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

• URL: http://arxiv.org/abs/2609.13356v1
• Date: Fri, 11 Sep 2026 17:18:04 GMT
• Title: ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search
• Abstract summary: ZGCM-1 is a fully open 7B foundation model trained from scratch with extreme data, system, and algorithmic efficiency.<n>We establish an AI-native R&D workflow where agent swarms autonomously manage cluster operations.<n>ZGCM-1-7B is competitive across 7B model family on general benchmarks.
• Score: 54.43696074323815
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this work, we present ZGCM-1, a fully open 7B dense foundation model trained from scratch with extreme data, system, and algorithmic efficiency. ZGCM-1 is founded on a core premise: compact models cannot passively memorize the open web, but can overcome parametric capacity limits by coupling deliberate internal thinking with active external tool use. To support this paradigm across a 256K context, we develop an end-to-end, high-efficiency open training recipe: Architecture & System Co-design: interleaved gated sliding-window and full attention, and a stable FP8 Muon optimizer; Progressive Curriculum & MDP Mid-Training: context scaling across 16K, 64K, and 256K, and the reformulation of interaction traces into Markov Decision Processes. Furthermore, we establish an AI-native R&D workflow where agent swarms autonomously manage cluster operations, data curation, and rapid diagnostic evaluation. Extensive evaluations show that ZGCM-1-7B is competitive across 7B model family on general benchmarks. On several challenging mathematical reasoning and agentic search suites, it remains competitive with frontier models orders of magnitude larger, such as Qwen3-235B-A22B and GLM-5.1. We also show that our pre-training design offers a ~4.2x efficiency improvement in 16K pre-training time-to-loss. Across the full development lifecycle, we distill eight actionable empirical findings-spanning architectural scaling, SFT quality pruning, long-context generalization, and agentic co-training dynamics. To facilitate community research, we open-source model weights from the pre-training, mid-training, and post-training stages, intermediate checkpoints, training code, per-stage data and data recipes, and W&B logs.

Related papers

• Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models [63.96252564303143]
  Embodied-R1.5 is a unified Embodied Foundation Model (EFM) that integrates comprehensive embodied reasoning capabilities.<n>We build a large-scale data system of over 15B tokens, and design a multi-task balanced RL recipe.<n>With only 8B parameters, Embodied-R1.5 SOTA on 16 out of 24 embodied VLM benchmarks, surpassing leading models like Gemini-Robotics-ER-1.5 and GPT-5.4.
  arXiv  Detail & Related papers  (2026-06-09T18:07:50Z)
• CoVe: Training Interactive Tool-Use Agents via Constraint-Guided Verification [17.56502992098113]
  We introduce textbfCoVe (textbfConstraint-textbfVerification), a post-training data synthesis framework designed for training interactive tool-use agents.<n>CoVe begins by defining explicit task constraints, which serve a dual role: they guide the generation of complex trajectories and act as deterministic verifiers for assessing trajectory quality.
  arXiv  Detail & Related papers  (2026-03-02T14:56:35Z)
• daVinci-Dev: Agent-native Mid-training for Software Engineering [22.845876048950483]
  We present a systematic study of agentic mid-training, establishing the data synthesis principles and training methodology for effective agent development at scale.<n>We demonstrate our superiority over the previous open software engineering mid-training recipe Kimi-Dev under two post-training settings with an aligned base model and agentic scaffold.
  arXiv  Detail & Related papers  (2026-01-26T12:20:18Z)
• Parameter-Efficient Domain Adaption for CSI Crowd-Counting via Self-Supervised Learning with Adapter Modules [11.651086215885735]
  Device-free crowd-counting using WiFi Channel State Information (CSI) is a key enabling technology for a new generation of privacy-preserving Internet of Things (IoT) applications.<n>We propose a novel two-stage framework centred on a CSI-ResNet-A architecture.<n>This model is pre-trained via self-supervised contrastive learning to learn domain-invariant representations and leverages lightweight Adapter modules for highly efficient fine-tuning.<n>Our framework sets a new state-of-the-art public WiAR benchmark with 98.8% accuracy.
  arXiv  Detail & Related papers  (2026-01-05T15:27:04Z)
• LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering [90.84806758077536]
  We introduce textbfLoCoBench-Agent, a comprehensive evaluation framework specifically designed to assess large language models (LLMs) agents in realistic, long-context software engineering.<n>Our framework extends LoCoBench's 8,000 scenarios into interactive agent environments, enabling systematic evaluation of multi-turn conversations.<n>Our framework provides agents with 8 specialized tools (file operations, search, code analysis) and evaluates them across context lengths ranging from 10K to 1M tokens.
  arXiv  Detail & Related papers  (2025-11-17T23:57:24Z)
• Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models [49.911784762244814]
  TraceRL is a trajectory-aware reinforcement learning framework for diffusion language models (DLMs)<n>We derive a series of state-of-the-art diffusion language models, namely TraDo.<n>TraDo-8B-Instruct achieves relative accuracy improvements of 6.1% over Qwen2.5-7B-Instruct and 51.3% over Llama3.1-8B-Instruct on mathematical reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-09-08T17:58:06Z)
• InternBootcamp Technical Report: Boosting LLM Reasoning with Verifiable Task Scaling [71.37579508777843]
  Large language models (LLMs) have revolutionized artificial intelligence by enabling complex reasoning capabilities.<n>To address this gap, we present InternBootcamp, an open-source framework comprising 1000+ domain-diverse task environments.
  arXiv  Detail & Related papers  (2025-08-12T05:00:00Z)
• Building Math Agents with Multi-Turn Iterative Preference Learning [56.71330214021884]
  This paper studies the complementary direct preference learning approach to further improve model performance.<n>Existing direct preference learning algorithms are originally designed for the single-turn chat task.<n>We introduce a multi-turn direct preference learning framework, tailored for this context.
  arXiv  Detail & Related papers  (2024-09-04T02:41:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.