Explore tools, prompts, skills, news and resources related to AI 第69页.
Prompt works related to AI 第69页
Latest articles, prompts, use cases and editorial content about AI 第69页
Anthropic released Claude Fable 5.2 and Mythos 5.2, claiming gains in coding, reasoning and vision, with Fable 5.2 topping the Artificial Analysis Intelligence Index at 65 and setting records on HLE-Diamond and FrontierC...
Meta Superintelligence Labs released Muse Ember, a hosted multimodal reasoning model aimed at high-volume agent subtasks such as tool calls, routing, extraction and long document parsing. It offers a 1M-token context win...
DeepMind researchers used a new AI tool to formally verify the Signal encryption protocol, confirming it works as intended. The tool aims to scale formal verification, with a stretch goal of verifying all software worldw...
A new arXiv paper analyzes agentic manipulation policies (AMPs), where a generalist AI model directly commands a robot manipulator and adapts actions as tasks unfold. The authors present AMP1, a reference harness that ru...
This arXiv paper analyzes the reliability of majority-vote pseudo-labels in test-time reinforcement learning with online Direct Preference Optimization, decomposing the error into population-majority bias and prompt-depe...
The paper introduces a radiology agentic framework that standardizes how an orchestrator calls modular tools to produce structured reports. It simulates report generation on a multi-modality corpus using either a catalog...
BitDecoding-FP4 is an algorithm-system co-design for accurate and efficient native FP4 KV cache decoding in long-context LLM serving. It combines dual-residual query quantization, underflow-aware probability scaling, and...
Researchers built a quantum program library in the Lean theorem prover in which LLM agents synthesize novel programs against formal specifications and verify their correctness and cost. Agent teams collaborate by sharing...
The paper addresses graph similarity computation, where exact Graph Edit Distance and Maximum Common Subgraph are NP-hard, and existing GNN approaches have mainly been tested on small graphs. It proposes FiLSim, a scalab...
Researchers re-engineered a 421M-parameter non-autoregressive multiple-choice checkpoint and tested whether its answer depends on where an option is listed. Across 951 Qwen-verified questions under cyclic rotations, the...
The paper studies how stale repository instruction files such as AGENTS.md and CLAUDE.md affect LLM-based coding agents. Using three real-world stale instructions, 22 maintenance tasks, and 732 trajectories from two mode...