149 citations · 169 across the 18 of their papers we have counts for
18 papers
MemoryWalker: Stop Training Agents on Contexts They Never Saw
Zinco J, Xunjie Zhu, Shen Huang +3
Production agent harnesses such as Claude Code and Qwen-Agent compress context during rollout, but training under compression creates a conditioning problem: every eviction branche…
EvoRubric: Self-Evolving Rubric-Driven RL for Open-Ended Generation
Xin Guan, Xiaomeng Hu, Shen Huang +6
Reinforcement Learning (RL) has advanced Large Language Models (LLMs) in verifiable domains, while open-ended generation remains challenging due to the absence of definitive reward…
DeltaMem: Towards Agentic Memory Management via Reinforcement Learning
Qi Zhang, Shen Huang, Chu Liu +4
Recent advances in persona-centric memory have revealed the powerful capability of multi-agent systems in managing persona memory, especially in conversational scenarios. However,…
Evidence-Augmented Policy Optimization with Reward Co-Evolution for Long-Context Reasoning
Xin Guan, Zijian Li, Shen Huang +3
While Reinforcement Learning (RL) has advanced LLM reasoning, applying it to long-context scenarios is hindered by sparsity of outcome rewards. This limitation fails to penalize un…
WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research
Zijian Li, Xin Guan, Bo Zhang +9
This paper tackles \textbf{open-ended deep research (OEDR)}, a complex challenge where AI agents must synthesize vast web-scale information into insightful reports. Current approac…
Tongyi DeepResearch Technical Report
Tongyi DeepResearch Team, Baixuan Li, Bo Zhang +54
We present Tongyi DeepResearch, an agentic large language model, which is specifically designed for long-horizon, deep information-seeking research tasks. To incentivize autonomous…
MaskSearch: A Universal Pre-Training Framework to Enhance Agentic Search Capability
Weiqi Wu, Xin Guan, Shen Huang +6
Retrieval-Augmented Language Models (RALMs) represent a classic paradigm where models enhance generative capabilities using external knowledge retrieved via a specialized module. R…
Unfolding the Headline: Iterative Self-Questioning for News Retrieval and Timeline Summarization
Weiqi Wu, Shen Huang, Yong Jiang +3
In the fast-changing realm of information, the capacity to construct coherent timelines from extensive event-related content has become increasingly significant and challenging. Th…
Learning Robust Named Entity Recognizers From Noisy Data With Retrieval Augmentation
Chaoyi Ai, Yong Jiang, Shen Huang +2
Named entity recognition (NER) models often struggle with noisy inputs, such as those with spelling mistakes or errors generated by Optical Character Recognition processes, and lea…
Exploring Key Point Analysis with Pairwise Generation and Graph Partitioning
Xiao Li, Yong Jiang, Shen Huang +3
Key Point Analysis (KPA), the summarization of multiple arguments into a concise collection of key points, continues to be a significant and unresolved issue within the field of ar…
EcomGPT-CT: Continual Pre-training of E-commerce Large Language Models with Semi-structured Data
Shirong Ma, Shen Huang, Shulin Huang +6
Large Language Models (LLMs) pre-trained on massive corpora have exhibited remarkable performance on various NLP tasks. However, applying these models to specific domains still pos…
EcomGPT: Instruction-tuning Large Language Models with Chain-of-Task Tasks for E-commerce
Yangning Li, Shirong Ma, Xiaobin Wang +6
Recently, instruction-following Large Language Models (LLMs) , represented by ChatGPT, have exhibited exceptional performance in general Natural Language Processing (NLP) tasks. Ho…
SeqGPT: An Out-of-the-box Large Language Model for Open Domain Sequence Understanding
Tianyu Yu, Chengyue Jiang, Chao Lou +12
Large language models (LLMs) have shown impressive ability for open-domain NLP tasks. However, LLMs are sometimes too footloose for natural language understanding (NLU) tasks which…
Bidirectional End-to-End Learning of Retriever-Reader Paradigm for Entity Linking
Yinghui Li, Yong Jiang, Yangning Li +4
Entity Linking (EL) is a fundamental task for Information Extraction and Knowledge Graphs. The general form of EL (i.e., end-to-end EL) aims to first find mentions in the given inp…
DAMO-NLP at SemEval-2023 Task 2: A Unified Retrieval-augmented System for Multilingual Named Entity Recognition
Zeqi Tan, Shen Huang, Zixia Jia +8
The MultiCoNER \RNum{2} shared task aims to tackle multilingual named entity recognition (NER) in fine-grained and noisy scenarios, and it inherits the semantic ambiguity and low-c…
ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPT
Xiang Wei, Xingyu Cui, Ning Cheng +9
Zero-shot information extraction (IE) aims to build IE systems from the unannotated text. It is challenging due to involving little human intervention. Challenging but worthwhile,…
DAMO-NLP at NLPCC-2022 Task 2: Knowledge Enhanced Robust NER for Speech Entity Linking
Shen Huang, Yuchen Zhai, Xinwei Long +4
Speech Entity Linking aims to recognize and disambiguate named entities in spoken languages. Conventional methods suffer gravely from the unfettered speech styles and the noisy tra…
Cognitive Representation Learning of Self-Media Online Article Quality
Yiru Wang, Shen Huang, Gongfu Li +5
The automatic quality assessment of self-media online articles is an urgent and new issue, which is of great value to the online recommendation and search. Different from tradition…