MLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning Engineering

Shangheng Du; Jinxin Shi; Shuaiyu Zhang; Yiming Wu; Junpeng Zhao; Shiyang Feng; Xin Li; Liang He

cs.AIOct 15, 2026

MLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning Engineering

Authors: Shangheng Du, Jinxin Shi, Shuaiyu Zhang, Yiming Wu, Junpeng Zhao, Shiyang Feng, Xin Li, Liang He,

Organizations: East China Normal University · Shanghai Artificial Intelligence Laboratory

Abstract

Large language models (LLMs) are expanding from assisting scientific research and engineering to autonomously developing and improving AI systems, advancing AI for AI (AI4AI) as a pathway toward recursive self-improvement (RSI). Workflow-driven machine learning engineering (MLE) systems provide a practical path toward this pursuit through complex orchestration that manages long-horizon experimentation, while recent MLE systems adopt model-directed interaction, allowing models to autonomously organize experiments and adapt optimization strategies based on execution feedback. However, feedback from each experiment reflects several preceding decisions, and a long MLE run contains many such costly experiments. Training must therefore select useful supervision from long interaction trajectories and learn from intermediate outcomes. We propose a post-training method for autonomous long-horizon MLE optimization and apply it to train MLExpert, a 35B Mixture-of-Experts agentic model. We design the Kaggle-MLE Factory to construct executable tasks and an interaction harness for model-directed experimentation. Hierarchical agentic SFT transfers general tool-use and coding capabilities to MLE through outcome-guided supervision. Windowed Interaction RL (WIRL) treats the multi-turn decisions between successive experiment results as an execution window and assigns it a shared outcome-based reward. Asynchronous collection and policy correction support policy updates before the trajectory ends. On MLE-Bench Lite, MLExpert improves the average medal rate of the base model from 37.9% to 72.7%, achieving performance comparable to larger frontier models such as Kimi-K3 and GLM-5.3. Further experiments show that MLExpert improves performance on NatureBench Lite, agent scaffold optimization, and algorithm optimization, suggesting that the learned optimization capability generalizes to other tasks.

Figures & tables

Figure 1: Decision making in long-horizon MLE optimization. (a) External orchestration organizes optimization through predefined workflows and search rules. (b) In model-directed interaction, the model selects subsequent actions based on experimental states and execution feedback.

Figure 2: Overview of MLExpert training for autonomous MLE. The Kaggle-MLE Factory constructs executable tasks, and the interaction harness supports model-directed experimentation and trajectory collection. Hierarchical agentic SFT learns from demonstrations, while WIRL further optimizes the policy from execution feedback collected during online interaction.

Model	MLExpert Harness					General-Purpose Harness
Model	Med+	Gold	Silver	Bronze	Medal	Harness	Medal
Same-scale baselines (35B total, $\sim$ 3B active)
Qwen3.6-35B-A3B	62.1	22.7	7.6	7.6	37.9	Claude Code	42.4
Ornith-1.5-35B-A3B	57.6	22.7	12.1	4.5	39.4	Claude Code	47.0
Nex-N2.5-mini	66.7	24.2	13.6	9.1	47.0	Claude Code	36.4
Larger frontier models

Table 1: Main results on MLE-Bench Lite. We report performance (%) under the unified MLExpert Harness and, where available, under general-purpose agentic coding harnesses. Bold and underline mark the best and second-best distinct values in each metric column, including ties. Detailed evaluation results are provided in Appendix D.1 .

Model	Harness	M (%) $\uparrow$	S (%) $\uparrow$
Same-scale baselines
Qwen3.6-35B-A3B	Claude Code	40.0 (4/10)	0.0 (0/10)
Nex-N2.5-mini	Claude Code	80.0 (8/10)	20.0 (2/10)
Ornith-1.5-35B-A3B	Claude Code	60.0 (6/10)	30.0 (3/10)
Larger frontier models
DeepSeek-V4-Pro Preview	Claude Code	60.0 (6/10)	20.0 (2/10)

Table 2: Results on NatureBench Lite. M denotes Match-SOTA (

g\geq 0

), while S denotes Surpass-SOTA (

g>0.1

), which serves as a key metric for directly assessing agents’ ability to surpass published scientific results.

Table 5

Figure 3: Long-horizon optimization on MLSP 2013 Birds. (a) Representative optimization progress of MLExpert. (b) Initial and final ROC-AUC for Base, MLExpert-SFT, and MLExpert.

Method	Dev. $\uparrow$	Held-out $\uparrow$	Calls $\downarrow$
Initial	21.1	20.0	1.00
Majority@5	24.4	24.8	5.00
Base	28.9	23.3	5.74
Kimi-K3	45.6	40.0	8.65
GLM-5.3	47.8	48.1	9.39
MLExpert-SFT (Ours)	37.8	38.1	3.51

Table 5: AIME scaffold optimization with GPT-4.1-nano. Higher accuracy (%) and fewer calls are better. Bold/underline: best/second-best.

Figure 4: Algorithm-component optimization on 12 selected MLS-Bench-Lite tasks. Bars show normalized verifier rewards for Base and MLExpert.

