13 papers
GitHarness: Git Init Your Harness Working Memory for Perpetual User Requirements
Zhibang Yang, Xinke Jiang, Yuxuan Liu +9
LLM-based agents increasingly collaborate with users on long-horizon tasks, accumulating evidence, code, and drafts through extensive search, reasoning, and execution. As users ins…
Harness-RL: Black-Box Reinforcement Learning with Action-Args Decoupling for Central-Agent Multi-Agent Harnesses
Xinke Jiang, Zhixin Zhang, Zhibang Yang +6
Large language model agents increasingly solve long-horizon tasks through multi-agent harnesses in which a central agent coordinates specialized sub-agents, tools, and environments…
AgenticRag-R1: Agentic Reinforcement Learning with Stack Memory for Multi-Step Reasoning, Retrieval and Memorizing
Xinke Jiang, Yue Fang, Zhibang Yang +12
Retrieval-Augmented Generation (RAG) improves the factuality of large language models (LLMs), yet existing RAG systems often struggle with complex, multi-step reasoning that requir…
LoongReflect: Boosting Long-Horizon Reflection in Search Agents via Global Perspective Distillation
Zhixin Zhang, Xinke Jiang, Zhibang Yang +5
Large language model agents increasingly rely on long-horizon reasoning to solve complex tasks involving planning, tool use, and memory. A critical capability in such settings is r…
Absorber LLM: Harnessing Causal Synchronization for Test-Time Training
Zhixin Zhang, Shabo Zhang, Chengcan Wu +2
Transformers suffer from a high computational cost that grows with sequence length for self-attention, making inference in long streams prohibited by memory consumption. Constant-m…
AgriWorld:A World Tools Protocol Framework for Verifiable Agricultural Reasoning with Code-Executing LLM Agents
Zhixing Zhang, Jesen Zhang, Hao Liu +4
Foundation models for agriculture are increasingly trained on massive spatiotemporal data (e.g., multi-spectral remote sensing, soil grids, and field-level management logs) and ach…
StackPlanner: A Centralized Hierarchical Multi-Agent System with Task-Experience Memory Management
Ruizhe Zhang, Xinke Jiang, Zhibang Yang +12
Multi-agent systems based on large language models, particularly centralized architectures, have recently shown strong potential for complex and knowledge-intensive tasks. However,…
GMoPE:A Prompt-Expert Mixture Framework for Graph Foundation Models
Zhibin Wang, Zhixing Zhang, Shuqi Wang +2
Graph Neural Networks (GNNs) have demonstrated impressive performance on task-specific benchmarks, yet their ability to generalize across diverse domains and tasks remains limited.…
Securing Multi-Agent Systems Against Corruptions via Node Contribution Backpropagation
Chengcan Wu, Zhixin Zhang, Mingqian Xu +2
Multi-Agent Systems (MAS) have become a prevalent paradigm for Large Language Model (LLM) applications. However, the complex multi-agent design in MAS introduces unique trustworthi…
Dynamic Orthogonal Continual Fine-tuning for Mitigating Catastrophic Forgettings
Zhixin Zhang, Zeming Wei, Meng Sun
Catastrophic forgetting remains a critical challenge in continual learning for large language models (LLMs), where models struggle to retain performance on historical tasks when fi…
UniAPO: Unified Multimodal Automated Prompt Optimization
Qipeng Zhu, Yanzhe Chen, Huasong Zhong +5
Prompting is fundamental to unlocking the full potential of large language models. To automate and enhance this process, automatic prompt optimization (APO) has been developed, dem…
Secure LLM Fine-Tuning via Safety-Aware Probing
Chengcan Wu, Zhixin Zhang, Zeming Wei +3
Large language models (LLMs) have achieved remarkable success across many applications, but their ability to generate harmful content raises serious safety concerns. Although safet…
Stackelberg Self-Annotation: A Robust Approach to Data-Efficient LLM Alignment
Xu Chu, Zhixin Zhang, Tianyu Jia +1
Aligning large language models (LLMs) with human preferences typically demands vast amounts of meticulously curated data, which is both expensive and prone to labeling noise. We pr…