10 papers
EGIP: An Evidence-Grounded Interaction Protocol for Clinical Agents
Zecheng Ren, Ruichen Cong, Yi Min Chen +8
Interactive clinical agents acquire evidence through patient dialogue and diagnostic examinations, yet their performance also depends on how the interaction environment exposes inf…
Learning from Unverified Peers via Shared Residual Distillation
Feiyang Chen, Runze Ma, Zichen Wang +4
A language model can generate several solutions to the same problem, some leading to correct answers and others to incorrect ones. Many post-training methods turn these trajectorie…
Jev-LiteMAS: Separating Decisions from Generation in Multi-Agent Workflows
Kaixiang Wang, Zhaijiacheng Zhou, Jiong Lou +1
Multi-agent LLM systems rely on generative models for expert execution, workflow planning, and artifact review. Yet many coordination operations require only bounded decisions, suc…
BRA-Audit: Budgeted Runtime Auditing for LLM Multi-Agent Systems via Cumulative-Exposure Audit-Point Placement
Kaixiang Wang, Yidan Lin, Jiong Lou +1
LLM-based multi-agent systems (LLM-MAS) solve complex tasks through specialized collaboration, but inter-agent dependencies can propagate hallucinated or malicious outputs into sys…
Stop When Memory Suffices: Evidence-Conditioned Progressive Execution for LLM Agents
Yidan Lin, Kaixiang Wang, Jiong Lou +1
The continued development of LLMs toward persistent and adaptive intelligence increasingly requires long-term memory mechanisms that preserve and reuse information across interacti…
Deep Interaction: An Efficient Human-AI Interaction Method for Large Reasoning Models
Hefeng Zhou, Jinxuan Zhang, Jiong Lou +4
The emergence of Chain-of-Thought (CoT) reasoning has significantly enhanced the ability of large language models (LLMs) to tackle complex, multi-step tasks. However, when errors o…
Privacy-Preserving Text Sanitization for Distributed Agents Collaboration via Disentangled Representations
Xuan Liu, Hefeng Zhou, Sicheng Chen +6
When distributed agents exchange text across organizational boundaries, privacy leakage arises not only from explicit identifiers but also from distributional signatures such as fo…
IEMAS: An Incentive-Efficiency Routing Framework for Open Agentic Web Ecosystems
Hongze Liu, Chang Guo, Yingzeng Li +6
The transition to open, distributed Multi-Agent Systems (MAS) promises scalable intelligence but introduces a non-trivial tension: maximizing global efficiency requires cooperative…
E-mem: Multi-agent based Episodic Context Reconstruction for LLM Agent Memory
Kaixiang Wang, Yidan Lin, Jiong Lou +3
The evolution of Large Language Model (LLM) agents towards System~2 reasoning, characterized by deliberative, high-precision problem-solving, requires maintaining rigorous logical…
MAS-Shield: A Defense Framework for Secure and Efficient LLM MAS
Kaixiang Wang, Zhaojiacheng Zhou, Bunyod Suvonov +9
Large Language Model (LLM)-based Multi-Agent Systems (MAS) are susceptible to linguistic attacks that can trigger cascading failures across the network. Existing defenses face a fu…