Stateless Language Agents: Scaling Long-Horizon Automated Research
cs.LG, cs.AI, cs.CL
Submitted: 2026-10-06
Updated: 2026-10-06
Code: https://github.com/anthropics/original_
Sources
- CodeEvolve: an open source evolutionary coding agent for algorithmic discovery and optimization
- AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization
- Accelerating scientific discovery with Co-Scientist
- AIDE: AI-Driven Exploration in the Space of Code
- SOL-ExecBench: Speed-of-Light Benchmarking for Real-World GPU Kernels Against Hardware Limits
- When Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token Analysis
- ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoning
- The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
- Kosmos: An AI Scientist for Autonomous Discovery
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- SwarmResearch: Orchestrating Coding Agents for Open-Ended Discovery
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- ThetaEvolve: Test-time Learning on Open Problems
- Diagnosing and Mitigating Context Rot in Long-horizon Search
- Self-Improving Language Models with Bidirectional Evolutionary Search
- The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks