# APEX-Agents

arXiv: https://arxiv.org/abs/2601.14242 · HTML: https://mlsanity.com/paper/2601.14242/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 5 of its 6 references that are in the map.
- First posted on arXiv 20 Jan 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 5 of 5)

- [AI Agents That Matter](https://mlsanity.com/paper/2407.01502/) (2024)
- [The BrowserGym Ecosystem for Web Agent Research](https://mlsanity.com/paper/2412.05467/) (2024)
- [ARE: Scaling Up Agent Environments and Evaluations](https://mlsanity.com/paper/2509.17158/) (2025)
- [The Measurement Imbalance in Agentic AI Evaluation Undermines Industry Productivity Claims](https://mlsanity.com/paper/2506.02064/) (2025)
- [The AI Productivity Index (APEX)](https://mlsanity.com/paper/2509.25721/) (2025)

## Built on by (most cited first, 30 of 32)

- [Kimi K3: Open Frontier Intelligence](https://mlsanity.com/paper/2607.24653/) (2026)
- [OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks](https://mlsanity.com/paper/2606.29537/) (2026)
- [Stop Comparing LLM Agents Without Disclosing the Harness](https://mlsanity.com/paper/2605.23950/) (2026)
- [Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading](https://mlsanity.com/paper/2607.08964/) (2026)
- [RRSI: Regularized Recursive Self-Improvement of Agent Harnesses](https://mlsanity.com/paper/2609.24972/) (2026)
- [Evo-Bench: Can Language Models Improve Agent Harness?](https://mlsanity.com/paper/2608.09096/) (2026)
- [π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows](https://mlsanity.com/paper/2605.14678/) (2026)
- [One Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business Workflows](https://mlsanity.com/paper/2608.19741/) (2026)
- [Locating Hidden Failures Makes Long-Horizon Agents More Reliable](https://mlsanity.com/paper/2609.17930/) (2026)
- [OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding](https://mlsanity.com/paper/2607.27155/) (2026)
- [Apodex 1.1: Scaling Agentic Intelligence for Complex Work](https://mlsanity.com/paper/2608.23283/) (2026)
- [Cost-Utility Alignment in LLM Agent Trajectories:Profiling,Attribution,Diagnosis,Adaptation,and Evaluation](https://mlsanity.com/paper/2608.26195/) (2026)
- [Is Bash All You Need? An Empirical Study of Tool Interfaces for Enterprise Digital Worker Agents](https://mlsanity.com/paper/2609.11999/) (2026)
- [COMPOSITE-Stem](https://mlsanity.com/paper/2604.09836/) (2026)
- [Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents](https://mlsanity.com/paper/2605.21347/) (2026)
- [CollabSkill: Evaluating Human-Agent Collaboration On Real-World Tasks](https://mlsanity.com/paper/2606.09833/) (2026)
- [DuMateBench: Evaluating Autonomous Agents in Complex Real-World Workflows](https://mlsanity.com/paper/2608.26546/) (2026)
- [AsymmetryZero: A Framework for Operationalizing Human Expert Preferences as Semantic Evals](https://mlsanity.com/paper/2605.04083/) (2026)
- [Relay-Bench: Evaluating LLMs on Multi-Domain Reasoning Chains](https://mlsanity.com/paper/2607.18438/) (2026)
- [SQBench: A Benchmark for Evaluating Task Delivery by Language-Model Agents in Production-Oriented Workflows](https://mlsanity.com/paper/2607.23123/) (2026)
- [The Reasoning Tax: Token Economics of LLM Reasoning Across Task Types and Deployment Contexts](https://mlsanity.com/paper/2608.26235/) (2026)
- [Efficient Test-Time Adaptation through Human-AI Interaction](https://mlsanity.com/paper/2609.04141/) (2026)
- [xDailyBench: Benchmarking LLMs on Professional Consultation for Real-Life Problems](https://mlsanity.com/paper/2609.07784/) (2026)
- [Studying Without a Syllabus: Task-Agnostic Environment Preprocessing](https://mlsanity.com/paper/2609.10824/) (2026)
- [Beyond Outcomes: Dual-View Relational Learning for Efficient Agent Benchmarking](https://mlsanity.com/paper/2609.18909/) (2026)
- [After the Fix: Transfer of Corrected Agent Experience](https://mlsanity.com/paper/2609.34603/) (2026)
- [APEX-Voice: Can Voice Agents Complete Professional Workflows Through Full-Duplex Interaction](https://mlsanity.com/paper/2609.34973/) (2026)
- [Long-Horizon Scaling: How Model Capabilities Shape the Returns to Computation](https://mlsanity.com/paper/2609.35236/) (2026)
- [FinAutoRubric: Expert-Guided Automatic Rubric Generation for Evaluating Financial Research Agents](https://mlsanity.com/paper/2609.35744/) (2026)
- [WorkGenesis: Building the Worlds That Teach Agents to Work](https://mlsanity.com/paper/2609.39325/) (2026)

## Abstract (arXiv)

We introduce the AI Productivity Index for Agents (APEX-Agents), a benchmark for assessing whether AI agents can execute long-horizon, cross-application tasks created by investment banking analysts, management consultants, and corporate lawyers. APEX-Agents requires agents to navigate realistic work environments with files and tools. We test eight agents for the leaderboard using Pass@1. Gemini 3 Flash (Thinking=High) achieves the highest score of 24.0%, followed by GPT-5.2 (Thinking=High), Claude Opus 4.5 (Thinking=High), and Gemini 3 Pro (Thinking=High). We open source the APEX-Agents benchmark (n=480) with all prompts, rubrics, gold outputs, files, and metadata. We also open source Archipelago, our infrastructure for agent execution and evaluation.