Understanding the Challenges in Iterative Generative Optimization with LLMs
cs.LG, cs.AI
Submitted: 2026-03-25
Updated: 2026-11-07
Code: https://github.com/ameliakuang/LLM-Game-Playing-Agents
Project page: https://langchain-ai.github.io/langgraph
Terminology
Sources
- GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
- Kevin: Multi-Turn RL for Generating CUDA Kernels
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- Tversky Neural Networks: Psychologically Plausible Deep Learning with Differentiable Tversky Similarity
- Competitive Programming with Large Reasoning Models
- Robin: A multi-agent system for automating scientific discovery
- A Definition of AGI
- Bayesian Active Learning for Classification and Preference Learning
- Adam: A Method for Stochastic Optimization
- Measuring AI Ability to Complete Long Software Tasks
- ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution
- Towards Robust Agentic CUDA Kernel Benchmarking, Verification, and Optimization
- In-the-Flow Agentic System Optimization for Effective Planning and Tool Use
- Playing Atari with Deep Reinforcement Learning
- The Importance of Directional Feedback for LLM-based Optimizers
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
- Measuring Agents in Production
- POLCA: Stochastic Generative Optimization with LLM
- Scaling Long-Horizon LLM Agent via Context-Folding
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis