The Meta-Agent Challenge shows frontier AI models rarely match human-engineered agent baselines when tasked with autonomous development, with proprietary models succeeding most often and some exhibiting cheating under pressure.
hub Mixed citations
MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering
Mixed citation behavior. Most common role is background (67%).
75
Pith papers citing it
Background
67% of classified citations
abstract
We introduce MLE-bench, a benchmark for measuring how well AI agents perform at machine learning engineering. To this end, we curate 75 ML engineering-related competitions from Kaggle, creating a diverse set of challenging tasks that test real-world ML engineering skills such as training models, preparing datasets, and running experiments. We establish human baselines for each competition using Kaggle's publicly available leaderboards. We use open-source agent scaffolds to evaluate several frontier language models on our benchmark, finding that the best-performing setup--OpenAI's o1-preview with AIDE scaffolding--achieves at least the level of a Kaggle bronze medal in 16.9% of competitions. In addition to our main results, we investigate various forms of resource scaling for AI agents and the impact of contamination from pre-training. We open-source our benchmark code (github.com/openai/mle-bench/) to facilitate future research in understanding the ML engineering capabilities of AI agents.
hub tools
citation-role summary
background 10
dataset 4
other 1
citation-polarity summary
representative citing papers
Glite ARF introduces a verifier-driven three-role framework for parallel LLM coding agents, demonstrated by first- and second-place finishes in the BEA 2026 vocabulary-difficulty shared task across three languages with 29.9-35.9% RMSE reduction at ~$450 API cost.
Introduces the Power Systems Agent Benchmark with 41 task families across eight power engineering areas for executable evaluation of AI agents using deterministic feasibility checks.
An LLM-driven agent with built-in seed-noise audits develops control policies for two aerospace problems that outperform undirected search and pass verification checks.
AgentBeats implements agentified evaluation of diverse AI agents through standardized interfaces, validated at scale in a five-month competition with 298 judges and 467 subjects plus a coding case study.
Data2Story is a multi-agent framework that generates evidence-grounded multimodal articles from data, evaluated on 18 articles against human pieces for verifiability, angle coverage, and quality across human, rubric, and automated judges.
AutoMedBench evaluates AI agents on long-horizon medical workflows across five stages and finds validation and submission as dominant failure points based on thousands of runs.
IdleSpec improves LLM agent accuracy by generating and aggregating speculative plans during idle time between tool calls and observations using complementary drafting strategies.
Evolutionary coding agents achieve most benchmark gains through a small subset of edit types and by cycling previously deleted code lines rather than developing new algorithmic structures.
DecisionBench supplies a fixed task suite, model pool, delegation interface, and multi-axis metrics to evaluate emergent delegation, showing similar quality across awareness conditions but 15-31 point headroom under perfect delegation.
WebGameBench is a new benchmark that evaluates coding agents on building browser-native games from frozen specifications, with runtime browser evaluation showing best agents reach 76.9% usable rate but only 20.2% excellent rate.
FML-Bench shows a simple greedy hill-climber nearly matches tree search on dense-opportunity tasks while an adaptive agent that broadens search on stagnation outperforms six baselines across 18 tasks.
BioXArena benchmarks LLM agents on generating end-to-end ML pipelines for 76 multi-modal biomedical tasks, with MLEvolve plus Gemini-3.1-Pro scoring highest at 0.666.
SMCEvolve applies Sequential Monte Carlo sampling to LLM program search with adaptive resampling, mutation mixtures, and convergence control, delivering finite-sample complexity bounds and benchmark gains over prior systems.
GoR extracts citation DAGs using position, frequency, predecessor links and time, then fine-tunes Qwen2.5-7B on 498 seed papers to generate ideas, claiming SOTA over gpt-4o baselines via LLM judges.
FrontierSmith automates synthesis of open-ended coding problems from closed-ended seeds and shows measurable gains on two open-ended LLM coding benchmarks.
Collider-Bench is a new benchmark showing that current LLM agents cannot reliably reproduce LHC analyses at the level of a physicist-in-the-loop.
BenchJack audits 10 AI agent benchmarks, synthesizes exploits achieving near-perfect scores without task completion, surfaces 219 flaws, and reduces hackable-task ratios to under 10% on four benchmarks via iterative patching.
KompeteAI accelerates AutoML pipeline evaluation 6.9 times and beats prior systems by 3% on MLE-Bench through candidate merging, external RAG, and predictive early scoring.
Frontier models demonstrate in-context scheming by strategically deceiving in multiple agentic evaluations to achieve given goals.
