# InnovatorBench: Evaluating Agents' Ability to Conduct Innovative LLM Research

arXiv: https://arxiv.org/abs/2510.27598 · HTML: https://mlsanity.com/paper/2510.27598/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 40 of its 52 references that are in the map.
- First posted on arXiv 31 Oct 2025.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 30 of 40)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [Kimi K2: Open Agentic Intelligence](https://mlsanity.com/paper/2507.20534/) (2025)
- [LIMO: Less is More for Reasoning](https://mlsanity.com/paper/2502.03387/) (2025)
- [MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering](https://mlsanity.com/paper/2410.07095/) (2024)
- [GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models](https://mlsanity.com/paper/2508.06471/) (2025)
- [PaperBench: Evaluating AI's Ability to Replicate AI Research](https://mlsanity.com/paper/2504.01848/) (2025)
- [DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments](https://mlsanity.com/paper/2504.03160/) (2025)
- [SWE-smith: Scaling Data for Software Engineering Agents](https://mlsanity.com/paper/2504.21798/) (2025)
- [GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents](https://mlsanity.com/paper/2504.10458/) (2025)
- [ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery](https://mlsanity.com/paper/2410.05080/) (2024)
- [RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts](https://mlsanity.com/paper/2411.15114/) (2024)
- [MLGym: A New Framework and Benchmark for Advancing AI Research Agents](https://mlsanity.com/paper/2502.14499/) (2025)
- [SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines](https://mlsanity.com/paper/2502.14739/) (2025)
- [ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code](https://mlsanity.com/paper/2311.09835/) (2023)
- [AgentRefine: Enhancing Agent Generalization through Refinement Tuning](https://mlsanity.com/paper/2501.01702/) (2025)
- [InternAgent: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification](https://mlsanity.com/paper/2505.16938/) (2025)
- [Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale](https://mlsanity.com/paper/2409.17115/) (2024)
- [EXP-Bench: Can AI Conduct AI Research Experiments?](https://mlsanity.com/paper/2505.24785/) (2025)
- [ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code](https://mlsanity.com/paper/2506.02314/) (2025)
- [ResearcherBench: Evaluating Deep AI Research Systems on the Frontiers of Scientific Inquiry](https://mlsanity.com/paper/2507.16280/) (2025)
- [Coding Agents with Multimodal Browsing are Generalist Problem Solvers](https://mlsanity.com/paper/2506.03011/) (2025)

## Built on by (most cited first, 19 of 19)

- [AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts](https://mlsanity.com/paper/2601.11044/) (2026)
- [ResearchGym: Evaluating Language Model Agents on Real-World AI Research](https://mlsanity.com/paper/2602.15112/) (2026)
- [daVinci-Dev: Agent-native Mid-training for Software Engineering](https://mlsanity.com/paper/2601.18418/) (2026)
- [SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation](https://mlsanity.com/paper/2605.07711/) (2026)
- [SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones?](https://mlsanity.com/paper/2605.30329/) (2026)
- [AI Can Learn Scientific Taste](https://mlsanity.com/paper/2603.14473/) (2026)
- [Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap](https://mlsanity.com/paper/2608.05179/) (2026)
- [InnoGym: Benchmarking the Innovation Potential of AI Agents](https://mlsanity.com/paper/2512.01822/) (2025)
- [daVinci-Agency: Unlocking Long-Horizon Agency Data-Efficiently](https://mlsanity.com/paper/2602.02619/) (2026)
- [Aligned Agents, Biased Swarm: Measuring Bias Amplification in Multi-Agent Systems](https://mlsanity.com/paper/2604.08963/) (2026)
- [Can LLM Agents Discover? Evaluating Creativity on ML Engineering Tasks](https://mlsanity.com/paper/2608.30047/) (2026)
- [Universe of Thoughts: Enabling Creative Reasoning with Large Language Models](https://mlsanity.com/paper/2511.20471/) (2025)
- [The Cost of Knowing: A Resource-Aware Protocol for Benchmarking Hallucination Beyond Static Leaderboards](https://mlsanity.com/paper/2607.24063/) (2026)
- [LU-500: A Logo Benchmark for Concept Unlearning](https://mlsanity.com/paper/2607.24101/) (2026)
- [Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation](https://mlsanity.com/paper/2609.11115/) (2026)
- [WhatWorkedBench: Benchmarking Experimental Understanding in AI Agents](https://mlsanity.com/paper/2609.27490/) (2026)
- [RECLAIM: Can Agents Reproduce the Claims of Machine Learning Papers?](https://mlsanity.com/paper/2609.28850/) (2026)
- [AutoDataBench: Can Agents Write the Data That Feeds the Self-Improvement Loop?](https://mlsanity.com/paper/2609.35025/) (2026)
- [Discovered, Not Designed: Population Evolution for Collaborative and Compute-Intensive Model Discovery](https://mlsanity.com/paper/2610.05950/) (2026)

## Abstract (arXiv)

AI agents could accelerate scientific discovery by automating hypothesis formation, experiment design, coding, execution, and analysis, yet existing benchmarks probe narrow skills in simplified settings. To address this gap, we introduce InnovatorBench, a benchmark-platform pair for realistic, end-to-end assessment of agents performing Large Language Model (LLM) research. It comprises 20 tasks spanning Data Construction, Filtering, Augmentation, Loss Design, Reward Design, and Scaffold Construction, which require runnable artifacts and assessment of correctness, performance, output quality, and uncertainty. To support agent operation, we develop ResearchGym, a research environment offering rich action spaces, distributed and long-horizon execution, asynchronous monitoring, and snapshot saving. We also implement a lightweight ReAct agent that couples explicit reasoning with executable planning using frontier models such as Claude-4, GPT-5, GLM-4.5, and Kimi-K2. Our experiments demonstrate that while frontier models show promise in code-driven research tasks, they struggle with fragile algorithm-related tasks and long-horizon decision making, such as impatience, poor resource management, and overreliance on template-based reasoning. Furthermore, agents require over 11 hours to achieve their best performance on InnovatorBench, underscoring the benchmark's difficulty and showing the potential of InnovatorBench to be the next generation of code-based research benchmark.