Apodex zaprezentował rodzinę modeli 1.1 zintegrowaną z runtime'em FrontierAgent, umożliwiającą tworzenie asynchronicznych zespołów agentów do realizacji długofalowych zadań na danych i kodzie.

Apodex 1.1 shifts from answering questions to completing analytical work across files, with code execution, traceable outputs, mid-task recovery, and multi-agent coordination, posting large benchmark gains over 1.0.

Apodex 1.1 moves from deep research into file and code execution and more than doubles 1.0 on three agent benchmarks.

Apodex has released Apodex 1.1, a model family built to complete work instead of describing it. The previous generation read web pages and returned a written answer. This one opens the files themselves- a spreadsheet, a PDF, a dataset- picks a method, writes and runs the analysis code, and hands back the tables, charts, and scripts it produced, with figures traceable to source. It went live on August 24. 0:00 /0:27 1× The problem it targets is the cost of a long task that collapses partway through. An agent that meets a missing value or a failed assumption at step forty either stops or returns something vague, and the hours spent getting there get spent again. Apodex calls its answer Adaptive Recovery, where the system explains the adjustment it is making and continues. Two training directions sit behind it. Environment Scaling widens the file, search, and code environments the model learns inside, and Agentic Coordination Scaling teaches it to break a task apart. Both execute on a runtime called AgentOS, which holds tool calls, file state, and progress for a whole job. Apodex 1.1 mini benchmarks The headline capability is Deep Discover, a mode where the model assembles what Apodex calls an Agent Team without being told how, deciding whether a task splits, how many subagents run, and when they consolidate. The team is asynchronous, so each branch reports to a shared task state as it finishes rather than at the end, and the main task absorbs findings in real time while a live task board carries plans, steps, and exceptions. Adding a file or changing a requirement mid-run keeps the intermediate results that still hold and replans only the affected parts. A step called Statement Review then checks the conclusions against their sources, data, and computations, and flags what conflicts. On benchmarks Apodex published and ran through its own harness, the Agent Team configuration scores 38.5 on APEX-Agents (1.0 scored 16.5) and 63.3 on FrontierScience-Research (28.3). In one inquiry run on the web product, a single Deep Discover task ran 395 steps across 28 sources and returned a 31 KB report, with the reviewer checking 51 claims before delivery. The flagship is a 397B model with a 260K context window, and a 35B open-weight sibling, Apodex 1.1 mini, carries the same coordination layer. Both are free to call on the Apodex API platform for now, at list prices of $0.30 and $0.10 per million input tokens. Deep Discover sits behind a preview program called Apodex Frontier, while the Deep Research and Deep Solve tiers are open to everyone. SPONSORED Test out Deep Discover on Apodex Learn more Apodex shipped 1.0 in June alongside AgentHarness, an evaluation harness limited to single-agent loops. FrontierAgent, released with 1.1 under Apache 2.0, replaces it with a runtime and terminal interface that covers both modes, starting with one command on macOS and Linux. Apodex also maintains TRACES, a benchmark for discovery-oriented AI, and says pretraining for Apodex 2.0 is underway, built for what it calls a Heavy-Duty Solver. Star FrontierAgent on GitHub, check the open weights on Hugging Face, or test the API platform.

今回の「生成AIウィークリー」（第158回）は、最初から最後まで実務プロセスを行う研究支援AI「Apodex 1.1」や、次世代モデル「Qwen4」を先行搭載したオープンウェイトAI「Qwen3.8-Flash-Next」を取り上げます。

今回の「生成AIウィークリー」（第158回）は、最初から最後まで実務プロセスを行う研究支援AI「Apodex 1.1」や、次世代モデル「Qwen4」を先行搭載したオープンウェイトAI「Qwen3.8-Flash-Next」を取り上げます。

FrontierAgent 소개 여러 시간에 걸친 조사 작업을 에이전트에게 맡기려면 대화형 챗봇과는 다른 것들이 필요합니다. 파일을 읽고 쓰는 권한을 어디까지 줄지, 중간에 사람이 끼어들면 진행 중인 작업을 버려야 하는지, 실행이 끊겼을 때 어디서부터 다시 시작할지, 결과물이 어느 디렉토리에 남는지를 정해 두지 않으면 오래 걸리는 작업일수록 손댈 수 없게 됩니다. 조사 범위가 넓어 여러 갈래를 동시에 파야 할 때는 하나의 에이전트를 더 길게 실행하는 것과 여러 에이전트에게 나눠 맡기는 것 사이에서 선택도 해야 합니다. FrontierAgent는 Apodex가 2026년 8월에 공개한 오픈소스 에이전트 런타임(runtime)이자 터미널 프로그램이고, 평가 도구까지 함께 들어 있습니다. 이 회사는 딥리서치(deep research) 모델 Apodex 시리즈를 만들고 상용 API로 제공하는 곳이며,...

今回の「生成AIウィークリー」（第158回）は、最初から最後まで実務プロセスを行う研究支援AI「Apodex 1.1」や、次世代モデル「Qwen4」を先行搭載したオープンウェイトAI「Qwen3.8-Flash-Next」を取り上げます。

今回の「生成AIウィークリー」（第158回）は、最初から最後まで実務プロセスを行う研究支援AI「Apodex 1.1」や、次世代モデル「Qwen4」を先行搭載したオープンウェイトAI「Qwen3.8-Flash-Next」を取り上げます。

YouTube video by TheAIGRID

Apodex 1.1 introduces a cutting-edge AI reasoning model that ensures complex tasks can be executed in a verifiable manner, enhancing research productivity.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

The Apodex Team developed Apodex 1.1, an agentic system that improves the ability of large language models to complete complex, verifiable work by scaling both interactive environments and...

Join the discussion on this paper page

General-purpose language models can reason and synthesize knowledge, but complex work also requires sustained interaction with files, information sources, and executable code, together with state main...

The Apodex Team developed Apodex 1.1, an agentic system that improves the ability of large language models to complete complex, verifiable work by scaling both interactive environments and...

Join the discussion on this paper page

General-purpose language models can reason and synthesize knowledge, but complex work also requires sustained interaction with files, information sources, and executable code, together with state main...

The Apodex Team developed Apodex 1.1, an agentic system that improves the ability of large language models to complete complex, verifiable work by scaling both interactive environments and...