The paper evaluates a manager‑worker scaffold that uses a shared filesystem workspace to orchestrate multi‑agent large language model (LLM) coding tasks without training or tuning. Across nine models—including five open‑weight and four closed‑weight systems—the scaffold yields statistically significant accuracy gains for some models (e.g., Qwen3.8‑27B, GPT‑5.6‑Luna, GPT‑5.6‑Terra, Kimi‑K3, Minimax‑M3) while producing null or negative effects for others (e.g., Qwen3.6‑35B). The study shows that the manager can triple token usage but still achieves higher accuracy at a fraction of the cost compared to larger single‑pass models, with key mechanisms identified as context management and problem decomposition.
By Victor Gao (Sang Won), Vida Khosrowshahi (Sang Won), Ali Khosrowshahi (Sang Won), Xihao Sun (Sang Won), Juhyun Lee (Sang Won), Simon (Sang Won), Lee
The paper reports a large‑scale post‑training ternarisation of the Qwen3 language model, extending a conversion pipeline from the 4B to the 8B variant. Using KOTMS rotation, E2M‑ATQ adaptive ternarisation, and GPTQ‑style error compensation, the authors achieve a 1.361× perplexity ratio across three corpora and retain 78.5% of the FP16 accuracy on zero‑shot tasks, with the 8B model outperforming the 4B by 8.9 percentage points. The study also demonstrates lossless lattice‑aware packing, producing an 8.24 GiB checkpoint that preserves perplexity, and shows that direct packed execution can reach 15.52 tokens/s in 7.35 GiB, though packed GEMV remains slower than FP16 cuBLAS.
By Anirudh Malik, M Sparsh Mehra, Poojith Devan
The paper introduces SCX Router, a lightweight GLiClass-based model selector that assigns suitability scores to inference-time language models without autoregressive generation. It uses a 0.6B-parameter Qwen3 decoder with a shallow bidirectional scorer, preserving a text-only key–value cache across sessions and predicting task attributes such as type, difficulty, and expected output length. The authors build a comprehensive task ontology with 23 families, 115 types, and 1,173 synthetic examples, generating 150,000 verifier-scored tasks to train the router, which outperforms baseline models on LiveBench subsets with a top‑1 score of 0.707 versus 0.696 for the strongest fixed model.
By Ihor Stepanov, Aleksandr Smechov, Mykhailo Shtopko, Dmytro Vodianytskyi, Oleksandr Lukashov
arXiv:2608. 08910v1 Announce Type: cross Abstract: PTQTP decomposes LLM weight matrices into two ternary (trit) planes with two free per-group scales.
By Matteo Grella
arXiv:2607. 04244v1 Announce Type: new Abstract: This report describes our approach to the Efficient Qwen Competition, where the goal is to enable low-latency serving of Qwen3.
By Jaeyeon Kim, Jewon Lee, Bo-Kyeong Kim
arXiv:2609.26333v1 Announce Type: new
Abstract: Prefill and decode reward different approaches to quantization: low-precision arithmetic accelerates prompt processing, while compact weights reduce me...
By Andrei Panferov, Maximilian Kleinegger, Sweta Priyadarshi, Tijmen Blankevoort, Dan Alistarh
StagQ is a multi‑precision weight format for large language models that uses a 2‑bit group‑wise affine base followed by optional 1‑bit refinement planes. Each supported precision can be read as a prefix of the main stream, decoded via a shared affine map without per‑weight lookups, and a sparse side record stores the few weights that the grid handles poorly. Experiments show that StagQ outperforms baseline multi‑precision schemes on Llama‑3.1‑8B, Phi‑4, and OLMo‑2‑7B across various bit‑widths, and its GPU kernel is faster than baseline kernels for most shape‑precision combinations.
arXiv:2609.39223v2 Announce Type: new
Abstract: Large language model (LLM) inference is increasingly moving toward lower precision to realize the throughput of hardware accelerators, but aggressive p...
By Weili Xu, Jisen Li, Yuqing Jian, Chenxi Li, Zhizhou Sha, Yifan Yu, Qingyang Wu, Chenfeng Xu, Zhongzhu Zhou, Tianyi Zhang, Ben Athiwaratkun
arXiv:2609.36654v1 Announce Type: new
Abstract: Large language models make weight storage and memory traffic major inference costs, motivating low-precision formats that represent each weight with on...
By Ruiyi Ding, Jie Li, Kang He, Ziyan Liu, Chengru Song, Yuedong Xu, Yuan Cheng
Instruction-Based Video Editing by Repurposing an Image Editing Model demonstrates that a strong image‑editing model can be adapted to edit videos by operating on video‑VAE latents. The authors tile latent frames into a large virtual image, reuse the editor’s positional encoding, and bridge latent spaces with lightweight projections, fine‑tuning on Ditto‑1M editing triplets. Their experiments show that per‑frame video latents are close enough to the image domain that mature image‑editing priors transfer with minimal adaptation.
By Yunpeng Bai, Yossi Gandelsman, Micha\"el Gharbi, Qixing Huang
arXiv:2608.20953v1 Announce Type: cross
Abstract: Serving large language models cheaply increasingly means shipping models that are both structurally compressed to a fraction of their parameters and...
By Bakbergen Ryskulov, Iker Garc\'ia-Ferrero, David Montero, David Jansen, Ali Hashemi, Jezabel R. Garcia, Antonio Tiene, Rom\'an Or\'us
While draft-model-free speculative decoding offers a promising path to efficient LLM inference, it is frequently constrained by stale draft candidates and the high computational cost of the verificati...