Apodex 1.1: Scaling Agentic Intelligence for Complex Work

ArticleB. An et al.Research

Researchers introduce Apodex 1.1, an agentic system designed for sustained, verifiable progress on complex tasks across coding, science, and finance. It pairs environment scaling with multi-agent coordination, achieving top-tier performance while keeping model sizes comparatively compact.

Key points

  1. Emphasis on 'working capability': Sustained and verifiable progress toward real-world goals rather than standalone text generation.
  2. Two core scaling dimensions: Environment Scaling (broad, verifiable file, search, and code environments) and Agentic Coordination Scaling (task decomposition, delegation, and replanning).
  3. Shared execution harness and AgentOS to maintain task state and provenance across diverse agents and tools.
  4. Apodex 1.1 Mini offers a 35B-parameter locally deployable model that retains core working capabilities.

Why it matters

Autonomous agents often fail on long-horizon objectives due to state drift and poor error recovery. Apodex demonstrates that structured orchestration, execution provenance, and verifiable environment feedback can deliver frontier-level results with smaller model architectures.

Analysis

The authors tackle the gap between synthetic reasoning benchmarks and real-world execution. Rather than simply scaling raw parameter counts, the architecture focuses on AgentOS-managed coordination and learning from multi-agent trajectory traces. The availability of a 35B Mini version makes these long-horizon agent capabilities feasible for on-premises and private deployments.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Link:Apodex AI

    Apodex-1.1-mini: Multimodal Agentic Model Released on Hugging Face

    Apodex AI has released Apodex-1.1-mini under the Apache-2.0 licence on Hugging Face. Based on the qwen3_5_moe architecture, the model is designed for long-horizon research and agentic workflows with native tool execution.

    AI & LLMs· Tool

  • Link:apodex.ai

    Apodex: Reasoning Engine for Verified Briefs

    Apodex presents itself as a step-by-step reasoning solver designed to verify each conclusion before progressing, delivering structured briefs rather than simple chat replies.

    AI & LLMs· Tool

  • Link:Abacus.AI

    Abacus.AI AutoBots: Self-Improving Autonomous Agents

    Abacus.AI has launched AutoBots, a platform offering recursively self-improving autonomous agents designed to handle end-to-end workflows. Configured via text prompts, the agents run continuously without human intervention and refine their strategies across successive executions.

    AI & LLMs· Tool

  • Article:Liyan Tang, Cyrus Rashtchian, Chun-Sung Ferng, Andrew Tomkins, Da-Cheng Juan, Tu Vu

    WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution

    This research paper introduces WikiSkill, a framework that co-evolves AI agent skills alongside a persistent knowledge base (wiki). By disentangling raw execution experience, accumulated knowledge, and executable skills, WikiSkill enables systematic reuse of insights across iterations.

    AI & LLMs· Research

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.