8 papers
Proxy OPD: On-Policy Distillation with Transferable Relative Proxy Update
Daocheng Fu, Rong Wu, Yu Yang +7
Post-training for large language models typically couples policy exploration with model optimization, hindering the reuse of high-reward behaviors from policy exploration. While on…
Quo Vadis, World Modeling?
Yu Yang, Xuemeng Yang, Licheng Wen +17
Continually improving agents require dynamic interaction feedback beyond static supervision, yet direct real-environment interaction is costly, slow, unsafe, and hard to paralleliz…
ShadowMerge: A Novel Poisoning Attack on Graph-Based Agent Memory via Relation-Channel Conflicts
Yang Luo, Zifeng Kang, Tiantian Ji +4
Graph-based agent memory is increasingly used in LLM agents to support structured long-term recall and multi-hop reasoning, but it also creates a new poisoning surface: an attacker…
The Agent's First Day: Benchmarking Learning, Exploration, and Scheduling in the Workplace Scenarios
Daocheng Fu, Jianbiao Mei, Rong Wu +7
The rapid evolution of Multi-modal Large Language Models (MLLMs) has advanced workflow automation; however, existing research mainly targets performance upper bounds in static envi…
UR-Bench: A Benchmark for Multi-Hop Reasoning over Ultra-High-Resolution Images
Siqi Li, Xinyu Cai, Jianbiao Mei +7
Recent multimodal large language models (MLLMs) show strong capabilities in visual-language reasoning, yet their performance on ultra-high-resolution imagery remains largely unexpl…
RE-Searcher: Robust Agentic Search with Goal-oriented Planning and Self-reflection
Daocheng Fu, Jianbiao Mei, Licheng Wen +11
Large language models (LLMs) excel at knowledge-intensive question answering and reasoning, yet their real-world deployment remains constrained by knowledge cutoff, hallucination,…
O-Searcher: A Searching-based Agent Model for Open-Domain Open-Ended Question Answering
Jianbiao Mei, Tao Hu, Daocheng Fu +11
Large Language Models (LLMs), despite their advancements, are fundamentally limited by their static parametric knowledge, hindering performance on tasks requiring open-domain up-to…
GDI-Bench: A Benchmark for General Document Intelligence with Vision and Reasoning Decoupling
Siqi Li, Yufan Shen, Xiangnan Chen +13
The rapid advancement of multimodal large language models (MLLMs) has profoundly impacted the document domain, creating a wide array of application scenarios. This progress highlig…