EvoCast: Reliable Autonomous Research Agents for Iterative Forecasting Architecture Evolution
cs.AI, cs.LG
Submitted: 2026-10-03
Updated: 2026-10-03
Comments: 26 pages, 11 figures, including references and appendices. Code: https://github.com/18e0-x/EvoCast
Code: https://github.com/18e0-x/EvoCast
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Nexus : An Agentic Framework for Time Series Forecasting
- ResearchGym: Evaluating Language Model Agents on Real-World AI Research
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
- AIRA_2: Overcoming Bottlenecks in AI Research Agents
- TimeKAN: KAN-based Frequency Decomposition Learning Architecture for Long-term Time Series Forecasting
- InternAgent: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification
- Agentic Neural Architecture Search
- AIDE: AI-Driven Exploration in the Space of Code
- Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
- Toto 2.0: Time Series Forecasting Enters the Scaling Era
- AutoResearch: An Execution-Grounded Multi-Agent Framework for Reliable Research Workflow Automation
- TS-Agent: Understanding and Reasoning Over Raw Time Series via Iterative Insight Gathering
- Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors
- The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
- MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement
- GenAutoML: An Agentic Framework for Dynamic Architecture Generation and Optimization in Time-Series Analysis
- Deep Time Series Models: A Comprehensive Survey and Benchmark
- ResearchLoop: An Evidence-Gated Control Plane for AI-Assisted Research
- SEA-TS: Self-Evolving Agent for Autonomous Code Generation of Time Series Forecasting Algorithms
- The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
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