6 citations · 7 across the 21 of their papers we have counts for
15 papers · 1 filter
Retrieval-Driven Memory Reconsolidation for Long-Term LLM Agents
Yuanyi Song, Yukai Wang, Xinbei Ma +7
Long-term memory is essential for LLM-based agents operating over extended interactions. Existing memory systems primarily update memory when new information arrives, treating retr…
Beyond Over-Refusal: Defending Indirect Prompt Injection via Latent Instruction Manifolds
Jiahao Chen, Rui Yin, Xinfeng Li +6
Large Language Models (LLMs) have been integrated into complex ecosystems (e.g., Code Agents), while Indirect Prompt Injection (IPI) attacks have emerged as critical barriers to th…
The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails
Shuo Shi, Rui Yin, Naen Xu +7
Multimodal guard models have emerged as critical safety components for screening content in vision-language systems. While adversarial research has extensively studied jailbreaking…
LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents
Aofan Yu, Chenyu Zhou, Tianyi Xu +8
Agent systems increasingly use textual skills to encode reusable task procedures, but injecting these skills into the prompt at every step incurs substantial context overhead and e…
SkillMAS: Skill Co-Evolution with LLM-based Multi-Agent System
Shuai Pan, Yixiang Liu, Jiaye Gao +7
Large language model (LLM) agent systems are increasingly expected to improve after deployment, but existing work often decouples two adaptation targets: skill evolution and multi-…
SMMBench: A Benchmark for Source-Distributed Multimodal Agent Memory
Huacan Chai, Yukai Wang, Yingxuan Yang +7
Existing benchmarks for multimodal memory reasoning largely evaluate systems within pre-assembled contexts, but under-evaluate whether agents can use evidence distributed across in…
Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents
Jingxing Wang, Chenyu Zhou, Zhihui Fu +4
Additional test-time compute can give LLM agents access to more past experience, yet expanding the context or adding rollouts does not necessarily yield greater agent capability. W…
Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors
Rui Yin, Tianxu Han, Naen Xu +8
Safety-aligned large language models (LLMs) are increasingly deployed in real-world pipelines, yet this deployment also enlarges the supply-chain attack surface: adversaries can di…
Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering
Chenyu Zhou, Huacan Chai, Wenteng Chen +18
Large language model (LLM) agents are increasingly built less by changing model weights than by reorganizing the runtime around them. Capabilities that earlier systems expected the…
"I See What You Did There": Can Large Vision-Language Models Understand Multimodal Puns?
Naen Xu, Jiayi Sheng, Changjiang Li +7
Puns are a common form of rhetorical wordplay that exploits polysemy and phonetic similarity to create humor. In multimodal puns, visual and textual elements synergize to ground th…
When Agents "Misremember" Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent Systems
Naen Xu, Hengyu An, Shuo Shi +7
Recent advancements in large language models (LLMs) have significantly enhanced the capabilities of collaborative multi-agent systems, enabling them to address complex challenges.…
POP: Prefill-Only Pruning for Efficient Large Model Inference
Junhui He, Zhihui Fu, Jun Wang +1
Large Language Models (LLMs) and Vision-Language Models (VLMs) have demonstrated remarkable capabilities. However, their deployment is hindered by significant computational costs.…
FraudShield: Knowledge Graph Empowered Defense for LLMs against Fraud Attacks
Naen Xu, Jinghuai Zhang, Ping He +6
Large language models (LLMs) have been widely integrated into critical automated workflows, including contract review and job application processes. However, LLMs are susceptible t…
Attributing and Exploiting Safety Vectors through Global Optimization in Large Language Models
Fengheng Chu, Jiahao Chen, Yuhong Wang +4
While Large Language Models (LLMs) are aligned to mitigate risks, their safety guardrails remain fragile against jailbreak attacks. This reveals limited understanding of components…
Knowledge-Driven Multi-Turn Jailbreaking on Large Language Models
Songze Li, Ruishi He, Xiaojun Jia +2
Large Language Models (LLMs) face a significant threat from multi-turn jailbreak attacks, where adversaries progressively steer conversations to elicit harmful outputs. However, th…