23 citations · 71 across the 18 of their papers we have counts for
18 papers
MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification
MiroMind Team, S. Bai, L. Bing +39
We present MiroThinker-1.7, a new research agent designed for complex long-horizon reasoning tasks. Building on this foundation, we further introduce MiroThinker-H1, which extends…
DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation
Yibo Wang, Lei Wang, Yue Deng +7
Deep research systems are widely used for multi-step web research, analysis, and cross-source synthesis, yet their evaluation remains challenging. Existing benchmarks often require…
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
MiroMind Team, Song Bai, Lidong Bing +52
We present MiroThinker v1.0, an open-source research agent designed to advance tool-augmented reasoning and information-seeking capabilities. Unlike previous agents that only scale…
A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning
Yixin Ji, Juntao Li, Yang Xiang +6
The remarkable performance of the o1 model in complex reasoning demonstrates that test-time compute scaling can further unlock the model's potential, enabling powerful System-2 thi…
Multi-Agent Sampling: Scaling Inference Compute for Data Synthesis with Tree Search-Based Agentic Collaboration
Hai Ye, Mingbao Lin, Hwee Tou Ng +1
Scaling laws for inference compute in multi-agent systems remain under-explored compared to single-agent scenarios. This work aims to bridge this gap by investigating the problem o…
Self-Judge: Selective Instruction Following with Alignment Self-Evaluation
Hai Ye, Hwee Tou Ng
Pre-trained large language models (LLMs) can be tailored to adhere to human instructions through instruction tuning. However, due to shifts in the distribution of test-time data, t…
Preference-Guided Reflective Sampling for Aligning Language Models
Hai Ye, Hwee Tou Ng
Iterative data generation and model re-training can effectively align large language models(LLMs) to human preferences. The process of data sampling is crucial, as it significantly…
On the Robustness of Question Rewriting Systems to Questions of Varying Hardness
Hai Ye, Hwee Tou Ng, Wenjuan Han
In conversational question answering (CQA), the task of question rewriting~(QR) in context aims to rewrite a context-dependent question into an equivalent self-contained question t…
Multi-Source Test-Time Adaptation as Dueling Bandits for Extractive Question Answering
Hai Ye, Qizhe Xie, Hwee Tou Ng
In this work, we study multi-source test-time model adaptation from user feedback, where K distinct models are established for adaptation. To allow efficient adaptation, we cast th…
Test-Time Adaptation with Perturbation Consistency Learning
Yi Su, Yixin Ji, Juntao Li +2
Currently, pre-trained language models (PLMs) do not cope well with the distribution shift problem, resulting in models trained on the training set failing in real test scenarios.…
Robust Question Answering against Distribution Shifts with Test-Time Adaptation: An Empirical Study
Hai Ye, Yuyang Ding, Juntao Li +1
A deployed question answering (QA) model can easily fail when the test data has a distribution shift compared to the training data. Robustness tuning (RT) methods have been widely…
On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation
Ruidan He, Linlin Liu, Hai Ye +6
Adapter-based tuning has recently arisen as an alternative to fine-tuning. It works by adding light-weight adapter modules to a pretrained language model (PrLM) and only updating t…
Feature Adaptation of Pre-Trained Language Models across Languages and Domains with Robust Self-Training
Hai Ye, Qingyu Tan, Ruidan He +3
Adapting pre-trained language models (PrLMs) (e.g., BERT) to new domains has gained much attention recently. Instead of fine-tuning PrLMs as done in most previous work, we investig…
Deep Ranking Based Cost-sensitive Multi-label Learning for Distant Supervision Relation Extraction
Hai Ye, Zhunchen Luo
Knowledge base provides a potential way to improve the intelligence of information retrieval (IR) systems, for that knowledge base has numerous relations between entities which can…
Jointly Learning Semantic Parser and Natural Language Generator via Dual Information Maximization
Hai Ye, Wenjie Li, Lu Wang
Semantic parsing aims to transform natural language (NL) utterances into formal meaning representations (MRs), whereas an NL generator achieves the reverse: producing a NL descript…
Semi-Supervised Learning for Neural Keyphrase Generation
Hai Ye, Lu Wang
We study the problem of generating keyphrases that summarize the key points for a given document. While sequence-to-sequence (seq2seq) models have achieved remarkable performance o…
Interpretable Charge Predictions for Criminal Cases: Learning to Generate Court Views from Fact Descriptions
Hai Ye, Xin Jiang, Zhunchen Luo +1
In this paper, we propose to study the problem of COURT VIEW GENeration from the fact description in a criminal case. The task aims to improve the interpretability of charge predic…
Jointly Extracting Relations with Class Ties via Effective Deep Ranking
Hai Ye, Wenhan Chao, Zhunchen Luo +1
Connections between relations in relation extraction, which we call class ties, are common. In distantly supervised scenario, one entity tuple may have multiple relation facts. Exp…