Tech Meridian ← ENTITY INDEX
PROMY MERIDIAN RU

COMPANY · ENTITY #8627

Qwen3.6

Related event timeline, sources and context from the news index.

EVENT TIMELINE

3

RESEARCH · 1 SOURCE · The Decoder

Study finds agent 'harnesses' drive token costs but rarely improve coding performance

Researchers at Shandong University (Liu and Han) ran five models through three shipped coding-agent harnesses (Claude Code, OpenCode, mini-SWE-agent) on SWE-bench Verified and a larger 447-task pool, and found that swapping harnesses changes results little beyond run-to-run noise while token costs can triple because of large system prompts and repeated context. OpenCode consistently trailed the others on the larger pool (partly due to output limits), and many reported leaderboard gaps fall below statistical detectability given sample sizes and noise.

7.0

MODELS · 1 SOURCE · Hugging Face

H company releases Holo4 agentic models (27B & 35B-A3B) and Holotron4 Nano

H company announced Holo4, a new series of generalist agentic models (Holo4-27B and Holo4-35B-A3B) available via the H Models API, plus an updated Holotron4 Nano. The models are trained to interact across GUIs, code sandboxes, Android/web and APIs, report benchmark scores on OSWorld 2.0 and AutomationBench, and H company has published the evaluation trajectories at trajectories.hcompany.ai and on Hugging Face.

7.0

MODELS · 1 SOURCE · arXiv cs.AI

Pistis: 27B and 9B multimodal LLM family with IDRL post-training (arXiv:2609.28554v1)

arXiv:2609.28554v1 presents the Pistis model family—27B- and 9B-parameter multimodal LLMs built on Qwen3.6 and Qwen3.5—trained via a scalable post-training framework that starts with large-scale multimodal supervised fine-tuning and then applies Interleaved Distillation and Reinforcement Learning (IDRL). The paper describes two specialized variants (Pistis-Thinking for deep multimodal reasoning and Pistis-Agentic for long-horizon planning and tool use), plus a system method Pistis-Auto-Harnessing (PAH); both scales reportedly outperform their corresponding base models, with the Agentic variant strong in multimodal search.

7.0