10 papers
Beyond the Best Guess: Improving LLM Solution Coverage with Evolution Strategies
Conor F. Hayes, Elliot Meyerson, Kajetan Schweighofer +4
Large Language Models (LLMs) are increasingly deployed in discovery domains such as math and science. The usual approach is to present the problem to the model and use its answer a…
Simple-to-Complex Structured Demonstrations for Vision-Language-Action Learning
Xinchuan Qiu, Yi Yu
Vision-Language-Action (VLA) models have demonstrated strong capabilities in robotic manipulation by integrating visual perception, language understanding, and robot action generat…
Benchmarking Vision-Language-Action Models on SO-101: Failure and Recovery Analysis
Yi Yu, Xinchuan Qiu
Vision-Language-Action (VLA) models have demonstrated strong generalization in robotic manipulation, yet existing evaluations are primarily conducted in simulation or on expensive…
Overcoming Forgetting in LLM Fine-Tuning with Evolution Strategies
Kajetan Schweighofer, Conor F. Hayes, Roberto Dailey +2
Evolution Strategies (ES) has recently emerged as a competitive alternative to reinforcement learning (RL) for large language model (LLM) fine-tuning, offering advantages through s…
Quantized Evolution Strategies: High-precision Fine-tuning of Quantized LLMs at Low-precision Cost
Yinggan Xu, Kajetan Schweighofer, Risto Miikkulainen +1
Post-Training Quantization (PTQ) is essential for deploying Large Language Models (LLMs) on memory-constrained devices, yet it renders models static and difficult to fine-tune. Sta…
Fine-Tuning Language Models to Know What They Know
Sangjun Park, Elliot Meyerson, Xin Qiu +1
Evaluating true metacognition in Large Language Models (LLMs) is difficult due to biases and heuristics. This paper presents a framework to measure and enhance LLM metacognition wh…
The Blessing of Dimensionality in LLM Fine-tuning: A Variance-Curvature Perspective
Qiyao Liang, Jinyeop Song, Yizhou Liu +4
Weight-perturbation evolution strategies (ES) can fine-tune billion-parameter language models with surprisingly small populations (e.g., ), contradicting classical…
Solving a Million-Step LLM Task with Zero Errors
Elliot Meyerson, Giuseppe Paolo, Roberto Dailey +6
LLMs have achieved remarkable breakthroughs in reasoning, insights, and tool use, but chaining these abilities into extended processes at the scale of those routinely executed by h…
Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning
Xin Qiu, Yulu Gan, Conor F. Hayes +6
Fine-tuning large language models (LLMs) for downstream tasks is an essential stage of modern AI deployment. Reinforcement learning (RL) has emerged as the dominant fine-tuning par…
Position: Scaling LLM Agents Requires Asymptotic Analysis with LLM Primitives
Elliot Meyerson, Xin Qiu
Decomposing hard problems into subproblems often makes them easier and more efficient to solve. With large language models (LLMs) crossing critical reliability thresholds for a gro…