9 papers
CHIME: Credit-Aware Hierarchical Memory Evolution for Long-Horizon Agentic Planning
Yongshi Ye, Tian Lan, Feihu Jiang +7
Planning is a central capability that enables agents to decompose complex long-horizon tasks into manageable steps. Test-time search and training-based methods improve planning but…
Wuying-Browser-Agent: Real-World Centric Fundamental Long-Horizon Browser Agents
AIMAE Team, Tianxiang Chen, Yan Cheng +39
Browser agents perform well on short, clean demonstrations, but real deployment is fundamentally different: agents must sustain dozens of decisions on live websites while recoverin…
Search2Skill: Skill Distillation Beyond Knowledge Boundaries Via Rubric-Based Reinforcement Learning
Muyang Ye, Tian Lan, Feihu Jiang +10
Reusable skills, which encapsulate the procedural knowledge required to solve real-world professional tasks, offer LLM-based agents a path toward self-evolution in expert domains.…
Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design
Bin Zhu, Qianghuai Jia, Tian Lan +6
Deep research agents autonomously conduct open-ended investigations, integrating complex information retrieval with multi-step reasoning across diverse sources to solve real-world…
Table-as-Search: Formulate Long-Horizon Agentic Information Seeking as Table Completion
Tian Lan, Felix Henry, Bin Zhu +7
Current Information Seeking (InfoSeeking) agents struggle to maintain focus and coherence during long-horizon exploration, as tracking search states, including planning procedure a…
DeepWideSearch: Benchmarking Depth and Width in Agentic Information Seeking
Tian Lan, Bin Zhu, Qianghuai Jia +6
Current search agents fundamentally lack the ability to simultaneously perform \textit{deep} reasoning over multi-hop retrieval and \textit{wide}-scale information collection-a cri…
Agentic Lybic: Multi-Agent Execution System with Tiered Reasoning and Orchestration
Liangxuan Guo, Bin Zhu, Qingqian Tao +5
Autonomous agents for desktop automation struggle with complex multi-step tasks due to poor coordination and inadequate quality control. We introduce Agentic Lybic, a novel multi-a…
Benchmarking Gaslighting Attacks Against Speech Large Language Models
Jinyang Wu, Bin Zhu, Xiandong Zou +3
As Speech Large Language Models (Speech LLMs) become increasingly integrated into voice-based applications, ensuring their robustness against manipulative or adversarial input beco…
Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System
Haorui He, Yupeng Li, Bin Benjamin Zhu +3
State-of-the-art (SOTA) fact-checking systems combat misinformation by employing autonomous LLM-based agents to decompose complex claims into smaller sub-claims, verify each sub-cl…