3 citations · 7 across the 13 of their papers we have counts for
17 papers
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks
Hongjin Qian, Chaofan Li, Kun Luo +11
We present AREX-2, an effort to advance the self-improving capability of LLM agents, which we define as the ability to iteratively refine a solution at test time. This ability rest…
Just-In-Time Agent Memory with Runtime Agentic Research
Bingyu Yan, Chaofan Li, Hongjin Qian +3
Memory is critical for AI agents. Many existing agent-memory systems follow an Ahead-of-Time (AOT) design, constructing memory before a specific request arrives. While this reduces…
AREX: Towards a Recursively Self-Improving Agent for Deep Research
Shuqi Lu, Chaofan Li, Kun Luo +21
Deep research requires agents to find answers that jointly satisfy multiple constraints. Discovering such answers is costly, whereas verifying a candidate can often be decomposed i…
CoeusBI: A Comprehensive Interactive Business Intelligence System Powered by LLMs at Baidu [Extended Version]
Jinqing Lian, Chaofan Li, Yingxia Shao +7
The advent of Large Language Models has catalyzed the emergence of interactive Business Intelligence (BI) systems. Although commercial BI products increasingly adopt semantic layer…
Cutscene Agent: An LLM Agent Framework for Automated 3D Cutscene Generation
Lanshan He, Haozhou Pang, Qi Gan +12
Cutscenes are carefully choreographed cinematic sequences embedded in video games and interactive media, serving as the primary vehicle for narrative delivery, character developmen…
General Agentic Memory Via Deep Research
B. Y. Yan, Chaofan Li, Hongjin Qian +2
Memory is critical for AI agents, yet the widely-adopted static memory, aiming to create readily available memory in advance, is inevitably subject to severe information loss. To a…
Retro*: Optimizing LLMs for Reasoning-Intensive Document Retrieval
Junwei Lan, Jianlyu Chen, Zheng Liu +3
With the growing popularity of LLM agents and RAG, it has become increasingly important to retrieve documents that are essential for solving a task, even when their connection to t…
ReasonEmbed: Enhanced Text Embeddings for Reasoning-Intensive Document Retrieval
Jianlyu Chen, Junwei Lan, Chaofan Li +2
In this paper, we introduce ReasonEmbed, a novel text embedding model developed for reasoning-intensive document retrieval. Our work includes three key technical contributions. Fir…
OmniGen2: Towards Instruction-Aligned Multimodal Generation
Chenyuan Wu, Pengfei Zheng, Ruiran Yan +19
In this work, we introduce OmniGen2, a versatile and open-source generative model designed to provide a unified solution for diverse generation tasks, including text-to-image, imag…
Towards A Generalist Code Embedding Model Based On Massive Data Synthesis
Chaofan Li, Jianlyu Chen, Yingxia Shao +2
Code embedding models attract increasing attention due to the widespread popularity of retrieval-augmented generation (RAG) in software development. These models are expected to ca…
FG-RAG: Enhancing Query-Focused Summarization with Context-Aware Fine-Grained Graph RAG
Yubin Hong, Chaofan Li, Jingyi Zhang +1
Retrieval-Augmented Generation (RAG) enables large language models to provide more precise and pertinent responses by incorporating external knowledge. In the Query-Focused Summari…
Reinforced Information Retrieval
Chaofan Li, Zheng Liu, Jianlyv Chen +2
While retrieval techniques are widely used in practice, they still face significant challenges in cross-domain scenarios. Recently, generation-augmented methods have emerged as a p…
Matryoshka Re-Ranker: A Flexible Re-Ranking Architecture With Configurable Depth and Width
Zheng Liu, Chaofan Li, Shitao Xiao +3
Large language models (LLMs) provide powerful foundations to perform fine-grained text re-ranking. However, they are often prohibitive in reality due to constraints on computation…
AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark
Jianlyu Chen, Nan Wang, Chaofan Li +6
Evaluation plays a crucial role in the advancement of information retrieval (IR) models. However, current benchmarks, which are based on predefined domains and human-labeled data,…
Making Text Embedders Few-Shot Learners
Chaofan Li, MingHao Qin, Shitao Xiao +5
Large language models (LLMs) with decoder-only architectures demonstrate remarkable in-context learning (ICL) capabilities. This feature enables them to effectively handle both fam…
SEA-SQL: Semantic-Enhanced Text-to-SQL with Adaptive Refinement
Chaofan Li, Yingxia Shao, Yawen Li +1
Recent advancements in large language models (LLMs) have significantly contributed to the progress of the Text-to-SQL task. A common requirement in many of these works is the post-…
Llama2Vec: Unsupervised Adaptation of Large Language Models for Dense Retrieval
Zheng Liu, Chaofan Li, Shitao Xiao +2
Dense retrieval calls for discriminative embeddings to represent the semantic relationship between query and document. It may benefit from the using of large language models (LLMs)…