9 papers
MemFuse: Multi-Source Memory Fusion from Fragmented Observations
Chao Li, Yuanfa Li, Wenhao Wu +3
Long-term memory is essential for agents that operate across extended interactions, yet existing memory systems and benchmarks predominantly focus on single-source textual historie…
DACCI: A Dual-Loop Diagnostic Protocol for Evidence-Preserving Agent Memory
Xule Liu, Yijun Liu, Chao Li +1
Memory is a key capability of LLM agents. Persistent memory extends this across sessions---enabling recall, revision, and personalization. Yet its multi-stage pipeline (ingestion,…
G-ReAct: Graph-Guided Deep Search via Structure-State Co-Evolution
Shaoxiong Yang, Mengyuan Zhang, Shaojun Lin +4
Deep search has become a fundamental capability of large language models (LLMs) for solving open-domain complex tasks. However, existing approaches typically rely on linear sequent…
HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
Tingyang Chen, Shuo Lu, Kang Zhao +11
AI agent performance depends critically on the runtime harness, comprising the prompts, tools, memory, and control flow that mediate how a model observes, reasons, and acts. Yet to…
Mi-Memory: A Lifecycle Memory Framework for Personal AI
Xule Liu, Hanlin Teng, Chao Li +15
Personal AI is moving beyond chat-only interaction toward continuous services that span phones, cars, homes, wearables, cameras, and tools. In this setting, memory cannot remain a…
FSFM: A Biologically-Inspired Framework for Selective Forgetting of Agent Memory
Yingjie Gu, Wenjian Xiong, Liqiang Wang +7
For LLM agents, memory management critically impacts efficiency, quality, and security. While much research focuses on retention, selective forgetting--inspired by human cognitive…
FutureMind: Equipping Small Language Models with Strategic Thinking-Pattern Priors via Adaptive Knowledge Distillation
Shaoxiong Yang, Junting Li, Mengyuan Zhang +3
Small Language Models (SLMs) are attractive for cost-sensitive and resource-limited settings due to their efficient, low-latency inference. However, they often struggle with comple…
ICPO: Intrinsic Confidence-Driven Group Relative Preference Optimization for Efficient Reinforcement Learning
Jinpeng Wang, Chao Li, Ting Ye +3
Reinforcement Learning with Verifiable Rewards (RLVR) demonstrates significant potential in enhancing the reasoning capabilities of Large Language Models (LLMs). However, existing…
End-to-End Optimization of LLM-Driven Multi-Agent Search Systems via Heterogeneous-Group-Based Reinforcement Learning
Guanzhong Chen, Shaoxiong Yang, Chao Li +3
Large language models (LLMs) are versatile, yet their deployment in complex real-world settings is limited by static knowledge cutoffs and the difficulty of producing controllable…