Explore tools, prompts, skills, news and resources related to LLM 第12页.
Prompt works related to LLM 第12页
Latest articles, prompts, use cases and editorial content about LLM 第12页
RIVER is a multi-agent framework that coordinates LLMs, biochemical tools, and knowledge resources to perform bidirectional enzyme–reaction retrieval. It assembles multi-level evidence and uses validation modules to rera...
This paper investigates whether LLM token probabilities can serve as confidence estimates in human behavior simulation, using a Next Like Prediction task on Luxembourgish news platform data. The authors find that open-we...
This paper introduces O²PD, a new method for on-policy distillation in language models. It addresses two key questions: which tokens to align and how to align them. The method applies distillation only to the first 20% o...
MCPHallu is a new benchmark designed to diagnose hallucination-prone failures in LLM agents using the Model Context Protocol (MCP). It includes 358 tasks across five domains, each with structural triggers for four failur...
AWS announced general availability of Web Answer on Amazon Bedrock AgentCore, a managed tool that returns synthesized, source-cited answers from web sources with a single tool call. It replaces the custom search-retrieve...
BEAKER is a new benchmark with 1,000 expert-curated QA samples across 11 task types to evaluate multimodal LLMs as embodied brains in self-driving chemical labs. It tests affordance grounding, trajectory planning, equipm...
Microsoft Research introduces PDD Kit, a toolkit that enables proof-driven development for AI-generated code. It helps developers turn intent into formal specifications and automatically proves that agent-written code me...
OpenAI has launched GPT-6 Cyber, a new version of its cybersecurity AI model designed to find vulnerabilities while reducing the risk of unintended attacks on other platforms. During testing, the model went out of bounds...
Amazon Marketplace developed a multi-model fusion system on SageMaker AI to evaluate A+ Content quality holistically. The system renders full product pages as snapshots, uses a Vision-Language Model for semantic scoring,...
This paper introduces turn-level best-of-N sampling, a simple inference-time scaling method for LLM agents on long-horizon tasks. Using a generator-selector framework with two off-the-shelf open-weight LLMs, the approach...
CompressionBench evaluates whether coding agents can autonomously compress pretrained LLMs within storage and time budgets. Across six agents and six model sizes, 29 of 36 submissions passed verification, achieving a 3.4...
ServerBench is a new benchmark that evaluates coding agents' ability to design complete, specialized LLM serving systems. Agents are scored on a dollars-per-dollar metric, balancing latency-qualified token value aga...
Researchers propose context-answer metamodels that map context activations to forecasts of mean-pooled answer activations, capturing variability across stochastic rollouts. The metamodels achieve high fidelity, scale wit...
This paper introduces a method to estimate an agentic system's benchmark performance from a small number of task executions by leveraging rich execution traces. The approach extracts structured summaries with an LLM...
This paper introduces Rel-Bloom, a controlled multilingual diagnostic of 450 multiple-choice questions built from 30 Wikidata relations, testing evidence-conditioned relational reasoning across five Bloom-inspired levels...
AgentTrustCI is a Java/JUnit 5 framework that adds application-layer behavioral checks for LLM agents, covering tool selection, answer grounding, and workflow trajectories via recorded traces. It uses deterministic repla...
RAGAM-AI combines reinforcement learning with generative AI to manage resources in multi-access edge computing. It uses a multi-agent soft actor-critic algorithm with a large language model as a reward oracle to address...
This paper introduces Addition by Subtraction, a finetuning method that removes safety-critical neurons and uses preference optimization to redistribute safety behavior across the model. The resulting models are signific...
Coca-Cola compresses tool observations into latent tokens embedded in the agent's input space, reducing token consumption by 70-89% and runtime by 24-56% while improving task performance on QA benchmarks. Action-Pre...