SkillSafetyBench is a benchmark of 155 cases across 47 tasks and 6 risk domains showing that non-user attacks via skills, artifacts, or environments can consistently induce unsafe agent behavior.
Enforcing role separation in agent teams reveals that prompt-only setups hide coordination failures, with verifiers approving 49% of failing work and teams sometimes harming performance when solo agents already succeed.
AcademiClaw is a new benchmark of 80 student-sourced academic tasks where the best frontier AI agents achieve only a 55% pass rate.
LLMs predict outcomes of real scientific experiments at 14-26% accuracy, comparable to human experts, but lack calibration on prediction reliability while humans demonstrate strong calibration.
citing papers explorer
-
The Meta-Agent Challenge: Are Current Agents Capable of Autonomous Agent Development?
The Meta-Agent Challenge shows frontier AI models rarely match human-engineered agent baselines when tasked with autonomous development, with proprietary models succeeding most often and some exhibiting cheating under pressure.
-
Power Systems Agent Benchmark: Executable Evaluation of AI Agents in Electric Power Engineering
Introduces the Power Systems Agent Benchmark with 41 task families across eight power engineering areas for executable evaluation of AI agents using deterministic feasibility checks.
-
Agentic AutoResearch forSpace Autonomy: An Auditable, LLM-Driven Research Agent for Aerospace Control Problems
An LLM-driven agent with built-in seed-noise audits develops control policies for two aerospace problems that outperform undirected search and pass verification checks.
-
AgentBeats: Agentifying Agent Assessment for Openness, Standardization, and Reproducibility
AgentBeats implements agentified evaluation of diverse AI agents through standardized interfaces, validated at scale in a five-month competition with 298 judges and 467 subjects plus a coding case study.
-
Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories
Data2Story is a multi-agent framework that generates evidence-grounded multimodal articles from data, evaluated on 18 articles against human pieces for verifiability, angle coverage, and quality across human, rubric, and automated judges.
-
What Do Evolutionary Coding Agents Evolve?
Evolutionary coding agents achieve most benchmark gains through a small subset of edit types and by cycling previously deleted code lines rather than developing new algorithmic structures.
-
DecisionBench: A Benchmark for Emergent Delegation in Long-Horizon Agentic Workflows
DecisionBench supplies a fixed task suite, model pool, delegation interface, and multi-axis metrics to evaluate emergent delegation, showing similar quality across awareness conditions but 15-31 point headroom under perfect delegation.
-
WebGameBench: Requirement-to-Application Evaluation for Coding Agents via Browser-Native Games
WebGameBench is a new benchmark that evaluates coding agents on building browser-native games from frozen specifications, with runtime browser evaluation showing best agents reach 76.9% usable rate but only 20.2% excellent rate.
-
FML-bench: A Controlled Study of AI Research Agent Strategies from the Perspective of Search Dynamics
FML-Bench shows a simple greedy hill-climber nearly matches tree search on dense-opportunity tasks while an adaptive agent that broadens search on stagnation outperforms six baselines across 18 tasks.
-
BioXArena: Benchmarking LLM Agents on Multi-Modal Biomedical Machine Learning Tasks
BioXArena benchmarks LLM agents on generating end-to-end ML pipelines for 76 multi-modal biomedical tasks, with MLEvolve plus Gemini-3.1-Pro scoring highest at 0.666.
-
SMCEvolve: Principled Scientific Discovery via Sequential Monte Carlo Evolution
SMCEvolve applies Sequential Monte Carlo sampling to LLM program search with adaptive resampling, mutation mixtures, and convergence control, delivering finite-sample complexity bounds and benchmark gains over prior systems.
-
Graphs of Research: Citation Evolution Graphs as Supervision for Research Idea Generation
GoR extracts citation DAGs using position, frequency, predecessor links and time, then fine-tunes Qwen2.5-7B on 498 seed papers to generate ideas, claiming SOTA over gpt-4o baselines via LLM judges.
-
Collider-Bench: Benchmarking AI Agents with Particle Physics Analysis Reproduction
Collider-Bench is a new benchmark showing that current LLM agents cannot reliably reproduce LHC analyses at the level of a physicist-in-the-loop.
-
KompeteAI: Accelerated Autonomous Multi-Agent System for End-to-End Pipeline Generation for Machine Learning Problems
KompeteAI accelerates AutoML pipeline evaluation 6.9 times and beats prior systems by 3% on MLE-Bench through candidate merging, external RAG, and predictive early scoring.
