How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering?
cs.AI
Submitted: 2026-09-30
Updated: 2026-09-30
Code: https://github.com/anomalyco/opencode
Sources
- Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent
- AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering
- Why Do Multi-Agent LLM Systems Fail?
- MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering
- MARS: Modular Agent with Reflective Search for Automated AI Research
- AutoMLGen: Navigating Fine-Grained Optimization for Coding Agents
- MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery
- MLZero: A Multi-Agent System for End-to-end Machine Learning Automation
- Beyond Solution-Centric Search: Adaptive Inquiry and Knowledge Revision for Autonomous ML Engineering
- Gemma 4 Technical Report
- GLM-5: from Vibe Coding to Agentic Engineering
- AIRA_2: Overcoming Bottlenecks in AI Research Agents
- AIDE: AI-Driven Exploration in the Space of Code
- SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
- Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
- Kimi K3: Open Frontier Intelligence
- KompeteAI: Accelerated Autonomous Multi-Agent System for End-to-End Pipeline Generation for Machine Learning Problems
- iML: Executable, Problem-Grounded, and Broadly Exploratory Code-Driven AutoML
- MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI
- ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems