AIAny
Icon for item

ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search

Presents an open 7B dense foundation model for mathematical reasoning and tool-assisted web search, supporting 256K-token context. Key features: hybrid gated sliding-window + global attention for efficient long-context training, FP8 Muon optimizer, progressive 16K→64K→256K curriculum, and open-source weights, data, and recipes.

Introduction

The paper argues that compact foundation models can exceed memory-limited performance by combining deliberate internal reasoning with active external tool use, and demonstrates this at 7B scale with extreme long-context and training efficiency. The surprising claim is empirical: a carefully designed small dense model can rival much larger models on math and agentic search benchmarks when paired with long contexts and tool interaction.

Key Findings
  • Architecture & efficiency: interleaved gated sliding-window local attention with a small number of global attention layers reduces KV-cache and raises throughput for 256K contexts (reported ~3.9× throughput gain vs full attention at 256K).
  • Training recipe: hybrid FP8 precision with a Muon optimizer and a progressive context curriculum (pretrain → midtrain 16K→64K→256K) yields an estimated ~4.2× improvement in 16K pretraining time-to-loss.
  • Capabilities: strong performance on math and agentic-search tasks (examples reported: MATH-500 97.13%, AIME 2026 75.00%, WebWalkerQA ~63%). The model supports both internal “thinking” and direct-response modes and is trained with execution-verified trajectories for agentic behavior.
  • Reproducibility: authors open-source weights, intermediate checkpoints, per-stage data recipes, training code, and W&B logs to enable community follow-up.
Who it's for and tradeoffs

Great fit if you are a researcher or practitioner who needs an open, long-context LLM optimized for reasoning and tool-assisted search and who values reproducible training artifacts. The release is valuable for people evaluating architectural long-context tradeoffs, hybrid-precision training, and agentic co-training dynamics. Look elsewhere if you need a multimodal foundation model, extremely large-capacity models (>100B) for purely memorization-heavy tasks, or turnkey hosted inference APIs — this work focuses on training recipes, model design, and datasets rather than managed serving.

Method and practical notes

The development lifecycle combines ~4.19T tokens of pretraining, a mid-training phase of ~600B tokens with explicit context scaling, and supervised fine-tuning that mixes thinking/direct-response examples and execution-verified tool trajectories. The model is a 7.39B decoder-only dense Transformer (32 layers, 4,096 hidden) with 27 gated sliding-window layers and 5 global layers and a 262,144-token context length target. The paper also distills practical empirical findings about SFT quality pruning, long-context generalization, and agentic co-training dynamics that can guide follow-up experiments.

Information

  • Websitearxiv.org
  • AuthorsJiyan He, Guang Liang, Hao Liu, Haoxiang Guan, Jinbo Sun, Junyi Guo, Wenjun Feng, Yantai Xie, Yifei Shen, Bin Shao
  • Published date2026/09/11

More Items

Presents Atria Dawn Preview, an agentic foundation LLM trained with a Verifiable Experience Pipeline to connect tool-mediated interactions to executable environments; evaluated across 16 real-world research and engineering benchmarks with top scores on five, and a human–AI collaboration analysis of 769 task records.

Progressively prunes and distills audio encoders for speech LLMs to cut inference cost while preserving decoder-facing embeddings, using behavioral probes, representation alignment, cross-scale distillation and LoRA finetuning; reports reduced macro-error on Chinese–English benchmarks.

Adds a Next Concept Prediction objective that predicts discrete, product-quantized latent concepts spanning multiple tokens alongside next-token prediction, yielding faster pretraining convergence and measurable downstream gains with an 8.9B-parameter latent-space LLM.