吴奕

2024

人工智能时代高校网络舆情治理的机遇、挑战与对策

《江苏大学学报：社会科学版》，Vol. 26, No. 4

下载原文

2023

改革开放以来党对高校领导的实践探索

《中国高等教育》

2026

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation

arXiv preprint

2026

ML-DCN: Masked Low-Rank Deep Crossing Network Towards Scalable Ads Click-through Rate Prediction at Pinterest

arXiv preprint

2026

Learning to Alleviate Familiarity Bias in Video Recommendation

arXiv preprint

2026

Knowledge-Graph Paths as Intermediate Supervision for Self-Evolving Search Agents

arXiv preprint

2026

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents

arXiv preprint

2026

Code-to-Harness: Distilling Black-Box Optimizers from Self-Play

arXiv preprint

2026

Tournament-GRPO: Group-Wise Tournament Rewards for Reinforcement Learning in Open-Ended Long-Form Generation

arXiv preprint

2026

Verifiable Process Rewards for Agentic Reasoning

arXiv preprint

2026

ExVerus: Verus Proof Repair via Counterexample Reasoning

arXiv preprint

2026

Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models

arXiv preprint

2026

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models

arXiv preprint

2026

Perceive, Interact, Reason: Building Tool-Augmented Visual Agents for Spatial Reasoning

arXiv preprint

2026

Deep Research as Rubric for Reinforcement Learning

arXiv preprint

2026

RING: Retrieval-Internalized Generation for Continual Large-Scale Knowledge Injection

arXiv preprint

2026

Harness-Search: Guiding Long-Horizon Search through Multi-Agent Coordination

arXiv preprint

2026

MAGE: Meta-Reinforcement Learning for Language Agents toward Strategic Exploration and Exploitation

arXiv preprint

2026

LLMs Are Not Good Strategists, Yet Memory-Enhanced Agency Boosts Reasoning

arXiv preprint

2026

Self-Evolving Recommendation System: End-To-End Autonomous Model Optimization With LLM Agents

arXiv preprint

2026

Lightweight Ranking Heads: Accelerating Multi-Task Experimentation in Production Recommender Systems

arXiv preprint

2026

QP-OneModel: A Unified Generative LLM for Multi-Task Query Understanding in Xiaohongshu Search

arXiv preprint

2026

SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utility

arXiv preprint

2026

Aligning Large Language Models with Searcher Preferences

arXiv preprint

2026

EGM: Efficient Visual Grounding Language Models

arXiv preprint

2026

Focus on the Core: Empowering Diffusion Large Language Models by Self-Contrast

arXiv preprint

2026

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models

arXiv preprint

2026

ReaLB: Real-Time Load Balancing for Multimodal MoE Inference

arXiv preprint

2026

HTPO: Towards Exploration-Exploitation Balanced Policy Optimization via Hierarchical Token-level Objective Control

arXiv preprint

2026

Multi-Image Visual Token Pruning in Large Visual Language Models

arXiv preprint

2026

UnityMAS-O: A General RL Optimization Framework for LLM-Based Multi-Agent Systems

arXiv preprint

2026

NavCMPO: Critic-Guided MeanFlow Policy Optimization for Adaptive Navigation

arXiv preprint

2026

Fetch-then-Explore: Decoupling Selection from Extraction over a Persistent Workspace for Search Agents

arXiv preprint

2026

Humanoid Badminton: Learning Dynamic Racket Skills from Limited Human Motion Data

arXiv preprint

2026

AREAL-DTA: Dynamic Tree Attention for Efficient Reinforcement Learning of Large Language Models