Appendix figures & tables8 assets

Supplementary material from the paper’s appendix.

Appendix

Tools	Purpose
analyze	Delegate data, result, or error analysis
execute_bash	Inspect data and runtime environment
write_full_code , patch_code	Create or revise candidate solutions
execute_code , control_run	Launch and control experiments
write_plan , edit_plan , read_plan	Maintain persistent experiment plans
list_nodes , select_node	Retrieve candidate states and history

Appendix

Table 6: Tools provided by the Interaction Harness.

Domain	Teacher	Source trajectories	Input records
MLE	GLM-5.2	412	4,961
Scientific experimentation	GLM-5.2	143	342
Scientific experimentation	Qwen3.8-Max	81	236
Total		636	5,539

Appendix

Table 7: Composition of the MLE-domain SFT input corpus. Source trajectories count distinct retained runs. Input records count serialized training examples after segmentation and repeated sampling, before training-time preprocessing and packing.

Hyperparameter	Description	Value
General Agent SFT
Learning rate	Initial / minimum learning rate	$2\times 10^{-5}\,/\,10^{-6}$
Batch size	Global batch size	32
Sequence length	Maximum training tokens per sequence	131,072
Training epochs	Number of passes over the dataset	1
Warmup ratio	Fraction of training steps for warmup	0.05

Appendix

Table 8: Key hyperparameters for hierarchical agentic SFT and WIRL.

Model	Med+ (%)	Gold (%)	Silver (%)	Bronze (%)	Any Medal (%)
Qwen3.6-35B-A3B	$62.12\pm 4.01$	$22.73\pm 2.62$	$7.58\pm 4.01$	$\underline{7.58}\pm 1.52$	$37.88\pm 5.46$
Ornith-1.5-35B-A3B	$57.58\pm 1.52$	$22.73\pm 6.94$	$12.12\pm 1.52$	$4.55\pm 2.62$	$39.39\pm 4.01$
Nex-N2.5-mini	$66.67\pm 1.52$	$24.24\pm 6.06$	$13.64\pm 2.62$	$\mathbf{9.09}\pm 4.55$	$46.97\pm 1.52$
DeepSeek-V4-Pro Preview	86.36	40.91	13.64	9.09	63.64
MiniMax M3	81.82	54.55	13.64	0.00	68.18
GLM-5.3	90.91	59.09	13.64	0.00	72.73

Appendix

Table 9: MLE-Bench Lite results with the MLExpert Harness. Percentages are reported as average

\pm

SEM over three evaluations for MLExpert and same-scale baselines; one result is reported for each larger frontier model.

Method	Any Medal (%)
GRPO	$56.06\pm 5.46$
PPO-style	$60.61\pm 4.01$
WIRL w/o trend reward	$\underline{66.67}\pm 3.03$
WIRL w/o policy correction	$65.15\pm 5.46$
WIRL	$\mathbf{72.73}\pm 2.62$

Appendix

Table 10: RL baselines and WIRL ablations on MLE-Bench Lite. Any Medal rates are reported as average

\pm

SEM over three evaluations.

Figure 5: Learner waiting fractions during RL training. Light curves show recorded per-update values; dark curves show trailing five-update means.

Method	Development	Held-out accuracy (%)				Calls per problem
	2025	2023	2024	2026	Average
Initial	21.1	20.0	23.3	16.7	20.0	1.00
Majority@5	24.4	18.9	32.2	23.3	24.8	5.00
Base	28.9	18.9	28.9	22.2	23.3	5.74
Ornith-1.5-35B-A3B	24.4	20.0	18.9	16.7	18.5	1.00
Nex-N2.5-mini	32.2	17.8	27.8	33.3	26.3	5.93

Appendix

Table 11: Complete AIME scaffold optimization results. Accuracy (%) is higher-is-better; calls are lower-is-better. Held-out accuracy and calls are averaged over AIME 2023, 2024, and 2026; each year’s accuracy averages three evaluations of 30 problems. Bold and underline mark the best and second-best distinct values in each column, including ties.

Domain	Official task title	Base	MLExpert
Language Models	Masked Diffusion Demasking Policy	0.148150	0.386696
Classical & Adaptive Learning	Geometry-Robust Clustering Algorithm	0.439982	0.525322
Reinforcement Learning	Value-Based Discrete Control	0.141849	0.425318
Optimization & Theory	Multi-Objective Evolutionary Survival and Variation	0.160624	0.350473
Robotics	Behavioral Cloning Loss for Manipulation	0.435532	0.444879
Vision & Generation	3D Scene Densification Strategy	0.000000	0.000000

Appendix

Table 12: Results on 12 tasks selected from MLS-Bench-Lite, one per domain. Scores are normalized rewards from the official Harbor verifier; the final row is the arithmetic mean over the 12 tasks. Bold and underline mark the best and second-best values within each row, including ties.

LLM Agent Training

Large language model agent training teaches models to plan, use tools, and learn from multi-step interaction with environments.

