmarks is critical, yet public benchmarks rarely evaluate whether agents can integrate business know

arXiv:2602.05354v3 Announce Type: replace Abstract: Autonomous web agents are increasingly deployed in moderation and policy enforcement, where correct decisions often depend on evidence that is not i

arXiv:2601.13591v3 Announce Type: replace Abstract: Recent LLM-based data agents aim to automate data science tasks ranging from data analysis to deep learning. However, the open-ended nature of real-

arXiv:2609.08790v1 Announce Type: cross Abstract: Threat hunting increasingly depends on converting unstructured knowledge (e.g., Cyber Threat Intelligence reports) into actionable hunt leads: concise

arXiv:2609.10155v1 Announce Type: new Abstract: We approach a cognitive simulation perspective on episodic and semantic memory in multiple-choice question answering by incorporating text from individu

arXiv:2609.08015v1 Announce Type: new Abstract: Long-running AI agents may read state, reason, wait for tools or human approval, and perform an external action much later. The state that justified the

arXiv:2503.19599v3 Announce Type: replace-cross Abstract: While software requirements are often expressed in natural language, verifying the correctness of a program against such requirements is a har

arXiv:2609.06250v1 Announce Type: cross Abstract: Security Operations Centers (SOCs) process large amounts of tickets, most of which are low-interest events not worthy of further investigation. The re

arXiv:2605.21694v2 Announce Type: replace-cross Abstract: Connecting large language models (LLMs) to defensive enforcement requires more than asking a model whether an attack is happening. A defender

arXiv:2609.07901v1 Announce Type: new Abstract: Weight quantization largely determines the economics of serving open-weight LLMs. Its costs are usually assessed with capability benchmarks, on which 4-

arXiv:2609.10505v1 Announce Type: new Abstract: Credit default prediction is a tabular classification problem in which modest gains in F1 translate directly into reduced financial exposure. We ask whe

arXiv:2609.08258v1 Announce Type: new Abstract: Long-running language-model agents depend on persistent memory. Many agent-memory systems preserve history through soft revocation: a contradicted fact

arXiv:2609.08789v1 Announce Type: cross Abstract: Frontier AI developers publish safety frameworks that commit them to evidencing whether their models are dangerous. The European Union and California

arXiv:2609.06835v1 Announce Type: cross Abstract: Agentic AI systems execute complex tasks through long-horizon workflows of planning, tool use, and multi-agent coordination. Task failures in these sy

arXiv:2609.05928v1 Announce Type: cross Abstract: Large language models now compute correct tax liabilities on over 90% of well-formed cases in statutory benchmarks, which makes them candidates for th

arXiv:2609.09561v1 Announce Type: new Abstract: Surveys remain the primary way researchers grasp the lineage of methods within an AI subfield, but they scale poorly against the current rate of publica

arXiv:2609.05910v1 Announce Type: cross Abstract: Reinforcement learning (RL) excels on tasks with verifiable rewards, but in open-ended tasks, the reliability of reward models remains a key challenge

arXiv:2609.07065v1 Announce Type: new Abstract: Agent-to-agent (A2A) alpha discovery is slowed by repeated feedback cycles between mining and evaluation agents, whose hand-offs, in contemporary LLM mu

arXiv:2504.00285v2 Announce Type: replace Abstract: Large Language Models (LLMs) are effective at deceiving when prompted to do so. Models that demonstrate better performance on reasoning tasks are al

arXiv:2609.09628v1 Announce Type: cross Abstract: Inferring speaker relationships from spoken conversations is an important step towards socially aware speech understanding. However, this task remains

arXiv:2609.05677v1 Announce Type: cross Abstract: Lifelong LLM agents increasingly rely on external skill artifacts as one element for preserving and reusing capabilities over time. These skills (usua

arXiv:2609.08826v1 Announce Type: cross Abstract: When an external reference set (an anchor) is used to decompose an LLM-judge panel's error into a quality signal and a shared common-mode error, stand