arXiv preprint

2026

Analyzing and Mitigating Cost-Inefficient Behaviors in Coding Agents

arXiv preprint

2026

Parason: Revealing Subtask and Trial Parallelism in LLM Reasoning

arXiv preprint

2026

Self-Compression of Chain-of-Thought via Multi-Agent Reinforcement Learning

arXiv preprint

2026

Building Multi-Task Agentic LLMs via Two-Phase Distillation

arXiv preprint

2026

OASES: Outcome-Aligned Search-Evaluation Co-Training for Agentic Search

arXiv preprint

2026

JADE: Bridging the Strategic-Operational Gap in Dynamic Agentic RAG

arXiv preprint

2026

SSKG Hub: An Expert-Guided Platform for LLM-Empowered Sustainability Standards Knowledge Graphs

arXiv preprint

2026

From Self-Evolving Synthetic Data to Verifiable-Reward RL: Post-Training Multi-turn Interactive Tool-Using Agents

arXiv preprint

2026

What Should Embodied Agents Remember? Benchmarking and Evaluating Memory Modality for Embodied Agents

arXiv preprint

2025

TENET: One Step Toward Test-Driven Development for Repository-Level Code Generation

arXiv preprint

2025

Optimizing Generative Ranking Relevance via Reinforcement Learning in Xiaohongshu Search

arXiv preprint

DOI

2025

Reflective VLM Planning for Dual-Arm Desktop Cleaning: Bridging Open-Vocabulary Perception and Precise Manipulation

arXiv preprint

2025

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

arXiv preprint

2025

D3P: Dynamic Denoising Diffusion Policy via Reinforcement Learning

arXiv preprint

2025

Toward Real-World Cooperative and Competitive Soccer with Quadrupedal Robot Teams

arXiv preprint

2025

RealBench: A Chinese Multi-image Understanding Benchmark Close to Real-world Scenarios

arXiv preprint

2025

Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL

arXiv preprint

2025

Learning Strategic Language Agents in the Werewolf Game with Iterative Latent Space Policy Optimization

arXiv preprint

2025

QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation

arXiv preprint

2025

DecEx-RAG: Boosting Agentic Retrieval-Augmented Generation with Decision and Execution Optimization via Process Supervision

arXiv preprint

2025

Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspective

arXiv preprint

2025

VS-Bench: Evaluating VLMs for Strategic Abilities in Multi-Agent Environments

arXiv preprint

2025

R3A: Reinforced Reasoning for Relevance Assessment for RAG in User-Generated Content Platforms

arXiv preprint

2025

ESGenius: Benchmarking LLMs on Environmental, Social, and Governance (ESG) and Sustainability Knowledge

arXiv preprint

DOI

2025

Qilin: A Multimodal Information Retrieval Dataset with APP-level User Sessions

arXiv preprint

2025

What Can RL Bring to VLA Generalization? An Empirical Study

arXiv preprint

2025

RedOne: Revealing Domain-specific LLM Post-Training in Social Networking Services

arXiv preprint

2025

SelfRACG: Enabling LLMs to Self-Express and Retrieve for Code Generation

arXiv preprint

2025

How Far Are We from Optimal Reasoning Efficiency?

arXiv preprint

2025

Extending Test-Time Scaling: A 3D Perspective with Context, Batch, and Turn

arXiv preprint

2025

Fine-tuning Diffusion Policies with Backpropagation Through Diffusion Timesteps

arXiv preprint

2025

AReaL-Hex: Accommodating Asynchronous RL Training over Heterogeneous GPUs

arXiv preprint

2025

MMESGBench: Pioneering Multimodal Understanding and Complex Reasoning Benchmark for ESG Tasks

arXiv preprint

2025

ACT: Automated Constraint Targeting for Multi-Objective Recommender Systems

arXiv preprint

2025

SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment

arXiv preprint

2025

RAG-IGBench: Innovative Evaluation for RAG-based Interleaved Generation in Open-domain Question Answering

arXiv preprint

2025

PaRT: Enhancing Proactive Social Chatbots with Personalized Real-Time Retrieval

arXiv preprint

2025

AI Realtor: Towards Grounded Persuasive Language Generation for Automated Copywriting