-
SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces
SkillSafetyBench is a benchmark of 155 cases across 47 tasks and 6 risk domains showing that non-user attacks via skills, artifacts, or environments can consistently induce unsafe agent behavior.
-
TeamBench: Evaluating Agent Coordination under Enforced Role Separation
Enforcing role separation in agent teams reveals that prompt-only setups hide coordination failures, with verifiers approving 49% of failing work and teams sometimes harming performance when solo agents already succeed.
-
AcademiClaw: When Students Set Challenges for AI Agents
AcademiClaw is a new benchmark of 80 student-sourced academic tasks where the best frontier AI agents achieve only a 55% pass rate.
-
SciPredict: Can LLMs Predict the Outcomes of Scientific Experiments in Natural Sciences?
LLMs predict outcomes of real scientific experiments at 14-26% accuracy, comparable to human experts, but lack calibration on prediction reliability while humans demonstrate strong calibration.
-
FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks
FrontierFinance benchmark shows human financial experts outperform state-of-the-art LLMs by achieving higher scores and more client-ready outputs on realistic long-horizon tasks.
-
OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
OSWorld 2.0 is a benchmark of 108 realistic long-horizon computer-use tasks where current agents achieve only 20.6% binary completion, struggling with state inference and constraint tracking.
-
Learning the ARTS of Search for Automated Discovery
ARTS improves automated scientific discovery by using reasoning LMs with test-time training to separate hypothesis merit from execution quality in tree search, achieving 15.3% relative gains on 22 MLGym and MLEBench tasks.
-
Trustworthy Self-Composable Big-Data-as-a-Service: An LLM-Orchestrated Multi-Agent Framework for Automated Data Engineering, AutoML, MLOps Deployment, and Drift-Aware Lifecycle Optimization
An LLM-orchestrated multi-agent framework for end-to-end BDaaS automation with drift awareness is proposed and evaluated on tabular benchmarks for improved lifecycle reliability over baselines.
-
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
Arbor combines a coordinator, executors, and a hypothesis tree to enable cumulative autonomous research, outperforming Codex and Claude Code by over 2.5x on six real tasks and reaching 86.36% Any Medal on MLE-Bench Lite.
-
Can Generalist Agents Automate Data Curation?
Generalist agents reach published data-selection baselines but require scaffolds forcing method adaptation to autonomously compose a policy that outperforms baselines at one-tenth the data budget.
-
VESTA: Visual Exploration with Statistical Tool Agents
VESTA introduces dynamic tool creation for VLMs that outperforms static-tool and no-tool baselines on distribution fitting, time series, and astronomy tasks in the new DAWN benchmark.
-
ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence
ScientistOne introduces Chain-of-Evidence and an audit system that achieves zero hallucinated references, perfect score verification, and top method-code alignment while matching or beating human experts on five frontier tasks and generalizing to six more.
-
WildRoadBench: A Wild Aerial Road-Damage Grounding Benchmark for Vision-Language Models and Autonomous Agents
WildRoadBench is a new dual-track benchmark on professionally annotated wild UAV road-damage images showing closed-source VLMs lead but leave over half the AP_50 metric on the table while agents lag and open-source models collapse on small targets.
-
What and When to Distill: Selective Hindsight Distillation for Multi-Turn Agents
SERL selectively reweights learning using task success and environment feedback to reach 90.0% success on ALFWorld and 80.1% on WebShop, outperforming RL and distillation baselines.
-
How Far Are We From True Auto-Research?
ResearchArena shows that agent-generated papers fail top-tier acceptance standards primarily due to fabricated results, underpowered experiments, and plan-execution mismatches that vary sharply by agent.
-
DiagEval: Trajectory-Conditioned Diagnosis for Reliable Software Evaluation with GUI Agents
DiagEval applies trajectory-conditioned diagnostic probes to recover 45.6-62.1% of misattributed failures in GUI-agent software evaluation, raising accuracy from 69.9% to 78.3% on WebDevJudge-Unit and 65.0% to 81.6% on RealDevBench.
-
DataMaster: Data-Centric Autonomous AI Research
DataMaster deploys an AI agent to autonomously engineer data via tree search over external sources, shared candidate pools, and memory of past outcomes, yielding 32% higher medal rates on MLE-Bench Lite and a small GPQA gain over the base instruct model.
-
Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search
Gome reaches 35.1% any-medal rate on MLE-Bench by mapping reasoning to gradient-based updates, outperforming tree search once models are sufficiently capable.
-
What Makes AI Research Replicable? Executable Knowledge Graphs as Scientific Knowledge Representations
xKG is a paper-centric knowledge base that extracts code and insights to improve LLM agent performance on AI research replication by 10.9% on PaperBench.
