Jianye Hao

PACE: Unleashing the Power of Code Embeddings to Boost AutoML Agents

Gangyi Zhao, Hebin Liang, Hongyao Tang, Yi Ma et autres

Large Language Model (LLM)-driven AutoML agents have shown strong capabilities in constructing end-to-end machine learning pipelines. However, their effectiveness is limited by costly execution-based feedback, which can make the search for high-quality solutions inefficient under restricted computational budgets. We propose PACE (Pre-execution …

cn (code pays fourni par la source)

Unveiling the Entropy Dynamics of Chain-of-Thought Reasoning

Ting Xu, Xu He, Yupu Lu, Jiankai Sun et autres

This paper investigates the entropy dynamics of Chain-of-Thought (CoT) and uncovers a consistent two-phase structure: an Uncertainty Region of exploration transitioning sharply to a Confidence Region of convergence. We demonstrate that the Confidence Region possesses two critical properties: 1) High Reliability -- …

Unveiling the Entropy Dynamics of Chain-of-Thought Reasoning

Ting Xu, Xu He, Yupu Lu, Jiankai Sun et autres

This paper investigates the entropy dynamics of Chain-of-Thought (CoT) and uncovers a consistent two-phase structure: an Uncertainty Region of exploration transitioning sharply to a Confidence Region of convergence. We demonstrate that the Confidence Region possesses two critical properties: 1) High Reliability -- …

Towards A Unified Policy Abstraction Theory and Representation Learning Approach in Markov Decision Processes

Min Zhang, Hongyao Tang, Jianye Hao, Zheng Yan

In intelligent decision-making systems, how policy is represented and optimized is a fundamental problem. The root challenge stems from the large scale and the high complexity of policy space. Towards a desirable surrogate policy space, recent policy representations in a low-dimensional latent …

cn (code pays fourni par la source)

A Survey on Vision--Language--Action Models for Embodied AI

Yueen Ma, Zixing Song, Yuzheng Zhuang, Jianye Hao et autres

Embodied AI is widely recognized as a cornerstone of artificial general intelligence (AGI) because it involves controlling embodied agents to perform tasks in the physical world. Building on the success of large language models (LLMs) and vision-language models (VLMs), a new category …

hk, gb, cn (code pays fourni par la source)

A robot operating system framework for using large language models in embodied AI

Christopher E. Mower, Yuhui Wan, Hongzhan Yu, Antoine Grosnit et autres

gb, de, ch (code pays fourni par la source)

Signaling-Driven Incentive Communication for Enhanced Multiagent Reinforcement Learning in Dynamic Environments

Kexing Peng, Pengyi Li, Jianye Hao

Centralized training and decentralized execution (CTDE) frameworks in cooperative multiagent reinforcement learning (MARL) address nonstationarity and scalability in dynamic environments. However, coordination among agents remains challenging due to limited observability, often leading to inefficient exploration of policy spaces and increased communication overhead. …

cn (code pays fourni par la source)

Hands-on LLM-based Agents: A Tutorial for General Audiences

Shuyue Hu, Siying Ren, Yang Chen, Chunjiang Mu et autres

This tutorial is aimed at general audiences interested in large language model (LLM) agents. No coding skill or prior knowledge of LLMs, machine learning, or artificial intelligence is required. It provides a gentle yet comprehensive introduction for newcomers, offering a broad, intuitive …

cn (code pays fourni par la source)

EVLP:Learning Unified Embodied Vision-Language Planner with Reinforced Supervised Fine-Tuning

Shiguang Wu, Dafeng Chi, Yuzheng Zhuang, Xingyue Quan et autres

In complex embodied long-horizon manipulation tasks, effective task decomposition and execution require synergistic integration of textual logical reasoning and visual-spatial imagination to ensure efficient and accurate operation. Current methods fail to adopt a unified generation framework for multimodal planning, lead to inconsistent …

The rise and potential opportunities of large language model agents in bioinformatics and biomedicine

Yihang Xiao, Zhijie Bao, Jianye Hao, Jiajie Peng

Large language model (LLM) agents have demonstrated remarkable potential in the fields of bioinformatics and biomedicine. This paper reviews the technical foundations of LLM agents, including their core architecture, key technologies, and collaborative modes. We explore the applications of LLM agents in …

cn, us (code pays fourni par la source)

ET-Plan-Bench: Embodied Task-level Planning Benchmark Towards Spatial-Temporal Cognition with Foundation Models

Lingfeng Zhang, Yuening Wang, Hongjian Gu, Atia Hamidizadeh et autres

Recent advancements in Large Language Models (LLMs) have catalyzed numerous efforts to apply these technologies to embodied tasks, with a particular focus on high-level task planning and task decomposition. LLMs face challenges in understanding the physical world, especially regarding spatial, temporal, and …

se (code pays fourni par la source)

More than A Point: Capturing Uncertainty with Adaptive Affordance Heatmaps for Spatial Grounding in Robotic Tasks

Xinyu Shao, Pengwei Xie, Kaiwen Zhou, Yuzheng Zhuang et autres

Many language-guided robotic systems rely on collapsing spatial reasoning into discrete points, making them brittle to perceptual noise and semantic ambiguity. To address this challenge, we propose RoboMAP, a framework that represents spatial targets as continuous, adaptive affordance heatmaps. This dense representation …