arXiv preprint

2024

SELP: Generating Safe and Efficient Task Plans for Robot Agents with Large Language Models

arXiv preprint

2024

Learned Ranking Function: From Short-term Behavior Predictions to Long-term User Satisfaction

arXiv preprint

2024

Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study

arXiv preprint

2024

On Designing Effective RL Reward at Training Time for LLM Reasoning

arXiv preprint

2024

MESA: Cooperative Meta-Exploration in Multi-Agent Learning through Exploiting State-Action Space Structure

arXiv preprint

2024

NPC: Neural Predictive Control for Fuel-Efficient Autonomous Trucks

arXiv preprint

DOI

2024

Offline Reinforcement Learning for LLM Multi-Step Reasoning

arXiv preprint

2024

Leveraging Symmetry in RL-based Legged Locomotion Control

arXiv preprint

DOI

2024

What Matters in Learning A Zero-Shot Sim-to-Real RL Policy for Quadrotor Control? A Comprehensive Study

arXiv preprint

2024

Multi-UAV Formation Control with Static and Dynamic Obstacle Avoidance via Reinforcement Learning

arXiv preprint

2024

ICPL: Few-shot In-context Preference Learning via LLMs

arXiv preprint

2024

ESP: Extro-Spective Prediction for Long-term Behavior Reasoning in Emergency Scenarios

arXiv preprint

2024

ReaL: Efficient RLHF Training of Large Language Models with Parameter Reallocation

arXiv preprint

2024

FlightBench: Benchmarking Learning-based Methods for Ego-vision-based Quadrotors Navigation

arXiv preprint

DOI

2024

Neural Internal Model Control: Learning a Robust Control Policy via Predictive Error Feedback

arXiv preprint

2024

Long-horizon Locomotion and Manipulation on a Quadrupedal Robot with Large Language Models

arXiv preprint

2023

Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased

arXiv preprint

2023

Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game

arXiv preprint

2023

Accelerate Multi-Agent Reinforcement Learning in Zero-Sum Games with Subgame Curriculum Learning

arXiv preprint

2023

Learning Agile Bipedal Motions on a Quadrupedal Robot

arXiv preprint

2023

OmniDrones: An Efficient and Flexible Platform for Reinforcement Learning in Drone Control

arXiv preprint

2023

Automatic Truss Design with Reinforcement Learning

arXiv preprint

2023

Asynchronous Multi-Agent Reinforcement Learning for Efficient Real-Time Multi-Robot Cooperative Exploration

arXiv preprint

2023

How Effective Are Neural Networks for Fixing Security Vulnerabilities

arXiv preprint

DOI

2023

Differentiable Arbitrating in Zero-sum Markov Games

arXiv preprint

2023

SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores

arXiv preprint

2023

Grounding Object Relations in Language-Conditioned Robotic Manipulation with Semantic-Spatial Reasoning

arXiv preprint

2023

LLM-Powered Hierarchical Language Agent for Real-time Human-AI Coordination

arXiv preprint

2023

LAGOON: Language-Guided Motion Control

arXiv preprint

2023

Fictitious Cross-Play: Learning Global Nash Equilibrium in Mixed Cooperative-Competitive Games

arXiv preprint

2023

Iteratively Learn Diverse Strategies with State Distance Information

arXiv preprint

2022

Learning Design and Construction with Varying-Sized Materials via Prioritized Memory Resets

arXiv preprint

2022

Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning

arXiv preprint

2022

AlphaSnake: Policy Iteration on a Nondeterministic NP-hard Markov Decision Process

arXiv preprint

2021

Learning to Design and Construct Bridge without Blueprint

arXiv preprint

2021

A Benchmark for Low-Switching-Cost Reinforcement Learning

arXiv preprint

2021

Multi-Agent Vulnerability Discovery for Autonomous Driving with Hazard Arbitration Reward

arXiv preprint

2019

Fairness in Recommendation Ranking through Pairwise Comparisons

arXiv preprint