8 papers
Self-Authored Verification Is Unreliable in Heuristic Self-Improving Agents
Diandian Guo, Cong Cao, Fangfang Yuan +3
Self-improving agents accumulate capability by repeatedly rewriting procedural policies, controllers, or heuristic rules. They typically rely on self-authored tests or metrics to d…
MOF-Sleuth: Tool-Grounded Reward Alignment for Explainable Fine-Grained MOF CIF Auditing
Yu Liu, Zhiwei Yang, Diandian Guo +7
Large metal-organic framework (MOF) databases support simulation, screening, and machine learning through crystallographic information files (CIFs). Subtle chemical and structural…
MuVaC: A Variational Causal Framework for Multimodal Sarcasm Understanding in Dialogues
Diandian Guo, Fangfang Yuan, Cong Cao +5
The prevalence of sarcasm in multimodal dialogues on the social platforms presents a crucial yet challenging task for understanding the true intent behind online content. Comprehen…
Does Faithfulness-Guided Alignment Hurt Accuracy? Unlocking Accurate and Faithful Post-Retrieval Reasoning
Yu Liu, Wenxiao Zhang, Diandian Guo +6
Retrieval-augmented generation (RAG) can achieve strong answer accuracy on multi-hop questions, but outcome-level rewards often leave reasoning traces weakly grounded and difficult…
PRISMA: Reinforcement Learning Guided Two-Stage Policy Optimization in Multi-Agent Architecture for Open-Domain Multi-Hop Question Answering
Yu Liu, Wenxiao Zhang, Cong Cao +10
Answering real-world open-domain multi-hop questions over massive corpora is a critical challenge in Retrieval-Augmented Generation (RAG) systems. Recent research employs reinforce…
Hot-Swap MarkBoard: An Efficient Black-box Watermarking Approach for Large-scale Model Distribution
Zhicheng Zhang, Peizhuo Lv, Mengke Wan +7
Recently, Deep Learning (DL) models have been increasingly deployed on end-user devices as On-Device AI, offering improved efficiency and privacy. However, this deployment trend po…