16 citations · 40 across the 43 of their papers we have counts for
46 papers
Compiling Autoregressive LLM Control into Policy-Exact Parallel Inference for Hierarchical RAG
Zehao Lin, Qianfeng Shen, Xixuan Hao +8
Large language models increasingly act as controllers in structured decision pipelines, yet their decisions are still executed by autoregressive text decoding. Hierarchical RAG is…
MemTrace: State-Consistent Memory for Long-Horizon Coding Agents
Hongming Xu, Le Zhou, ZhongHe Jin +5
As coding agents take on long-horizon software evolution tasks spanning multiple files and stages, longer execution trajectories introduce two coupled challenges: (1) accumulated h…
TRACE: Governing Memory Validity in Evolving Multi-Agent Systems
Wenjun Xiong, Shengtao Zhang, Shangding Gu +5
Persistent memory lets language-model agents carry information across long-running collaborations, but leaves a lifecycle question open: what may a returning agent still act on onc…
PHASE-Tree: Modeling Character-State Evolution in Long-Horizon Role-Playing Dialogue
Bo Tang, Jianan Yang, Junyi Zhu +7
Long-horizon role-playing demands that characters remain recognizable as they evolve with the narrative. Yet existing work falls short on two fronts: representations are typically…
Metis: Memory Foundation Model
Zeyu Zhang, Ziliang Guo, Yihang Sun +14
Recent advances in AI agents have increasingly internalized native capabilities into their underlying foundation models, giving rise to multimodal foundation models and large reaso…
MAPLE-Guard: Memory-Aware Link Enforcement Against Memory-Link Poisoning in Multi-Agent Systems
Wenjun Xiong, Yijin Zhou, Jiaqian Wang +6
LLM-based multi-agent systems (MAS) increasingly rely on persistent private and shared memories for long-horizon coordination. This memory layer improves continuity, but it also gi…
From Memory to Skills: Evidence-Grounded Co-Evolution Governance for Long-Horizon LLM Agents
Bo Tang, Yang Zhang, Guomian Zhuang +8
Existing memory systems for long-horizon LLM agents often retrieve prior traces as passive context rather than converting them into executable capabilities. In this paper, we propo…
SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution
Hongyi Liu, Haoyan Yang, Tao Jiang +4
Long-horizon LLM agents generate traces that could become reusable experience, but raw trajectories are noisy, local, and hard to govern. Agent Skills offer a structured artifact f…
SparseX: Efficient Segment-Level KV Cache Sharing for Interleaved LLM Serving
Quqing Zhang, Kai Chen, Ning Liao +5
In long-context LLM serving, the prefill stage often dominates time-to-first-token and computational cost. Although Prefix Cache in vLLM/PagedAttention has been widely used to reus…
MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents
Yining Chen, Jihao Zhao, Bo Tang +5
As LLM-powered agents are increasingly deployed in edge-cloud environments, personalized memory has become a key enabler of long-term adaptation and user-centric interaction. Howev…
MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGs
Junwei Liao, Haoting Shi, Ruiwen Zhou +9
Episodic memory allows LLM agents to accumulate and retrieve experience, but current methods treat each memory independently, i.e., evaluating retrieval quality in isolation withou…
MemReranker: Reasoning-Aware Reranking for Agent Memory Retrieval
Chunyu Li, Mengyuan Zhang, Jingyi Kang +6
In agent memory systems, the reranking model serves as the critical bridge connecting user queries with long-term memory. Most systems adopt the "retrieve-then-rerank" two-stage pa…
MemReader: From Passive to Active Extraction for Long-Term Agent Memory
Jingyi Kang, Chunyu Li, Ding Chen +3
Long-term memory is fundamental for personalized and autonomous agents, yet populating it remains a bottleneck. Existing systems treat memory extraction as a one-shot, passive tran…
MemFactory: Unified Inference & Training Framework for Agent Memory
Ziliang Guo, Ziheng Li, Bo Tang +2
Memory-augmented Large Language Models (LLMs) are essential for developing capable, long-term AI agents. Recently, applying Reinforcement Learning (RL) to optimize memory operation…
PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments
Shuochen Liu, Junyi Zhu, Long Shu +11
Empowering large language models with long-term memory is crucial for building agents that adapt to users' evolving needs. Existing evaluations of this capability typically interle…
Transformers are Stateless Differentiable Neural Computers
Bo Tang, Weiwei Xie
Differentiable Neural Computers (DNCs) were introduced as recurrent architectures equipped with an addressable external memory supporting differentiable read and write operations.…
MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory
Shengtao Zhang, Jiaqian Wang, Ruiwen Zhou +11
The hallmark of human intelligence is the self-evolving ability to master new skills by learning from past experiences. However, current AI agents struggle to emulate this self-evo…
Do Latent Tokens Think? A Causal and Adversarial Analysis of Chain-of-Continuous-Thought
Yuyi Zhang, Boyu Tang, Tianjie Ju +2
Latent tokens are gaining attention for enhancing reasoning in large language models (LLMs), yet their internal mechanisms remain unclear. This paper examines the problem from a re…
TAdaRAG: Task Adaptive Retrieval-Augmented Generation via On-the-Fly Knowledge Graph Construction
Jie Zhang, Bo Tang, Wanzi Shao +8
Retrieval-Augmented Generation (RAG) improves large language models by retrieving external knowledge, often truncated into smaller chunks due to the input context window, which lea…
HaluMem: Evaluating Hallucinations in Memory Systems of Agents
Ding Chen, Simin Niu, Kehang Li +6
Memory systems are key components that enable AI systems such as LLMs and AI agents to achieve long-term learning and sustained interaction. However, during memory storage and retr…
Text2Mem: A Unified Memory Operation Language for Memory Operating System
Yi Wang, Lihai Yang, Boyu Chen +6
Large language model agents increasingly depend on memory to sustain long horizon interaction, but existing frameworks remain limited. Most expose only a few basic primitives such…
MemOS: A Memory OS for AI System
Zhiyu Li, Chenyang Xi, Chunyu Li +36
Large Language Models (LLMs) have become an essential infrastructure for Artificial General Intelligence (AGI), yet their lack of well-defined memory management systems hinders the…
Adversarial Preference Learning for Robust LLM Alignment
Yuanfu Wang, Pengyu Wang, Chenyang Xi +13
Modern language models often rely on Reinforcement Learning from Human Feedback (RLHF) to encourage safe behaviors. However, they remain vulnerable to adversarial attacks due to th…
GuessArena: Guess Who I Am? A Self-Adaptive Framework for Evaluating LLMs in Domain-Specific Knowledge and Reasoning
Qingchen Yu, Zifan Zheng, Ding Chen +4
The evaluation of large language models (LLMs) has traditionally relied on static benchmarks, a paradigm that poses two major limitations: (1) predefined test sets lack adaptabilit…