TopPaper
Back to Categories
Category

Artificial Intelligence

3 Papers

January 15, 2026 Artificial Intelligence

The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models

Large language models (LLMs) are post-trained to adopt a default "helpful Assistant" persona, but this identity is fragile. The paper explores the internal "persona space" in model activations, discovering a dominant linear direction called the Assistant Axis the primary axis …

Christina Lu, Jack … 1 views 0 downloads
Artificial Intelligence

Toward Training Superintelligent Software Agents through Self-Play SWE-RL

Current LLM-based software engineering agents rely heavily on human-curated data (e.g., GitHub issues, pull requests) and environments (e.g., test suites), which limits their path to superintelligence. The paper introduces Self-play SWE-RL (SSR), a reinforcement learning framework that trains a single …

Yuxiang Wei et … 68 views 11 downloads
Artificial Intelligence

Training AI Co-Scientists Using Rubric Rewards

AI "co-scientists" (LLM-based assistants) can help researchers by generating detailed research plans from given goals and constraints. However, current models often produce plans that violate implicit requirements due to the open-ended nature of scientific planning and the lack of fast, …

Goel, Shashwat, et … 72 views 1 downloads