arXiv AI
The View from Nowhere: Population-Centered Agent Evolution
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
Hugging Face Trending Papers
2d ago
The View from Nowhere: Population-Centered Agent Evolution
Self-improving AI systems can revise the designs that govern their own behavior. Yet existing approaches center improvement on selected parent agents and their evolutionary experience, leaving the bro...
arXiv AI
Oct 21
Evolving Agent Interfaces
The paper introduces Agent S4, an autonomous system that learns to design and refine user interfaces for computer‑use agents by observing task execution without explicit success labels. By evolving a repository of interfaces through population‑based selection on unseen validation tasks, Agent S4 achieves state‑of‑the‑art performance on OSWorld V2 and significant gains on ScienceBoard, outperforming large commercial models at lower cost. The work demonstrates that interface design can be treated as an agent capability, enabling continuous improvement beyond fixed, hand‑crafted interfaces.
arXiv Computation and Language
Oct 22
Evolving with Open Worlds: Towards Recursive Self-Improvement for Future Forecasting
arXiv:2610.29784v1 Announce Type: new Abstract: Most contemporary artificial intelligence (AI) systems are released with frozen parameters and improve through external updates, whereas an ideal syste...
arXiv AI
Jun 26
The Red Queen G\"odel Machine: Co-Evolving Agents and Their Evaluators
arXiv:2606. 26294v1 Announce Type: cross Abstract: Self-improving agents are state-of-the-art (SOTA) on agentic coding benchmarks and have recently been extended to general domains.
arXiv Machine Learning
Oct 8
FreeEvolve: Learning to Evolve Beyond Fixed Loops
FREEEVOLVE automates the optimization loop used by agent evolvers, allowing the system to decide what to test, how much evidence to gather, which candidates to pursue, and when to stop, all within specified resource limits. By treating these decisions as an editable evolution skill and improving them through meta‑evolution, the method learns a capability that replaces hand‑crafted search loops. Experiments on several benchmarks show that FREEEVOLVE improves primary metrics by an average of 13.6 points and that meta‑evolved skills add further gains, indicating transferability across environments.
arXiv AI
Aug 11
DarwinX: Evolving Agent Harnesses Through Natural Selection
arXiv:2608. 07545v1 Announce Type: cross Abstract: An LLM agent's capability depends not only on model weights but on its harness: prompts, tools, skills, and control flow.