CoworkOS harness scales agent coworkers for real-world automation
CoworkOS uses GLM-5.3 backbone to post-train Qwen3.6-35B-A3B, raising average benchmark scores by 9.76 points.
35
AI model
Qwen3.6-35B-A3B
- Mentions · 7d0
- Mentions · 30d10
- All mentions24
- First seenSep 10, 2026
- Last mentioned7d ago
Timeline
24 articles · newest firstWISD self-distills reasoning models using a deliberately weaker copy
Pruning raises Qwen3.5-4B from 57.7% to 70.5% on HMMT 2025 and from 39.1% to 56.7% on LiveCodeBench v6.
44
DiffuSpace releases Clover-35B-A3B-Preview diffusion language model
The text-only model uses about 3B active parameters per token and a 128K context window.
48
Hirundo says Qwen3-Coder writes weaker code for some customers
Hirundo reports the gap closed after it removed CCP alignment from the weights, with coding success unchanged on ten other tasks.
62
NVIDIA releases Dory1.0-4B, a looped 4B reasoning model
The BF16 checkpoint uses a 256K context, OpenMDW-1.1, and variable loop counts without retraining.
62
tencent/Hy-Memory-30B-A3B — new model trending #30 on Hugging Face
Tencent released Hy-Memory-30B-A3B, a 3B-active memory writer that leads Mem0, MemOS, and Hy-Memory scores.
52
LFM2.5-24B-A2B: Built for fast on-device agents
Liquid AI released open-weight LFM2.5-24B-A2B, a 24B MoE with 2B active parameters for on-device agents.
70
Data World: Scaling Data Environments from Scratch
Data World synthesizes data-agent tasks and trains DataWorld-35B-A3B, which beats its Qwen3.6 base on several benchmarks.
52
Liquid AI Releases LFM2.5-24B-A2B: A 2B-Active MoE for On-Device Agents
Liquid AI released LFM2.5-24B-A2B, an open 24B MoE with 2.45B active parameters for local agents.
64
LiquidAI/LFM2.5-24B-A2B — new model trending #11 on Hugging Face
Liquid AI releases LFM2.5-24B-A2B, a 24B MoE with 2.45B active parameters for on-device agents.
72
openbmb/MiniCPM-V-4.7-35B-A3B — new model trending #29 on Hugging Face
OpenBMB released MiniCPM-V 4.7 35B-A3B, its first on-device mixture-of-experts vision-language model.
66
openbmb/MiniCPM-V-4.7-35B-A3B-gguf — new model trending #30 on Hugging Face
OpenBMB released GGUF weights for MiniCPM-V 4.7 35B-A3B, an on-device multimodal MoE model.
64
T-Search: An Open Agentic Retriever and Playground for Hard Multi-Step Search
T-Search, fine-tuned from Qwen3.6-35B-A3B, reaches 56.0 Recall@10, 14.4 points above its base.
52
Kolibri Has Landed: A Sovereign Open-Weight Model
Aleph Alpha released Kolibri, an Apache 2.0 English-German MoE with 78B total and 3B active parameters.
67
QuantCode Model: Specializing Language Models for Executable Algorithmic Trading Code
Continued pretraining and SFT specialize Qwen models for executable Backtrader trading code, raising Judge Pass to 58.2%.
48
H Company Releases Holo4: Open-Weight Computer-Use Models That Click, Code and Call Tools Across Desktop, Web, Android and APIs
H Company releases Holo4 open-weight computer-use models (27B dense, 35B-A3B MoE) that operate GUIs, code and tool calls across desktop, web, Android and APIs.
68
ROSS: Relearning from Self-Generated Rollouts through Selective Supervision
ROSS reuses historical self-generated rollouts with selective supervision, lifting Qwen3.6 SWE-bench Verified from 64.2% to 68.4%.
56
SlimWise: Decoupling Expert Pruning Across Prefill and Decode for Efficient MoE Serving
SlimWise prunes MoE experts only at decode, lifting Qwen3.6 throughput up to 1.81x in vLLM.
56
CompoWorld: Compositional Environment Scaling for General Agents
CompoWorld composes 448 services to train Qwen3.6-35B-A3B, beating Claude Opus 4.6 on AutomationBench.
60
Learning to Learn from Context: Synthetic Training from Perturbed Public Documents
Synthetic document perturbations train LLMs to reason from context, lifting Qwen3.6-35B-A3B to 24.6% on CL-bench.
48
Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms
VHD-Play builds 3,300 agentic RL environments and lifts Qwen3.6-35B-A3B's mean score from 0.204 to 0.815.
62
Best Open-Source Agent Harnesses for Local LLMs in 2026
A 2026 guide ranks 11 open-source agent harnesses, including OpenCode, Goose, Cline, and OpenHands, by local-LLM support, licensing, and safety controls.
28
[AINews] not much happened today
Latent Space AI news digest covers Anthropic's Claude Code Projects, Google's managed agent APIs, TypeSafe's Jev classifier, and OpenAI's Astra for Law launch.
35
DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF — new model trending #30 on Hugging Face
DavidAU releases Qwen3.8-27B-TWIN-TURBO, an uncensored GGUF fine-tune claiming sharply reduced thinking tokens and self-reported benchmark gains.
25
Appears with
- Hugging Faceorganization · 4
- NVIDIAvendor · 4
- LFM2.5-24B-A2Bai model · 3
- Gemma-4-26B-A4B-itai model · 2
- Qwen3.5-4Bai model · 2
- LFM2.5-24B-A2B-Baseai model · 2
- Liquid AIvendor · 2
- Qwen3.8-27Bai model · 2
- Nemotron-3.5-Lightningai model · 2
- OpenBMBorganization · 2
- vLLMproduct · 2
- MiniCPM-V-4.7-35B-A3Bai model · 2
- Applevendor · 2
- OpenBMBvendor · 2
- Liquid AIorganization · 2
- MiniCPM-V 4.7product · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.