A new framework called WER (Write, Execute, and Refine) trains a Skill Optimizer to improve tool-using agents' performance by learning from execution feedback, achieving a 7.80-point average Pass@1 im…
A new arXiv study (2608.14641v1) evaluating four open-source model routers across RouterBench, BFCL v4, tau2-bench, and WebArena found that only vLLM Semantic Router varies with prompt content, yet it…
Pokee AI released Pokee-Isaac 28B, a 28B text-only foundation model with a 10M-token context window designed to run inside the customer boundary. The model scores 93.3% on RULER at 10M tokens, leads B…
Pokee-Isaac 28B, the world's first real 10M-token context frontier-class agentic model, is now deployable on a single GPU starting from RTX 4090, according to its release announcement. The model achie…
MLCommons added an Agentic Inference benchmark to MLPerf on July 8, 2026, measuring how LLM serving systems handle multi-turn agent tasks with growing context and tool use. The benchmark uses 490 codi…