Prime Intellect Releases Verifiers v1: Composable Tasksets, Harnesses, and Runtimes for Agentic RL Training and Evaluations
Prime Intellect launched verifiers 0.2.0. It previews a rewritten core, shipped under the new verifiers.v1 namespace. Modern evaluations now run coding agents with tools, compaction, and subagents. Accordingly, v1 rebuilds environments to run these agentic workloads at scale. What is verifiers v1? First, consider what verifiers is: Prime Intellect’s environment stack for agentic reinforcement learning and evaluations. Previously, an environment bundled its data, agent logic, and inf
Get smart on it
Prime Intellect released verifiers v1, a framework that breaks down agentic reinforcement learning environments into three separate, reusable components: a taskset that defines the work and scoring, a harness that solves the task, and a runtime where the harness executes. Previously these components were bundled together, but the new architecture allows any taskset to run under any compatible harness, increasing flexibility and reusability. A central interception server manages communication between the agent and inference system, recording traces and handling tool responses to prevent reward hacking during training. The update replaces the previous version's quadratic trace growth with linear growth, enables support for long-horizon training, and allows existing datasets and harnesses from other frameworks to work without rewriting.
Related news
PrismML Releases Bonsai 27B: 1-bit and Ternary Builds of Qwen3.6-27B That Run on Laptops and Phones
PrismML just released Bonsai 27B. It is a low-bit representation of Qwen3.6-27B, not a new pretrain. The architecture is unchanged. Two variants ship under Apache 2.0. Ternary Bonsai 27B uses {−1, 0, +1} weights at a true 1.71 bits per weight. Its ideal size is 5.9GB. 1-bit Bonsai 27B uses binary {−1, +1} weights at 1.125 bits per weight, for 3.9GB. Both are multimodal. The split is ~24.8B language weights, a 0.46B vision tower, and 2.5B in embeddings and the LM head. The vision tower is
Mistral AI Releases Robostral Navigate: An 8B Model Enabling Robots to Navigate Complex Environments Using a Single RGB Camera
Mistral AI has released Robostral Navigate, its first model built for embodied navigation. The 8B model takes RGB images and a plain-language instruction, then moves a robot. Notably, it reaches 76.6% success on R2R-CE validation unseen using only a single RGB camera. What is Robostral Navigate? Robostral Navigate is an 8B model for robotic navigation through complex environments. These environments include offices, residential buildings, commercial buildings, and outdoor settings. You gi
