activity
20242026
collaborators
Showing cs.AIShow all

6 papers · 1 filter

cs.AI2026

Foundation Protocol: A Coordination Layer for Agentic Society

Bang Liu, Yongfeng Gu, Jiayi Zhang +26

Autonomous agents are moving from tools into a layer of social infrastructure: they browse, purchase, deploy software, manage systems, and increasingly interact with one another. A…

cs.AI2026

AutoWebWorld: Synthesizing Infinite Verifiable Web Environments via Finite State Machines

Yifan Wu, Yiran Peng, Yiyu Chen +12

The performance of autonomous Web GUI agents heavily relies on the quality and quantity of their training data. However, a fundamental bottleneck persists: collecting interaction t…

cs.AI2026

ReCode: Unify Plan and Action for Universal Granularity Control

Zhaoyang Yu, Jiayi Zhang, Huixue Su +9

Real-world tasks require decisions at varying granularities, and humans excel at this by leveraging a unified cognitive representation where planning is fundamentally understood as…

cs.AI2025

AutoEnv: Automated Environments for Measuring Cross-Environment Agent Learning

Jiayi Zhang, Yiran Peng, Fanqi Kong +12

Humans naturally adapt to diverse environments by learning underlying rules across worlds with different dynamics, observations, and reward structures. In contrast, existing agents…

cs.AI2025

Trainable Dynamic Mask Sparse Attention

Jingze Shi, Yifan Wu, Yiran Peng +4

The increasing demand for long-context modeling in large language models (LLMs) is bottlenecked by the quadratic complexity of the standard self-attention mechanism. The community…

cs.AI2025

Concise Reasoning, Big Gains: Pruning Long Reasoning Trace with Difficulty-Aware Prompting

Yifan Wu, Jingze Shi, Bingheng Wu +4

Existing chain-of-thought (CoT) distillation methods can effectively transfer reasoning abilities to base models but suffer from two major limitations: excessive verbosity of reaso…