Nemotron-Labs-Sigma, 3B and 8B continuous diffusion language models with 16-D embeddings and 3.46x speculative decoding ...
Meta FAIR’s Self-Improving Memory lets Kimi-K2.6 write its own LOAD and OFFLOAD memory prompts, then distills them into its weights. Optimized prompts score 56.0 versus 44.6 for the best hand-written ...
Meta FAIR’s Self-Improving Memory lets Kimi-K2.6 discover its own memory prompts, scoring 56.0 versus 44.6 for hand-written ...
Perplexity Orchestrator API unifies OpenAI, Anthropic, open-weight models; routing lifted Fable 5.2 from 38 to 41 ...
AI attackers are speeding up: the 4-pillar incident response playbook for AI platforms, plus Fireworks AI and Klue.
We ranked the 13 best agent gateways of 2026 by how they govern model, MCP tool and agent-to-agent traffic, with verified ...
RadixArk released DaisyRose-27B, an Apache 2.0 agentic coding model post-trained from Qwen3.8-27B with reinforcement learning only. It more than doubles Terminal Bench 4.1 pass@1 to 12.0 and runs on a ...
Google Deeepmind's Gemini 4 Neon offers 1M context at $3/$15 per million tokens and tops AA’s Coding Agent Index.
Artificial Intelligence is the process of using computers and machines to mimic human problem-solving abilities.
TinyFish published two engineering research articles on agentic search. One defines a 7-phase production architecture with ...
Hugging Face released Qwen3.8-27B-pi-adapted, an Apache-2.0 LoRA adapter trained with reinforcement learning for the pi coding agent. It lifts SWE-bench Pro hard-51 pass@1 from 39.2% to 64.7% and ...
Perplexity Computer Multiagent runs up to 16 parallel Claude, GPT and Gemini agents that cross-check each other’s work.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results