-
MachineLearningLM: Scaling Many-shot In-context Learning via Continued Pretraining
MachineLearningLM uses continued pretraining on SCM-synthesized ML tasks with random-forest distillation to give LLMs robust many-shot in-context learning on tabular classification, reaching random-forest accuracy levels while preserving general chat performance.
-
RExBench: Can coding agents autonomously implement AI research extensions?
RExBench is a new benchmark showing that LLM coding agents fail to autonomously implement most realistic research extensions to prior AI papers.
-
VS-Bench: Evaluating VLMs for Strategic Abilities in Multi-Agent Environments
VS-Bench is a new benchmark of ten visual multi-agent environments that measures VLMs on element recognition, next-action prediction, and normalized episode return, showing strong perception but large gaps in reasoning and decision-making with the best model at 46.6% prediction accuracy and 31.4% of
-
OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces
OPT-BENCH and OPT-Agent evaluate LLM self-optimization in large search spaces, showing stronger models improve via feedback but stay constrained by base capacity and below human performance.
-
Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning
Odysseus adapts PPO with a turn-level critic and leverages pretrained VLM action priors to train agents achieving at least 3x average game progress over frontier models in long-horizon Super Mario Land.
-
On Benchmark Hacking in ML Contests: Modeling, Insights and Design
In a game-theoretic model of ML contests, low-type contestants engage in benchmark hacking while high-types focus on creative effort, with more skewed rewards improving overall outcomes.
-
Evaluation-driven Scaling for Scientific Discovery
SimpleTES scales test-time evaluation in LLMs to discover state-of-the-art solutions on 21 scientific problems across six domains, outperforming frontier models and optimization pipelines with examples like 2x faster LASSO and new Erdos constructions.
-
TREX: Automating LLM Fine-tuning via Agent-Driven Tree-based Exploration
TREX automates the LLM training lifecycle via collaborative agents and tree-based exploration, delivering consistent performance gains across 10 real-world fine-tuning tasks in FT-Bench.
-
Frontier-Eng: Benchmarking Self-Evolving Agents on Real-World Engineering Tasks with Generative Optimization
Frontier-Eng is a new benchmark for generative optimization in engineering where agents iteratively improve designs under fixed interaction budgets using executable verifiers, with top models like GPT 5.4 showing limited success.
-
Pioneer Agent: Continual Improvement of Small Language Models in Production
Pioneer Agent automates the full lifecycle of adapting and continually improving small language models via diagnosis-driven data synthesis and regression-constrained retraining, delivering gains of 1.6-83.8 points on benchmarks and large lifts in production-style tasks.
-
Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent
A 35B MoE agent model trained on 45K-token trajectories via three-stage SFT and domain-routed distillation achieves leading or competitive scores against 1T models on SEAL-0, IFBench, HiPhO, FrontierScience-Olympiad and MolBench-Bind.
-
Towards Persistent Case-Based Memory for Autonomous Data Science: A CBR-Augmented R&D-Agent with a Locally Deployable Small Language Model
CBR integration into R&D-Agent with Gemma 4 31B yields directionally higher accuracy and lower variance than baseline on one of two Kaggle competitions.
-
AION: Next-Generation Tasks and Practical Harness for Time Series
AION is a time series harness using agents, skills, rules, memory, evaluation, and protocols with temporal grounding, shown in a Kaggle Store Sales case study to produce more artifacts and reviews than direct agent use.
-
Declarative Data Services: Structured Agentic Discovery for Composing Data Systems
DDS introduces typed contracts at intent, operator DAG, skills, and runtime layers to bound agentic search for data system compositions, achieving convergence on a trading workload where unbounded iteration fails.
-
AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration
AutoResearchClaw introduces a multi-agent research pipeline with debate, self-healing, verifiable outputs, human collaboration modes, and cross-run evolution that outperforms AI Scientist v2 by 54.7% on ARC-Bench.
-
Business Utility of Large Language Models as Exploratory Data Analysis Agents
Evaluation of 15 LLM configurations across four conditions in a supply chain EDA benchmark finds most lack sufficient repeatability for autonomous deployment, with GPT-5.4 at extra-high reasoning effort scoring highest on mean score (0.8748) and proposed Business utility (0.6952).
-
From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments
An empirical literature analysis reveals a bifurcation in RL environments into Semantic Prior (LLM-dominated) and Domain-Specific Generalization ecosystems with distinct cognitive fingerprints.