Apodex 1.1 Agent Team hits 63.3% pass rate on FrontierScience-Research, paper lands on Papers with Code
NielsRogge · x · 2026-09-08
The Apodex team announced that the Apodex 1.1 paper (arXiv:2608.23283) and its Agent Team results have been indexed on Papers with Code by Niels Rogge. On FrontierScience-Research, Apodex 1.1 (Agent Team) achieved a 63.3% pass rate across 60 tasks, with results also reported on HLE and GDPval.
The paper targets "sustained, verifiable progress toward real-world objectives" along two axes:
- Environment Scaling: expanding diverse, verifiable executable file, search, and code environments.
- Agentic Coordination Scaling: training agents to decompose long-horizon tasks, delegate parallel work, integrate asynchronous results, and replan.
A shared execution harness and an AgentOS maintain task state and provenance across tools and agents, with training converting environment trajectories and coordination traces into reliable behavior.
More from coding & agent
- Founder builds Command & Conquer-style RTS dashboard to monitor AI agent sessions — davidhoang · 2026-09-08
- Warp CEO: we shipped an AI coding feature 6 months before Claude Code — holding back is my biggest regret — vikvang1 · 2026-09-08
- Utilify MCP lets AI agents compare and sign up for Texas utility plans by ZIP code — modelcontextprotocol · 2026-09-08
- Building a Kinesin ATP animation with Blender and Unreal MCPs — Mister-Fordo · 2026-09-08
- A developer proposes an informal agent-native mathlib, tentatively named mathgraph — Sauers_ · 2026-09-08
- Ix builds a persistent symbol graph of your codebase across 26 languages for humans and AI — tom_doerr · 2026-09-08