Bo An

SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning

Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks

SMAN-Bench: A Cross-System Benchmark for Mobile Agents under Single- and Multi-path, Ambiguous, and Noisy Tasks

Generative Auto-Bidding in Large-Scale Auctions via Diffusion Completer-Aligner

MobileIPL: Enhancing Mobile Agents Thinking Process via Iterative Preference Learning

Vulnerable Agent Identification in Large-Scale Multi-Agent Reinforcement Learning

Enhancing Extreme Weather Forecasting via Dynamically Weighted MSE

Controlling Video Generation with Vision Language Models

PAC Reasoning: Controlling the Performance Loss for Efficient Reasoning

OSCAR: Orthogonal Stochastic Control for Alignment-Respecting Diversity in Flow Matching

Uncertainty-Aware Tree Search for Efficient LLM Reasoning

Offline Equilibrium Finding in Extensive-form Games: Datasets, Methods, and Analysis

DHEvo: Data-Algorithm Based Heuristic Evolution for Generalizable MILP Solving

Model-Heterogeneous Federated Prompt Learning

Solving Puzzles? Jailbreaking Multimodal Large Language Models!

FM-IRL: Flow-Matching for Reward Modeling and Policy Regularization in Reinforcement Learning

AgentOrchestra: Orchestrating Hierarchical Multi-Agent Intelligence with the Tool-Environment-Agent (TEA) Protocol

Fusing LLMs with Scientific Literature for Heuristic Discovery

MASLab: A Unified and Comprehensive Codebase for LLM-based Multi-Agent Systems

Anatomy of a Hybrid Mind: Deconstructing Hybrid Reasoning in Large Language Models

Adversarial Test Case Generation via Reinforcement Learning Extends Scaling Laws

REAR: Scalable Test-time Preference Realignment through Reward Decomposition

Value Shaping: Bias Reduction in Bellman Error for Deep Reinforcement Learning

StarDojo: Benchmarking Open-Ended Behaviors of Agentic Multimodal LLMs in Production–Living Simulations with Stardew Valley

Establishing Linear Surrogate Regret Bounds for Convex Smooth Losses via Convolutional Fenchel–Young Losses

Deciphering the Extremes: A Novel Approach for Pathological Long-tailed Recognition in Scientific Discovery

MF-LLM: Simulating Population Decision Dynamics via a Mean-Field Large Language Model Framework

Policy Regularization on Globally Accessible States in Cross-Dynamics Reinforcement Learning

Representation Surgery in Model Merging with Probabilistic Modeling

Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning

Policy Optimization under Imperfect Human Interactions with Agent-Gated Shared Autonomy

Group-in-Group Policy Optimization for LLM Agent Training

OPHR: Mastering Volatility Trading with Multi-Agent Deep Reinforcement Learning

Efficient Last-Iterate Convergence in Solving Extensive-Form Games

AgentStudio: A Toolkit for Building General Virtual Agents

Cradle: Empowering Foundation Agents towards General Computer Control

Let's Revise Step-by-Step: A Unified Local Search Framework for Code Generation with LLMs

Incentivizing LLMs to Self-Verify Their Answers

Improving Reward Models with Proximal Policy Exploration for Preference-Based Reinforcement Learning

Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning

A Closer Look at Backdoor Attacks on CLIP

Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation

Outward Odyssey: Improving Reward Models with Proximal Policy Exploration for Preference-Based Reinforcement Learning

A Closer Look at Backdoor Attacks on CLIP

Conformal Prediction for Deep Classifier via Truncating

Solving Urban Network Security Games: Learning Platform, Benchmark, and Challenge for AI Research

ASOR: Anchor State Oriented Regularization for Policy Optimization under Dynamics Shift

Cradle: Empowering Foundation Agents towards General Computer Control

Dual-Head Knowledge Distillation: Enhancing Logits Utilization with an Auxiliary Head

MEMO: Memory-Guided and Emotion-Aware Talking Video Generation

In-Context Learning for Games

Improving Ordinal Conformal Prediction by Stepwise Adaptive Posterior Alignment

Guiding VLM Agents with Process Rewards at Inference Time for GUI Navigation

Efficient LLM Alignment via Hierarchical Coarse-to-Fine Refinement

Offline Equilibrium Finding in Extensive-form Games: Datasets, Methods, and Analysis

Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning

Computing Ex Ante Equilibrium in Heterogeneous Zero-Sum Team Games