CLEAR: Structured Specifications for Controllable Long-Horizon ML Research Engineering
cs.SE
Submitted: 2026-11-04
Updated: 2026-11-04
Terminology
Sources
- Why Do Multi-Agent LLM Systems Fail?
- CodeR: Issue Resolving with Multi-Agent and Task Graphs
- Toward Autonomous Long-Horizon Engineering for ML Research
- AIDE: AI-Driven Exploration in the Space of Code
- DeepCode: Open Agentic Coding
- Routoo: Learning to Route to Large Language Models Effectively
- ChatDev: Communicative Agents for Software Development
- Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning
- LoongFlow: Directed Evolutionary Search via a Cognitive Plan-Execute-Summarize Paradigm
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
- Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives
- Beyond Self-Talk: A Communication-Centric Survey of LLM-Based Multi-Agent Systems
- GLM-5: from Vibe Coding to Agentic Engineering
- Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents
- AIBuildAI: An AI Agent for Automatically Building AI Models
- Toward Ultra-Long-Horizon Agentic Science: Cognitive Accumulation for Machine Learning Engineering
Related papers
- ArkEval: Benchmarking and Evaluating Automated CodeRepair for ArkTS
- TestPrism: Rethinking Test Evaluation Beyond a Single Reference
- Mining Workflow Graphs for Black-Box Boundary Testing of Conversational LLM Agents
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- For Coding Agents, the Repository Matters