6 papers · 1 filter
AgentIF-OneDay: A Task-level Instruction-Following Benchmark for General AI Agents in Daily Scenarios
Kaiyuan Chen, Qimin Wu, Taiyu Hou +42
The capacity of AI agents to effectively handle tasks of increasing duration and complexity continues to grow, demonstrating exceptional performance in coding, deep research, and c…
Beyond the Black Box: A Survey on the Theory and Mechanism of Large Language Models
Zeyu Gan, Ruifeng Ren, Wei Yao +9
The rapid emergence of Large Language Models (LLMs) has precipitated a profound paradigm shift in Artificial Intelligence, delivering monumental engineering successes that increasi…
EcoLANG: Efficient and Effective Agent Communication Language Induction for Social Simulation
Xinyi Mou, Chen Qian, Wei Liu +2
Large language models (LLMs) have demonstrated an impressive ability to role-play humans and replicate complex social dynamics. While large-scale social simulations are gaining inc…
NOVER: Incentive Training for Language Models via Verifier-Free Reinforcement Learning
Wei Liu, Siya Qi, Xinyu Wang +3
Recent advances such as DeepSeek R1-Zero highlight the effectiveness of incentive training, a reinforcement learning paradigm that computes rewards solely based on the final answer…
Aligning Large Language Models to Follow Instructions and Hallucinate Less via Effective Data Filtering
Shuzheng Si, Haozhe Zhao, Gang Chen +9
Training LLMs on data containing unfamiliar knowledge during the instruction tuning stage can encourage hallucinations. To address this challenge, we introduce NOVA, a novel framew…
Practical token pruning for foundation models in few-shot conversational virtual assistant systems
Haode Qi, Cheng Qian, Jian Ni +6
In an enterprise Virtual Assistant (VA) system, intent classification is the crucial component that determines how a user input is handled based on what the user wants. The VA syst…