# Pistis introduces 27B- and 9B-parameter multimodal models via new training framework

Digest AI · Generative AI & Models · published 2026-09-25T04:00:00Z

Canonical: https://digestai.news/story/pistis-introduces-27b-and-9b-parameter-multimodal-models-via-new-train

## Summary

Researchers released the Pistis model family on arXiv, featuring two multimodal large language models built on Qwen3.6 and Qwen3.5. The 27B-parameter model uses Qwen3.6, while the 9B-parameter model is based on Qwen3.5. Both leverage a novel post-training framework called Interleaved Distillation and Reinforcement Learning (IDRL), which alternates between on-policy distillation and reinforcement learning for better knowledge transfer and optimization stability.

The framework produces two specialized variants per scale: Pistis-Thinking for deep multimodal reasoning and Pistis-Agentic for long-horizon planning, iterative reasoning, and tool use. Pistis-Agentic excels in multimodal search. The team also introduced Pistis-Auto-Harnessing (PAH), a system-level method that optimizes inference harnesses without altering model parameters or increasing interaction costs. Experiments show PAH improves performance without parameter updates.

## Key points

- Pistis model family includes 27B-parameter (Qwen3.6-based) and 9B-parameter (Qwen3.5-based) multimodal LLMs
- IDRL framework alternates distillation and reinforcement learning for stronger performance and stability
- Pistis-Agentic variant excels in multimodal search and supports long-horizon agentic tasks

## Why it matters

The Pistis framework and models advance multimodal AI capabilities, particularly in reasoning and agentic behavior, with potential applications in search and complex decision-making systems.

## Sources

1. [Pistis Technical Report](https://arxiv.org/abs/2609.28554) (arXiv cs.AI, 2026-09-25, primary source)

## Cite

Digest AI, "Pistis introduces 27B- and 9B-parameter multimodal models via new training framework", 25 September 2026, https://digestai.news/story/pistis-introduces-27b-and-9b-parameter-multimodal-models-via-new-train

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/pistis-introduces-27b-and-9b-parameter-multimodal-models-via-new-train.json