Infercrane released Commerce-1, an open-weight 27B model that handles bounded decisions in commerce agents (product selection, payment routing, fulfillment). It scores supplied candidate actions directly and returns typed answers with probability distributions, generating zero output tokens. Weights, an Apache-2.0 runtime, demos, and a technical article are public.
EmpirioLabs released Aplomb 1, a 5.3B open-weights decision model built on Qwen3.5-4B that reads up to 1M tokens of text, JSON, images, video and audio in a single request. It returns probabilities for every tool and each enum/boolean argument, letting agents act on confident calls and defer uncertain ones to larger models. It ranks #1 on the Hugging Face Typed Decisions benchmark and #1 among 4B models on Decision Index 0.2.1.
EmpirioLabs released Aplomb 1, a 5.3B open-weights decision model built on Qwen3.5-4B that reads up to 1M tokens of text, JSON, images, video and audio in a single request. It returns probabilities for every tool and each enum/boolean argument, letting agents act on confident calls and defer uncertain ones to larger models. It ranks #1 on the Hugging Face Typed Decisions benchmark and #1 among 4B models on Decision Index 0.2.1.
TypeSafe AI, founded by ex-OpenAI researcher Diogo Almeida, released Jev on September 15, 2026 after two years in stealth — a frontier model that takes unstructured state plus typed questions and returns parallel, calibrated decisions instead of generated text. It is trained with a new objective, Reinforcement Learning for Calibrated Decisions (RLCD), positioned against RLHF and RLVR. TypeSafe claims roughly two orders of magnitude faster and cheaper inference than LLMs on decision tasks, and community reaction has been intense: follow-up analyses, a JevBench benchmark, and open-weight imitators like Kev appeared within days.
TypeSafe AI, founded by ex-OpenAI researcher Diogo Almeida, released Jev on September 15, 2026 after two years in stealth — a frontier model that takes unstructured state plus typed questions and returns parallel, calibrated decisions instead of generated text. It is trained with a new objective, Reinforcement Learning for Calibrated Decisions (RLCD), positioned against RLHF and RLVR. TypeSafe claims roughly two orders of magnitude faster and cheaper inference than LLMs on decision tasks, and community reaction has been intense: follow-up analyses, a JevBench benchmark, and open-weight imitators like Kev appeared within days.
The model's developer released DecisionTune 1.0, an Apache-2.0 395M encoder (ModernBERT-large plus a 4 KB scoring head) that scores given options rather than generating text, aimed at routine agent decisions like tool routing and yes/no checks. It runs fully locally via PyTorch, MLX, or ONNX backends and ships with an MCP server for local assistants. The developer is seeking feedback on where it picks wrong.
The model's developer released DecisionTune 1.0, an Apache-2.0 395M encoder (ModernBERT-large plus a 4 KB scoring head) that scores given options rather than generating text, aimed at routine agent decisions like tool routing and yes/no checks. It runs fully locally via PyTorch, MLX, or ONNX backends and ships with an MCP server for local assistants. The developer is seeking feedback on where it picks wrong.
Perplexity released Decider v1.3 and Decider Flash v1.3, open-weight decision models that return probability distributions over answer options instead of generating text. Both support text and images, and v1.3 adds a new `locate` type that extracts verbatim spans with character offsets for NER, PII detection, and extractive QA. The models are available on Hugging Face, OpenRouter, and Perplexity's API.
Perplexity released Decider v1.3 and Decider Flash v1.3, open-weight decision models that return probability distributions over answer options instead of generating text. Both support text and images, and v1.3 adds a new `locate` type that extracts verbatim spans with character offsets for NER, PII detection, and extractive QA. The models are available on Hugging Face, OpenRouter, and Perplexity's API.
InternLM released Intern-Decision-4B, a multimodal structured decision model fine-tuned from Qwen3.5-4B, alongside a 0.8B variant, with model weights, a demo, and a GitHub repo. The models take a shared state, a question schema, and optional images, and return answer distributions for all questions in a single forward pass without free-form generation. This gives practitioners a deterministic structured-candidate-scoring API for decision tasks rather than autoregressive text sampling.
InternLM released Intern-Decision-4B, a multimodal structured decision model fine-tuned from Qwen3.5-4B, alongside a 0.8B variant, with model weights, a demo, and a GitHub repo. The models take a shared state, a question schema, and optional images, and return answer distributions for all questions in a single forward pass without free-form generation. This gives practitioners a deterministic structured-candidate-scoring API for decision tasks rather than autoregressive text sampling.