# AgentCE-Bench: Agent Configurable Evaluation with Scalable Horizons and Controllable Difficulty under Lightweight Environments

arXiv: https://arxiv.org/abs/2604.06111 · HTML: https://mlsanity.com/paper/2604.06111/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 37 references that are in the map.
- First posted on arXiv 7 Apr 2026.

## Builds on (most cited first, 30 of 33)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [GLM-5: from Vibe Coding to Agentic Engineering](https://mlsanity.com/paper/2602.15763/) (2026)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks](https://mlsanity.com/paper/2412.15204/) (2024)
- [∞Bench: Extending Long Context Evaluation Beyond 100K Tokens](https://mlsanity.com/paper/2402.13718/) (2024)
- [WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?](https://mlsanity.com/paper/2403.07718/) (2024)
- [ScienceWorld: Is your Agent Smarter than a 5th Grader?](https://mlsanity.com/paper/2203.07540/) (2022)
- [MathArena: Evaluating LLMs on Uncontaminated Math Competitions](https://mlsanity.com/paper/2505.23281/) (2025)
- [SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?](https://mlsanity.com/paper/2509.16941/) (2025)
- [MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention](https://mlsanity.com/paper/2506.13585/) (2025)
- [L-Eval: Instituting Standardized Evaluation for Long Context Language Models](https://mlsanity.com/paper/2307.11088/) (2023)
- [The Landscape of Agentic Reinforcement Learning for LLMs: A Survey](https://mlsanity.com/paper/2509.02547/) (2025)
- [Survey on Evaluation of LLM-based Agents](https://mlsanity.com/paper/2503.16416/) (2025)
- [LAB-Bench: Measuring Capabilities of Language Models for Biology Research](https://mlsanity.com/paper/2407.10362/) (2024)
- [HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly](https://mlsanity.com/paper/2410.02694/) (2024)
- [MLGym: A New Framework and Benchmark for Advancing AI Research Agents](https://mlsanity.com/paper/2502.14499/) (2025)
- [DISCOVERYWORLD: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents](https://mlsanity.com/paper/2406.06769/) (2024)
- [SWE-Bench+: Enhanced Coding Benchmark for LLMs](https://mlsanity.com/paper/2410.06992/) (2024)
- [WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks](https://mlsanity.com/paper/2407.05291/) (2024)
- [LV-Eval: A Balanced Long-Context Benchmark with 5 Length Levels Up to 256K](https://mlsanity.com/paper/2402.05136/) (2024)
- [MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling](https://mlsanity.com/paper/2511.11793/) (2025)
- [Generative to Agentic AI: Survey, Conceptualization, and Challenges](https://mlsanity.com/paper/2504.18875/) (2025)
- [IntellAgent: A Multi-Agent Framework for Evaluating Conversational AI Systems](https://mlsanity.com/paper/2501.11067/) (2025)
- [Beyond Prompts: Dynamic Conversational Benchmarking of Large Language Models](https://mlsanity.com/paper/2409.20222/) (2024)

## Built on by (most cited first, 3 of 3)

- [AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security](https://mlsanity.com/paper/2605.29801/) (2026)
- [Path-Lock Expert: Separating Reasoning Mode in Hybrid Thinking via Architecture-Level Separation](https://mlsanity.com/paper/2604.27201/) (2026)
- [Agent Team Work Zone: An Automated, Persistent Workspace for Long-Lived Claude Code Agent Teams](https://mlsanity.com/paper/2607.22917/) (2026)

## Abstract (arXiv)

Existing Agent benchmarks suffer from two critical limitations: high environment interaction overhead (up to 41% of total evaluation time) and imbalanced task horizon and difficulty distributions that make aggregate scores unreliable. To address these issues, we propose AgentCE-Bench built around a unified grid-based planning task, where agents must fill hidden slots in a partially completed schedule subject to both local slot constraints and global constraints. Our benchmark offers fine-grained control through two orthogonal axes: Scalable Horizons, controlled by the number of hidden slots H, and Controllable Difficulty, governed by a decoy budget B that determines the number of globally misleading decoy candidates. Crucially, all tool calls are resolved via static JSON files under a Lightweight Environment design, eliminating setup overhead and enabling fast, reproducible evaluation suitable for training-time validation. We first validate that H and B provide reliable control over task horizon and difficulty, and that AgentCE-Bench exhibits strong domain consistency and model discriminability. We then conduct comprehensive experiments across 13 models of diverse sizes and families over 6 domains, revealing significant cross-model performance variation and confirming that AgentCE-Bench provides interpretable and controllable evaluation of agent reasoning.