6 papers
Connect the Dots: Training LLMs for Long-Lifecycle Agents with Cross-Domain Generalization Via Reinforcement Learning
Yanxi Chen, Weijie Shi, Yuexiang Xie +6
This work presents a general framework for training large language models (LLMs) to "Connect the Dots" (CoD), a meta-capability required by long-lifecycle agents: as an LLM-based A…
TCOD: Exploring Temporal Curriculum in On-Policy Distillation for Multi-turn Autonomous Agents
Jiaqi Wang, Wenhao Zhang, Weijie Shi +2
On-policy distillation (OPD) has shown strong potential for transferring reasoning ability from frontier or domain-specific models to smaller students. While effective on static si…
Perception, Understanding and Reasoning, A Multimodal Benchmark for Video Fake News Detection
Cui Yakun, Peng Qi, Fushuo Huo +6
The advent of multi-modal large language models (MLLMs) has greatly advanced research on video fake news detection (VFND) tasks. Existing benchmarks typically focus on the detectio…
Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving
Chuxue Cao, Mengze Li, Juntao Dai +7
Large language models (LLMs) have shown promising first-order logic (FOL) reasoning capabilities with applications in various areas. However, their effectiveness in complex mathema…
Measuring Hong Kong Massive Multi-Task Language Understanding
Chuxue Cao, Zhenghao Zhu, Junqi Zhu +6
Multilingual understanding is crucial for the cross-cultural applicability of Large Language Models (LLMs). However, evaluation benchmarks designed for Hong Kong's unique linguisti…
AgentMonitor: A Plug-and-Play Framework for Predictive and Secure Multi-Agent Systems
Chi-Min Chan, Jianxuan Yu, Weize Chen +6
The rapid advancement of large language models (LLMs) has led to the rise of LLM-based agents. Recent research shows that multi-agent systems (MAS), where each agent plays a specif…