See all 585 papers

Oct 9, 2026

Humanize MLE Agents: Multi-Agent Session Alternation Beyond Single-Agent Limits

Existing LLM-based agent approaches for long-horizon machine learning engineering (MLE) often use context engineering, implemented through custom harnesses that manage tools, skills, and accumulated experience. However, we find that as single-session execution lengthens, the agent's reasoning intensity declines alongside slowing progress, summarized as long-horizon deceleration, and the benefits of these custom harnesses vanish as the underlying model improves, summarized as harness staleness. These findings suggest that their benefits may not persist across versions, which motivates a workflow-level approach in which agents build on one another's work across sessions. We model these alternating agent sessions as a context-reset semi-Markov decision process (CR-SMDP) and establish sufficient conditions for alternation to exceed single-agent reference limits, derive an explicit experiment-budget bound, and characterize when session caps preserve this advantage. Guided by this analysis, we introduce Humanize MLE Agents (HMA), which alternates two agents on a shared workspace, limits each session to at most k experiments and resets the context between sessions, without additional task-specific harness or prior knowledge supplements. Across 75 Kaggle tasks in MLE-bench, HMA reaches a state-of-the-art any-medal rate of 78.2%, exceeding the strongest open-source baseline by 8.0 points with a quarter of its time budget. Moreover, among six configurations spanning five heterogeneous agent pairs, HMA improves any-medal rate over the constituent baselines by 6.4 points on average, demonstrating cross-pair generality. A supplementary case on kernel optimization reaches 878 cycles, within 1.6% of the community leaderboard leader, demonstrating applicability beyond MLE.

Changye Li, Zijian Zhang, Muheng Li +12

Tsinghua University · NVIDIA · Zhejiang University +1

Long-Horizon LLM Agents Multi-Agent Collaboration

Ask PDF

Apr 14, 2026

Toward Autonomous Long-Horizon Engineering for ML Research

Agentic systems increasingly automate pieces of AI research. Yet turning underspecified research objectives into runnable, experimentally validated ML systems remains a central bottleneck. We study this operational setting as long-horizon ML research engineering: converting a research specification into a runnable ML system through repeated implementation, experimentation, and refinement. The central challenge is to sustain cumulative project progress across heterogeneous stages under delayed, confounded feedback. We introduce AiScientist, a multi-agent system built around thin control over thick state: a lightweight hierarchical research team coordinates through a File-as-Bus workspace that preserves decision-relevant artifacts across roles and invocations. On PaperBench, AiScientist improves over the strongest matched baselines by 9.92 and 11.15 points with Gemini-3-Flash and GLM-5, respectively. On MLE-Bench Lite, it reaches 81.82 Any Medal% under both backbones, improving over the strongest matched baselines by 4.55 and 16.67 points, and exceeding a Codex/GPT-5.5 xhigh frontier harness reference by 13.64 Any Medal points. Ablations and process analyses show that durable project state is central to later-round refinement: removing File-as-Bus lowers PaperBench score by 6.41 points and MLE-Bench Lite Any Medal% by 31.82 points. These results suggest that long-horizon AI research is not only a problem of stronger local reasoning, but a systems problem of maintaining cumulative, inspectable project progress.

Guoxin Chen, Jie Chen, Lei Chen +7

Long-Horizon LLM Agents Multi-Agent LLM Systems Memory-Augmented Agents

Ask PDF

Jul 27, 2026

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering

Machine learning engineering (MLE) tasks require long-horizon decision making over iterative solution debugging and refinement, under expensive and feedback-driven environment interactions. Developing and training a monolithic agent for such tasks is fundamentally challenging, as it must simultaneously manage extremely long and noisy contexts, explore vast solution spaces, and remain effective under limited model capacity and computational budgets. To address these challenges, we propose Matryoshka Agent, a unified hierarchical agent framework for complex long-horizon tasks. Matryoshka Agent decomposes agentic problem solving into a coordinated hierarchy of decision making and execution: a high-level Orchestrator maintains compact, long-horizon exploration states and issues strategic instructions, while lower-level Sub-Agents execute concrete solution attempts through direct environment interaction, mediated by standardized Tool interface. This design decouples strategic exploration from costly execution, substantially reducing the burden of long-context reasoning and enabling efficient iterative refinement. We further develop an efficient training paradigm for Matryoshka Agent. Experimental results on a broad range of MLE tasks with diverse model types and scales demonstrate that Matryoshka Agent is an effective and scalable paradigm for long-horizon MLE tasks and complex agentic problem solving. Notably, Matryoshka Agent enables Qwen3-4B-Instruct to reach Orchestrator performance comparable to o4-mini. Applying Matryoshka Agent to Qwen3-30B-Coder results in at most 36.7% relative performance gain.

Rushi Qiang, Changhao Li, Haotian Sun +3

Georgia Institute of Technology

LLM Agent Orchestration LLM Agents LLM Agent Training Long-Horizon Agent Tasks

Ask PDF

Abstract

LLM Agent Training

Explore similar work

Humanize MLE Agents: Multi-Agent Session Alternation Beyond Single-Agent Limits

Toward Autonomous Long-Horizon Engineering for ML Research

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering