Inquiring Lines
A library of AI research read for its standing questions: the papers, the synthesis notes drawn from them, and the inquiring lines that run across them. Below, the papers featured lately, each with the lines it touches and the notes around it. Paste a paper of your own to see where it sits.
On the site·Featured Sep 27·Evolution
Recursive self-improvement is becoming increasingly vital for autonomous AI agents, where progress hinges on discovering high-value solutions across complex domains. The driver of this process is effective exploration, however, managing and improving exploration strategies remains a major bottleneck.
On the site·Featured Sep 27·Evolution
AI agents operate in persistent environments where early state changes can influence decisions far into the future. Unlike conventional language-model interactions, agent behavior is mediated through a shared state that is repeatedly modified and reused across long-horizon workflows. Current safety benchmarks often fail to capture these cumulative risks because they focus on short, static tasks.
On the site·Featured Sep 27·Memory
Language models may need to internalize information that arrives over time and retain it through many subsequent updates. To study this challenge, we introduce long-horizon memorization, a setting in which a model learns 100 query-answer tasks through continual supervised fine-tuning without retaining earlier training examples or receiving task identifiers at inference.
New research·Featured Sep 27·Psychology Therapy Practice
Conversational AI systems can pose safety risks to their users such as hallucination, sycophancy, overconfidence, and anthropomorphism, but these risks are difficult for users to detect during everyday use. We introduce Safety Nudges, a browser-based tool that provides lightweight, in situ flags when concerning behavior is detected in chatbot conversations. We evaluated Safety Nudges in a two-week field study with 45 frequent chatbot users, collecting interaction logs, surveys, and feedback on individual nudges.
New research·Featured Sep 27·Personas Personality
Procedural character generation aims to populate games, simulations, and other virtual worlds with diverse characters. Large language models (LLMs) offer a promising foundation for scaling this task. However, LLM-based procedural character generation remains at an early stage: existing methods either generate characters directly or adapt profiles retrieved from persona banks.
New research·Featured Sep 27·Argumentation
Large Language Models (LLMs) are increasingly deployed as argumentative agents in persuasive dialogues, necessitating rigorous evaluation of their debating competence relative to human interlocutors. In this study, we focus on character attacks (ad hominem arguments), traditionally dismissed as fallacies, which play a pivotal role in political persuasive dialogues where ethos often rivals propositional content.
New research·Featured Sep 27·Psychology Therapy Practice
Increasing numbers of people now routinely interact with large language models (LLMs) across many aspects of life, including in the workplace, educational settings, and for personal activities. The pace at which these tools have been adopted across society in recent years has led to substantial shifts in the ways in which people approach tasks and access information and advice.
On the site·Featured Sep 27·Evolution
As AI agents become participants in the development of their successors, they reshape both the production of intelligence and the role of human researchers. We introduce Atria Dawn Preview, a foundation agentic language model designed for scientific research and engineering workflows, with the goal of expanding the frontier of agent productivity in the real world.
On the site·Featured Sep 27·Reinforcement Learning
Automating empirical research is a long-standing direction of AI. Recent automatic research (AutoResearch) agents bring this goal within reach, as modern LLMs show the capability to independently implement solutions and learn from the execution outcomes. Behind these gains, post-training (especially RL) plays a central role.
On the site·Featured Sep 27·Reasoning Architectures
We introduce BDH-CQ, a reasoning model that combines in-context learning with recurrent latent reasoning. Inputs presented at inference time continuously update the model's recurrent memory; the model then solves a query through iterative computation in a high-dimensional latent space, without verbalizing its intermediate reasoning.
Ways in: Inquiring lines · Topics · Papers · Featured · Knowledge graph