2 citations · 2 across the 8 of their papers we have counts for
9 papers
Agents-K1: Towards Agent-native Knowledge Orchestration
Zongsheng Cao, Bihao Zhan, Jinxin Shi +25
Current LLM-based research agents have advanced through agent orchestration, yet largely overlook scientific knowledge orchestration. Existing works often reduce papers to abstract…
Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent
Lei Bai, Zongsheng Cao, Yang Chen +50
We introduce Agents-A1, a 35B Mixture-of-Experts Agentic Model that reaches trillion-parameter-level performance by scaling the agent horizon. We investigate agent-horizon scaling…
FlowRAG: Synergizing Explicit Reasoning via Frequency-Aware Multi-Granularity Graph Flow
Bihao Zhan, Zongsheng Cao, Jie Zhou +2
Graph-based retrieval-augmented generation (GraphRAG) is effective for knowledge-intensive and multi-hop query tasks; however, many existing methods primarily seed entity-based gra…
AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution
Yutao Yang, Junsong Li, Qianjun Pan +9
In practical LLM applications, users repeatedly express stable preferences and requirements, such as reducing hallucinations, following institutional writing conventions, or avoidi…
Black-box Model Merging for Language-Model-as-a-Service with Massive Model Repositories
Shilian Chen, Jie Zhou, Tianyu Huai +9
Model merging refers to the process of integrating multiple distinct models into a unified model that preserves and combines the strengths and capabilities of the individual models…
LifeAlign: Lifelong Alignment for Large Language Models with Memory-Augmented Focalized Preference Optimization
Junsong Li, Jie Zhou, Bihao Zhan +7
Alignment plays a crucial role in Large Language Models (LLMs) in aligning with human preferences on a specific task/domain. Traditional alignment methods suffer from catastrophic…
Forget What's Sensitive, Remember What Matters: Token-Level Differential Privacy in Memory Sculpting for Continual Learning
Bihao Zhan, Jie Zhou, Junsong Li +9
Continual Learning (CL) models, while adept at sequential knowledge acquisition, face significant and often overlooked privacy challenges due to accumulating diverse information. T…
Reinforced Interactive Continual Learning via Real-time Noisy Human Feedback
Yutao Yang, Jie Zhou, Junsong Li +5
This paper introduces an interactive continual learning paradigm where AI models dynamically learn new skills from real-time human feedback while retaining prior knowledge. This pa…
Teaching LLMs for Step-Level Automatic Math Correction via Reinforcement Learning
Junsong Li, Jie Zhou, Yutao Yang +7
Automatic math correction aims to check students' solutions to mathematical problems via artificial intelligence technologies. Most existing studies focus on judging the final answ…