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.
hub
AIDE: AI-Driven Exploration in the Space of Code
50 Pith papers cite this work. Polarity classification is still indexing.
50
Pith papers citing it
abstract
Machine learning, the foundation of modern artificial intelligence, has driven innovations that have fundamentally transformed the world. Yet, behind advancements lies a complex and often tedious process requiring labor and compute intensive iteration and experimentation. Engineers and scientists developing machine learning models spend much of their time on trial-and-error tasks instead of conceptualizing innovative solutions or research hypotheses. To address this challenge, we introduce AI-Driven Exploration (AIDE), a machine learning engineering agent powered by large language models (LLMs). AIDE frames machine learning engineering as a code optimization problem, and formulates trial-and-error as a tree search in the space of potential solutions. By strategically reusing and refining promising solutions, AIDE effectively trades computational resources for enhanced performance, achieving state-of-the-art results on multiple machine learning engineering benchmarks, including our Kaggle evaluations, OpenAI MLE-Bench and METRs RE-Bench.
hub tools
citation-role summary
background 3
baseline 1
citation-polarity summary
representative citing papers
Data Flow Control formalizes data safety as aggregate predicates over provenance monomials and implements enforcement via the Passant query rewriting layer achieving near-zero overhead across five DBMS engines.
SpecBench shows frontier coding agents saturate visible test suites but exhibit persistent reward hacking on held-out tests, with the gap growing 28 percentage points per tenfold increase in code size.
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.
MEMOIR adds branch-local and global memory with a reflection step to tree search for LLM solver synthesis, reaching 96.7% solution validity and 7.3-point score gains over baselines on seven CO problems with lower run-to-run variance.
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.
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.
Reasoning LLMs with minimal tools for tree construction and analysis induce decision trees that outperform CART, compete with ensembles on low-resource tabular data, and provide human-readable reasoning traces.
SAGE with MHFA improves failure recovery in autonomous research agents, raising metrics-bearing outputs from 42% to 92% on a 12-topic benchmark versus single-reflection baselines.
Trellis treats agent experience graphs as first-class database state so that search patterns become queries, enabling crash recovery, scaling, and closed-loop training as architectural byproducts.
Heuresis evaluates six search strategies for autonomous ML research agents and finds that novel ideas are rare, none rated original, and only one reaches top-10 quality while strategies steer axes but do not expand the quality-novelty frontier.
Closed-loop LM-agent auto research finds some transferable gains on molecular property prediction benchmarks via external data but shows non-transfer for model and feature edits selected on validation.
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.
VTOS jointly searches solution and observer programs to adaptively orchestrate vision tools, outperforming static pipelines on dense object counting and zero-shot plant disease segmentation.
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.
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.
Decentralized AI agent teams self-organize around hypotheses, critique proposals, and share knowledge to outperform single-agent baselines on biomedical ML, language-model optimization, and protein fitness tasks.
Proposes agentic framework-based reproduction with a slot-binding interface to turn 16 PHM papers into standardized, assumption-aware benchmark implementations.
MLReplicate benchmark evaluates six autonomous systems on 45 manuscripts from ICML 2025 papers, finding that automated reviews accept flawed outputs with fabricated claims while human review exposes methodological failures, and that the cheapest system outperforms the most expensive by a wide margin
DrugSAGE accumulates cross-task memory of skills, statistical evidence, and recurring errors to let LLM agents achieve top-ranked performance on molecular property prediction tasks with reduced or zero test-time search.
AutoLLMResearch trains agents in a multi-fidelity LLMConfig-Gym environment formulated as a long-horizon MDP to enable cross-fidelity extrapolation for automating high-cost LLM experiment configurations.
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.
CellScientist introduces a dual-space hierarchical orchestration system that enables closed-loop refinement of virtual cell models by routing execution discrepancies back to hypothesis or implementation updates, yielding improved benchmark performance with auditable traces.
SHARP is a neuro-symbolic method that evolves bounded, auditable rule rubrics for LLM trading agents via cross-sample attribution and walk-forward validation, raising compact-model performance by 10-20 percentage points across equity sectors.