arXiv:2510.26243v1 Announce Type: cross Abstract: Controlling specific behaviors in large language models while preserving their general capabilities is a central challenge for safe and reliable artificial intelligence deployment. Current steering methods, such as vector addition and directional ablation, are constrained within a two-dimensional subspace defined by the activation and feature direction, making them sensitive to […]
Integrated Information Theory: A Consciousness-First Approach to What Exists
arXiv:2510.25998v1 Announce Type: new Abstract: This overview of integrated information theory (IIT) emphasizes IIT’s “consciousness-first” approach to what exists. Consciousness demonstrates to each of us that something exists–experience–and reveals its essential properties–the axioms of phenomenal existence. IIT formulates these properties operationally, yielding the postulates of physical existence. To exist intrinsically or absolutely, an entity must […]
Can Agent Conquer Web? Exploring the Frontiers of ChatGPT Atlas Agent in Web Games
arXiv:2510.26298v1 Announce Type: cross Abstract: OpenAI’s ChatGPT Atlas introduces new capabilities for web interaction, enabling the model to analyze webpages, process user intents, and execute cursor and keyboard inputs directly within the browser. While its capacity for information retrieval tasks has been demonstrated, its performance in dynamic, interactive environments remains less explored. In this study, […]
Revealing Multimodal Causality with Large Language Models
arXiv:2509.17784v2 Announce Type: replace-cross Abstract: Uncovering cause-and-effect mechanisms from data is fundamental to scientific progress. While large language models (LLMs) show promise for enhancing causal discovery (CD) from unstructured data, their application to the increasingly prevalent multimodal setting remains a critical challenge. Even with the advent of multimodal LLMs (MLLMs), their efficacy in multimodal CD […]
From Amateur to Master: Infusing Knowledge into LLMs via Automated Curriculum Learning
arXiv:2510.26336v1 Announce Type: cross Abstract: Large Language Models (LLMs) excel at general tasks but underperform in specialized domains like economics and psychology, which require deep, principled understanding. To address this, we introduce ACER (Automated Curriculum-Enhanced Regimen) that transforms generalist models into domain experts without sacrificing their broad capabilities. ACER first synthesizes a comprehensive, textbook-style curriculum […]
AutoSurvey2: Empowering Researchers with Next Level Automated Literature Surveys
arXiv:2510.26012v1 Announce Type: new Abstract: The rapid growth of research literature, particularly in large language models (LLMs), has made producing comprehensive and current survey papers increasingly difficult. This paper introduces autosurvey2, a multi-stage pipeline that automates survey generation through retrieval-augmented synthesis and structured evaluation. The system integrates parallel section generation, iterative refinement, and real-time retrieval […]
Reinforcement Learning for Pollution Detection in a Randomized, Sparse and Nonstationary Environment with an Autonomous Underwater Vehicle
arXiv:2510.26347v1 Announce Type: cross Abstract: Reinforcement learning (RL) algorithms are designed to optimize problem-solving by learning actions that maximize rewards, a task that becomes particularly challenging in random and nonstationary environments. Even advanced RL algorithms are often limited in their ability to solve problems in these conditions. In applications such as searching for underwater pollution […]
Large Language Models Report Subjective Experience Under Self-Referential Processing
arXiv:2510.24797v2 Announce Type: replace-cross Abstract: Large language models sometimes produce structured, first-person descriptions that explicitly reference awareness or subjective experience. To better understand this behavior, we investigate one theoretically motivated condition under which such reports arise: self-referential processing, a computational motif emphasized across major theories of consciousness. Through a series of controlled experiments on GPT, […]
Human-in-the-loop Online Rejection Sampling for Robotic Manipulation
arXiv:2510.26406v1 Announce Type: cross Abstract: Reinforcement learning (RL) is widely used to produce robust robotic manipulation policies, but fine-tuning vision-language-action (VLA) models with RL can be unstable due to inaccurate value estimates and sparse supervision at intermediate steps. In contrast, imitation learning (IL) is easy to train but often underperforms due to its offline nature. […]
Large Language Model-assisted Autonomous Vehicle Recovery from Immobilization
arXiv:2510.26023v1 Announce Type: new Abstract: Despite significant advancements in recent decades, autonomous vehicles (AVs) continue to face challenges in navigating certain traffic scenarios where human drivers excel. In such situations, AVs often become immobilized, disrupting overall traffic flow. Current recovery solutions, such as remote intervention (which is costly and inefficient) and manual takeover (which excludes […]