7 papers
IterResearch: Rethinking Long-Horizon Agents with Interaction Scaling
Guoxin Chen, Zile Qiao, Xuanzhong Chen +13
Recent advances in deep-research agents have shown promise for autonomous knowledge construction through dynamic reasoning over external sources. However, existing approaches rely…
MARS: Co-evolving Dual-System Deep Research via Multi-Agent Reinforcement Learning
Guoxin Chen, Zile Qiao, Wenqing Wang +10
Large Reasoning Models (LRMs) face two fundamental limitations: excessive token consumption when overanalyzing simple information processing tasks, and inability to access up-to-da…
WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents
Zile Qiao, Guoxin Chen, Xuanzhong Chen +13
Recent advances in deep-research systems have demonstrated the potential for AI agents to autonomously discover and synthesize knowledge from external sources. In this paper, we in…
From Data-Centric to Sample-Centric: Enhancing LLM Reasoning via Progressive Optimization
Xinjie Chen, Minpeng Liao, Guoxin Chen +4
Reinforcement learning with verifiable rewards (RLVR) has recently advanced the reasoning capabilities of large language models (LLMs). While prior work has emphasized algorithmic…
LLMs Can Achieve High-quality Simultaneous Machine Translation as Efficiently as Offline
Biao Fu, Minpeng Liao, Kai Fan +4
When the complete source sentence is provided, Large Language Models (LLMs) perform excellently in offline machine translation even with a simple prompt "Translate the following se…
Efficient and Adaptive Simultaneous Speech Translation with Fully Unidirectional Architecture
Biao Fu, Donglei Yu, Minpeng Liao +4
Simultaneous speech translation (SimulST) produces translations incrementally while processing partial speech input. Although large language models (LLMs) have showcased strong cap…