30 citations · 108 across the 57 of their papers we have counts for
44 papers · 1 filter
Demystifying On-Policy Distillation: Roles, Pathologies, and Regulations
Rui Wang, Hongru Wang, Yi Chen +4
On-policy distillation (OPD) has become a key paradigm in LLM post-training, yet its training dynamics remain poorly understood. We present a systematic study examining the role, p…
DeepSearch-World: Self-Distillation for Deep Search Agents in a Verifiable Environment
Xinyu Geng, Xuanhua He, Sixiang Chen +7
Training tool-use agents to improve from their own experience remains challenging, as supervised fine-tuning relies on fixed teacher-distilled trajectories, while sparse-reward rei…
PatchWorld: Gradient-Free Optimization of Executable World Models for Agent Environments
Jiaxin Bai, Yue Guo, Yifei Dong +13
World models for interactive text agents must typically be learned from observation-action trajectories alone. Specifically, the environment returns text observations after each ac…
GeoBrowse: A Geolocation Benchmark for Agentic Tool Use with Expert-Annotated Reasoning Traces
Xinyu Geng, Yanjing Xiao, Yuyang Zhang +5
Deep research agents integrate fragmented evidence through multi-step tool use. BrowseComp offers a text-only testbed for such agents, but existing multimodal benchmarks rarely req…
Verified Critical Step Optimization for LLM Agents
Mukai Li, Qingcheng Zeng, Tianqing Fang +5
As large language model agents tackle increasingly complex long-horizon tasks, effective post-training becomes critical. Prior work faces fundamental challenges: outcome-only rewar…
WebAggregator: Enhancing Compositional Reasoning Capabilities of Deep Research Agent Foundation Models
Rui Wang, Ce Zhang, Jun-Yu Ma +10
The hallmark of Deep Research agents lies in compositional reasoning, the capacity to aggregate distributed, heterogeneous information into coherent logical insights. However, curr…
UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression
Chenlong Deng, Zhisong Zhang, Kelong Mao +6
Large language models are increasingly capable of handling long-context inputs, but the memory overhead of key-value (KV) cache remains a major bottleneck for general-purpose deplo…
Recall with Reasoning: Chain-of-Thought Distillation for Mamba's Long-Context Memory and Extrapolation
Junyu Ma, Tianqing Fang, Zhisong Zhang +3
Mamba's theoretical infinite-context potential is limited in practice when sequences far exceed training lengths. This work explores unlocking Mamba's long-context memory ability b…
InComeS: Integrating Compression and Selection Mechanisms into LLMs for Efficient Model Editing
Shuaiyi Li, Zhisong Zhang, Yang Deng +6
Although existing model editing methods perform well in recalling exact edit facts, they often struggle in complex scenarios that require deeper semantic understanding rather than…
WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollback
Minda Hu, Tianqing Fang, Jianshu Zhang +7
Web agents powered by Large Language Models (LLMs) show promise for next-generation AI, but their limited reasoning in uncertain, dynamic web environments hinders robust deployment…
WebEvolver: Enhancing Web Agent Self-Improvement with Coevolving World Model
Tianqing Fang, Hongming Zhang, Zhisong Zhang +4
Agent self-improvement, where the backbone Large Language Model (LLM) of the agent are trained on trajectories sampled autonomously based on their own policies, has emerged as a pr…
WebRollback: Enhancing Web Agents with Explicit Rollback Mechanisms
Zhisong Zhang, Tianqing Fang, Kaixin Ma +4
With recent advancements in large language models, web agents have been greatly improved. However, dealing with complex and dynamic web environments requires more advanced planning…
Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models
Zhisong Zhang, Yan Wang, Xinting Huang +5
Large language models have shown remarkable performance across a wide range of language tasks, owing to their exceptional capabilities in context modeling. The most commonly used m…
ConKE: Conceptualization-Augmented Knowledge Editing in Large Language Models for Commonsense Reasoning
Liyu Zhang, Weiqi Wang, Tianqing Fang +1
Knowledge Editing (KE) aims to adjust a Large Language Model's (LLM) internal representations and parameters to correct inaccuracies and improve output consistency without incurrin…
OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization
Hongliang He, Wenlin Yao, Kaixin Ma +5
The rapid development of large language and multimodal models has sparked significant interest in using proprietary models, such as GPT-4o, to develop autonomous agents capable of…
Concept-Reversed Winograd Schema Challenge: Evaluating and Improving Robust Reasoning in Large Language Models via Abstraction
Kaiqiao Han, Tianqing Fang, Zhaowei Wang +2
While Large Language Models (LLMs) have showcased remarkable proficiency in reasoning, there is still a concern about hallucinations and unreliable reasoning issues due to semantic…
CLR-Fact: Evaluating the Complex Logical Reasoning Capability of Large Language Models over Factual Knowledge
Tianshi Zheng, Jiaxin Bai, Yicheng Wang +4
While large language models (LLMs) have demonstrated impressive capabilities across various natural language processing tasks by acquiring rich factual knowledge from their broad t…
On the Role of Entity and Event Level Conceptualization in Generalizable Reasoning: A Survey of Tasks, Methods, Applications, and Future Directions
Weiqi Wang, Tianqing Fang, Haochen Shi +8
Conceptualization, a fundamental element of human cognition, plays a pivotal role in human generalizable reasoning. Generally speaking, it refers to the process of sequentially abs…
MIND: Multimodal Shopping Intention Distillation from Large Vision-language Models for E-commerce Purchase Understanding
Baixuan Xu, Weiqi Wang, Haochen Shi +12
Improving user experience and providing personalized search results in E-commerce platforms heavily rely on understanding purchase intention. However, existing methods for acquirin…
IntentionQA: A Benchmark for Evaluating Purchase Intention Comprehension Abilities of Language Models in E-commerce
Wenxuan Ding, Weiqi Wang, Sze Heng Douglas Kwok +11
Enhancing Language Models' (LMs) ability to understand purchase intentions in E-commerce scenarios is crucial for their effective assistance in various downstream tasks. However, p…
Complex Reasoning over Logical Queries on Commonsense Knowledge Graphs
Tianqing Fang, Zeming Chen, Yangqiu Song +1
Event commonsense reasoning requires the ability to reason about the relationship between events, as well as infer implicit context underlying that relationship. However, data scar…
EntailE: Introducing Textual Entailment in Commonsense Knowledge Graph Completion
Ying Su, Tianqing Fang, Huiru Xiao +4
Commonsense knowledge graph completion is a new challenge for commonsense knowledge graph construction and application. In contrast to factual knowledge graphs such as Freebase and…
AbsInstruct: Eliciting Abstraction Ability from LLMs through Explanation Tuning with Plausibility Estimation
Zhaowei Wang, Wei Fan, Qing Zong +7
Abstraction ability is crucial in human intelligence, which can also benefit various tasks in NLP study. Existing work shows that LLMs are deficient in abstract ability, and how to…
ConstraintChecker: A Plugin for Large Language Models to Reason on Commonsense Knowledge Bases
Quyet V. Do, Tianqing Fang, Shizhe Diao +2
Reasoning over Commonsense Knowledge Bases (CSKB), i.e. CSKB reasoning, has been explored as a way to acquire new commonsense knowledge based on reference knowledge in the original…