A cluster of recent arXiv papers from Alibaba's DreamX group, Meta AI, Google Cloud, ByteDance Seed and others is converging on the "agent harness" — the runtime layer handling context construction, s…
ByteDance Seed, SUTD, Georgia Tech, M-A-P, and TokenWave.AI released HarnessDev, a benchmark that scores the runnable harness a model builds rather than the answer it returns, with 6 creator LLMs cons…
ByteDance Seed and UC Santa Cruz researchers introduced Chain-of-Experience (CoE), a technique that improves large language model accuracy by 5.6% on average and cuts API costs by 19% across eight mod…
ByteDance Seed and Tsinghua AIR released CUDA Agent, an agentic reinforcement learning system that trains a large language model to generate CUDA kernels outperforming a compiler. On KernelBench, the …
ByteDance Seed released Seed-2.0-Code, an AI model optimized for agentic coding, on July 30, 2026. The model, priced at $0.50 per 1 million input tokens and $3 per 1 million output tokens with a 262K …