FastContext 1.0 4B RL

FastContext-1.0 is a lightweight repository-exploration subagent for LLM coding agents. Instead of letting a single model both explore the repository and solve the task, FastContext separates these two roles: it is invoked on demand by a main coding agent, issues parallel read-only tool calls (READ, GLOB, GREP), and returns compact file paths and line ranges as focused context.

We introduce X-Reasoner, a vision-language model posttrained solely on general-domain text for generalizable reasoning, using a twostage approach: an initial supervised fine-tuning phase with distilled long chainof-thoughts, followed by reinforcement learning with verifiable rewards. Experiments show that X-Reasoner successfully transfers reasoning capabilities to both multimodal and out-of-domain settings, outperforming existing state-of-theart models trained with in-domain and multimodal data across various general and medical benchmarks. More details can be found in the paper: X-Reasoner: T

FrogBoss is built on the Qwen3-32B transformer architecture with a maximum context length of 64k tokens. The model uses multi-turn debugging workflows and complex code reasoning. Unlike general-purpose LLMs, FrogBoss is specialized for software engineering tasks.

OptiMind-SFT is a specialized 20B parameter model designed to bridge the gap between natural language and executable optimization solvers. It automates the translation of complex decision-making problems—such as supply chain planning, scheduling, and resource allocation—into correct MILP formulations.

Description: Fara-7B is Microsoft's first agentic small language model (SLM) designed specifically for computer use. With only 7 billion parameters, Fara-7B is an ultra-compact Computer Use Agent (CUA) that achieves state-of-the-art performance within its size class and is competitive with larger, more resource-intensive agentic systems.

Unlike typical LLMs that are trained to play the role of the "assistant" in conversation, we trained UserLM-8b to simulate the “user” role in conversation (by training it to predict user turns in a large corpus of conversations called WildChat). This model is useful in simulating more realistic conversations, which is in turn useful in the development of more robust assistants.