Papers

Filtered to benchmark verification · clear filter

Browse by term

continual learning 83reinforcement learning 50large language models 12benchmarking 11benchmarks 11language models 11vision-language models 11robotics 7natural language processing 6world models 6generative models 5recursive self-improvement 5attention mechanisms 4diffusion Transformers 4multi-agent systems 4multimodal learning 4multimodal models 4on-policy distillation 4self-distillation 4self-supervised learning 4transformers 4video generation 4vision-language-action models 4agent-based systems 3agentic models 3agentic search 3autonomous systems 3coding agents 3diffusion models 3image generation 3

Matching papers

DarwinX: Evolving Agent Harnesses Through Natural Selection

72 upvotes · 31 JUL 2026 · Yifan Zhang, Yutong Dai, Juntao Tan et al.

This paper introduces DarwinX, a method for evolving agent capabilities through natural selection, which improves the agent's overall performance on various benchmarks without relying on task-specific patches. Practitioners might care about this approach as it allows for the creation of more general and durable agents that can adapt to changing environments.

continual learningagent evolutionnatural selectionmodel preservationbenchmark verification