2 citations · 4 across the 13 of their papers we have counts for
14 papers
EPOCH: Reliable Discovery through Evidence-Governed Search
Binjie Guo, Aisheng Mo, Ruitong Li +1
AI research agents are increasingly used to search over programs, mathematical constructions, and proofs. However, existing systems typically optimize evaluator feedback without ad…
EM^2Mem: Event-Centric Multimodal Memory for Large Language Models
Yijun Chen, Yaqi Zheng, Yanya Li +11
Multimodal memory offers a scalable interface for long-video question answering, but existing methods often retrieve captions, frames, transcripts, summaries, or graph facts as iso…
PAC: Progress-Augmented Advantage Curriculum for Multi-Task Reinforcement Learning of LLMs
Yuanqiang Yu, Yanzhao Zheng, Zhentao Zhang +8
Reinforcement learning (RL) is used to improve the reasoning abilities of LLMs, while training data span heterogeneous tasks. However, most RL post-training pipelines rely on fixed…
MobileMem: Learning from a Year of Mobile Experiences
Xinle Deng, Yida Xue, Xiangyuan Ru +16
The next generation of AI agents is increasingly moving beyond systems that answer isolated questions toward persistent personal assistants that can understand, remember, and conti…
TokenPilot: Cache-Efficient Context Management for LLM Agents
Buqiang Xu, Zirui Xue, Dianmou Chen +12
As LLM agents are deployed in long-horizon sessions, context accumulation drives up inference costs. Existing approaches utilize text pruning or dynamic memory eviction to minimize…
Rethinking Memory as Continuously Evolving Connectivity
Jizhan Fang, Buqiang Xu, Zhixian Wang +12
Existing memory-augmented LLM agents often treat memory as a static repository with pre-defined representations and fixed retrieval pipelines, which is brittle in dynamic agentic e…
MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems
Xinle Deng, Ruobin Zhong, Hujin Peng +15
Memory is essential for enabling large language models to support long-horizon reasoning, yet existing memory systems remain unreliable and difficult to debug. Tracing memory's dyn…
Temp-R1: A Unified Autonomous Agent for Complex Temporal KGQA via Reverse Curriculum Reinforcement Learning
Zhaoyan Gong, Zhiqiang Liu, Songze Li +7
Temporal Knowledge Graph Question Answering (TKGQA) is inherently challenging, as it requires sophisticated reasoning over dynamic facts with multi-hop dependencies and complex tem…
Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency
Haoming Xu, Ningyuan Zhao, Yunzhi Yao +7
As Large Language Models (LLMs) are increasingly deployed in real-world settings, correctness alone is insufficient. Reliable deployment requires maintaining truthful beliefs under…
LightMem: Lightweight and Efficient Memory-Augmented Generation
Jizhan Fang, Xinle Deng, Haoming Xu +9
Despite their remarkable capabilities, Large Language Models (LLMs) struggle to effectively leverage historical interaction information in dynamic and complex environments. Memory…
EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models
Ziwen Xu, Shuxun Wang, Kewei Xu +7
In this paper, we introduce EasyEdit2, a framework designed to enable plug-and-play adjustability for controlling Large Language Model (LLM) behaviors. EasyEdit2 supports a wide ra…
A Multi-Modal AI Copilot for Single-Cell Analysis with Instruction Following
Yin Fang, Xinle Deng, Kangwei Liu +5
Large language models excel at interpreting complex natural language instructions, enabling them to perform a wide range of tasks. In the life sciences, single-cell RNA sequencing…
ChatCell: Facilitating Single-Cell Analysis with Natural Language
Yin Fang, Kangwei Liu, Ningyu Zhang +7
As Large Language Models (LLMs) rapidly evolve, their influence in science is becoming increasingly prominent. The emerging capabilities of LLMs in task generalization and free-for…
Weaver: Foundation Models for Creative Writing
Tiannan Wang, Jiamin Chen, Qingrui Jia +43
This work introduces Weaver, our first family of large language models (LLMs) dedicated to content creation. Weaver is pre-trained on a carefully selected corpus that focuses on im…