73 citations · 159 across the 38 of their papers we have counts for
40 papers
Benchmarking Hybrid Deep Research Across Database Querying and Web Search
Ruofan Wu, Peiran Xu, Xiaolong Li +9
While autonomous agents have made significant strides in "deep research" by iteratively navigating the open web to synthesize information, real-world problem-solving is rarely conf…
ArcticSwarm: Deferring Early Consensus in Long-Horizon Multi-Agent Research
Soyoung Yoon, Boyi Liu, Yite Wang +6
Multi-agent systems have shown strong performance in domains with reliable verifiers such as coding, where multi-parallel candidate generation selected by a verifier is effective.…
The Optimizer Is the Agent: Reasoning-Driven Search across Prompts, Programs, and ML Workflows
Junbo Li, Boyi Liu, Canwen Xu +5
Recent systems for optimizing prompts, programs, and ML workflows typically rely on explicit outer-loop controllers such as evolutionary search, bandits, or textual-gradient method…
MidTool: Mid-training Data Synthesis for Agentic Tool Use
Fengqing Jiang, Yite Wang, Boyi Liu +5
Mid-training is increasingly recognized as a critical stage for shaping the capabilities of large language models. Recent work has shown that targeted mid-training can strengthen r…
Spider 2.0-AIFunc: Extending Real-World Text-to-SQL to AI-Native SQL Workflows
Tianyang Liu, Canwen Xu, Fangyu Lei +6
Major cloud data platforms now expose large language model capabilities as native SQL functions, enabling analysts to perform classification, filtering, sentiment analysis, extract…
Reinforcement Learning without Ground-Truth Solutions can Improve LLMs
Yingyu Lin, Qiyue Gao, Nikki Lijing Kuang +6
Reinforcement learning with verifiable rewards (RLVR) for training LLMs typically rely on ground-truth answers to assign rewards, limiting their applicability to tasks where the gr…
Organize then Retrieve: Hierarchical Memory Navigation for Efficient Agents
Hao-Lun Hsu, Nikki Lijing Kuang, Boyi Liu +2
Large language model (LLM) agents struggle with long-horizon tasks due to their inherent statelessness, requiring all task-relevant information to be encoded in growing input conte…
Learning to Retrieve: Dual-Level Long-Term Memory for Text-to-SQL Agents
Yibo Wang, Nikki Lijing Kuang, Philip S. Yu +2
Interactive text-to-SQL agents solve database tasks through multi-turn interactions involving schema exploration, query execution, feedback interpretation, and decision revision. L…
Residual Skill Optimization for Text-to-SQL Ensembles
Jiongli Zhu, Haoquan Guan, Parjanya Prajakta Prashant +8
Text-to-SQL ensembles improve over single-candidate generation by drawing multiple SQL candidates and selecting one, but their effectiveness is bounded by Pass@K, the probability t…
R-SQL: Ranking Reward and Resampling for Text-to-SQL
Hojae Han, Yeonseok Jeong, Seung-won Hwang +2
Modern Text-to-SQL systems generate multiple candidate SQL queries and rank them to judge a final prediction. However, existing methods face two limitations. First, they often scor…
Learning to Hint for Reinforcement Learning
Yu Xia, Canwen Xu, Zhewei Yao +2
Group Relative Policy Optimization (GRPO) is widely used for reinforcement learning with verifiable rewards, but it often suffers from advantage collapse: when all rollouts in a gr…
Learning to Self-Evolve
Xiaoyin Chen, Canwen Xu, Yite Wang +3
We introduce Learning to Self-Evolve (LSE), a reinforcement learning framework that trains large language models (LLMs) to improve their own contexts at test time. We situate LSE i…
DARE-bench: Evaluating Modeling and Instruction Fidelity of LLMs in Data Science
Fan Shu, Yite Wang, Ruofan Wu +4
The fast-growing demands in using Large Language Models (LLMs) to tackle complex multi-step data science tasks create an emergent need for accurate benchmarking. There are two majo…
Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning
Zhaoyang Wang, Canwen Xu, Boyi Liu +5
Recent advances in large language model (LLM) have empowered autonomous agents to perform multi-turn interactions with tools and environments. However, scaling such agent training…
MedOrch: Medical Diagnosis with Tool-Augmented Reasoning Agents for Flexible Extensibility
Yexiao He, Ang Li, Boyi Liu +2
Healthcare decision-making represents one of the most challenging domains for Artificial Intelligence (AI), requiring the integration of diverse knowledge sources, complex reasonin…
ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering
Ruofan Wu, Youngwon Lee, Fan Shu +5
Retrieval-Augmented Generation (RAG) systems are increasingly diverse, yet many suffer from monolithic designs that tightly couple core functions like query reformulation, retrieva…
Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL
Zhewei Yao, Guoheng Sun, Lukasz Borchmann +7
Translating natural language into SQL (Test2SQL) is a longstanding challenge at the intersection of natural language understanding and structured data access. While large language…
ExCoT: Optimizing Reasoning for Text-to-SQL with Execution Feedback
Bohan Zhai, Canwen Xu, Yuxiong He +1
Text-to-SQL demands precise reasoning to convert natural language questions into structured queries. While large language models (LLMs) excel in many reasoning tasks, their ability…
ConvCodeWorld: Benchmarking Conversational Code Generation in Reproducible Feedback Environments
Hojae Han, Seung-won Hwang, Rajhans Samdani +1
Large language models (LLMs) have proven invaluable for code generation, particularly in interactive settings. However, existing code generation benchmarks fail to capture the dive…
Agentic Verification for Ambiguous Query Disambiguation
Youngwon Lee, Seung-won Hwang, Ruofan Wu +5
In this work, we tackle the challenge of disambiguating queries in retrieval-augmented generation (RAG) to diverse yet answerable interpretations. State-of-the-arts follow a Divers…
CORD: Balancing COnsistency and Rank Distillation for Robust Retrieval-Augmented Generation
Youngwon Lee, Seung-won Hwang, Daniel Campos +3
With the adoption of retrieval-augmented generation (RAG), large language models (LLMs) are expected to ground their generation to the retrieved contexts. Yet, this is hindered by…
Inference Scaling for Bridging Retrieval and Augmented Generation
Youngwon Lee, Seung-won Hwang, Daniel Campos +3
Retrieval-augmented generation (RAG) has emerged as a popular approach to steering the output of a large language model (LLM) by incorporating retrieved contexts as inputs. However…
STUN: Structured-Then-Unstructured Pruning for Scalable MoE Pruning
Jaeseong Lee, seung-won hwang, Aurick Qiao +3
Mixture-of-experts (MoEs) have been adopted for reducing inference costs by sparsely activating experts in Large language models (LLMs). Despite this reduction, the massive number…
FP6-LLM: Efficiently Serving Large Language Models Through FP6-Centric Algorithm-System Co-Design
Haojun Xia, Zhen Zheng, Xiaoxia Wu +10
Six-bit quantization (FP6) can effectively reduce the size of large language models (LLMs) and preserve the model quality consistently across varied applications. However, existing…