Evaluating Agentic Learning Harness Capabilities Without Labels via the Scaling

arXiv:2604.21003v1 Announce Type: new Abstract: AI agents are increasingly deployed on complex, domain-specific workflows -- navigating enterprise web applications that require

arXiv:2604.05013v1 Announce Type: cross Abstract: Current LLM coding agents are predominantly trained on composite benchmarks (e.g., bug fixing), which often leads to

arXiv:2605.15871v1 Announce Type: new Abstract: Toward recursive self-improvement, we investigate LLM agents autonomously designing foundation models beyond standard Transformers.

arXiv:2604.22748v1 Announce Type: new Abstract: As AI systems move from generating text to accomplishing goals through sustained interaction, the ability to model environment

arXiv:2605.08828v1 Announce Type: new Abstract: Large language model agents increasingly operate through environment-facing scaffolds that expose files, web pages, APIs, and logs.

arXiv:2610.00025v1 Announce Type: new Abstract: Agent harnesses increasingly want to run small language models (SLMs) on the microtasks around a frontier large language model

arXiv:2609.30967v1 Announce Type: new Abstract: Most work on improving large language models treats accuracy as the sole objective. We argue that the harness, the Python code

arXiv:2605.11556v1 Announce Type: new Abstract: Solving complex long-horizon tasks requires strong planning and reasoning capabilities. Although datasets with explicit