Large language model (LLM)-based multi-agent systems (MAS) tackle challenging tasks by dividing work among agents and coordinating their contributions toward shared objectives. Evaluating these systems therefore requires benchmarks that assess not only task-solving performance but also the ability to handle interdepend...
Ze-Rui Chen, Qing-Gang Zhang, Qi-Chuan Liu et al.· 0 citations
Large language model (LLM)-based multi-agent systems (MAS) tackle challenging tasks by dividing work among agents and coordinating their contributions toward shared objectives. Evaluating these systems therefore requires benchmarks that assess not only task-solving performance but also the ability to handle interdepend...
Ze-Rui Chen, Qing-Gang Zhang, Qi-Chuan Liu et al.· 0 citations
LLM-based multi-agent systems (MAS) rely on collaboration among specialized agents to solve complex tasks. Existing methods improve MAS by refining the prompts, skills, and execution strategies of individual agents based on task feedback. However, improving individual agents does not necessarily lead to better team col...
Qi-Nuo Cao, Xin He, Dian-Xuan Fu et al.· 0 citations
Self-improving LLM agents increasingly distill successful experiences into persistent, reusable skills. Existing skill attack methods corrupt this learning pipeline by injecting malicious triggers, behaviors, or false facts into individual experiences or extracted skills. However, such attacks are easily detected, and...
Li-Zhi Zhang, Xin He, Dian-Xuan Fu et al.· 0 citations
Long-term memory enables LLM-based agents to retain and reuse information across tasks and sessions, supporting personalization and long-horizon interactions. However, persistent memories can also induce sycophancy, causing agents to over-align with users'historical beliefs even when they are inaccurate, outdated, or i...
Ru-Qin Ning, Hai-Bo Meng, Zhi-Shang Xiang et al.· 0 citations
Genomic prediction can accelerate crop breeding by predicting phenotypes from genome-wide SNP sequences. In practice, this task operates in a severe p \gg n regime, hundreds of thousands to millions of SNPs but only thousands of samples, making end-to-end deep learning prone to overfitting. Genomic foundation models he...
Hua-Chi Zhou, Jia-He Du, Yu-Jing Zhang et al.· Proceedings of the 32nd ACM...· 0 citations
LA-CPD is proposed, a structured method that transforms noisy sentence-level score sequences into coherent authorship segments and outperforms WCP+AIC, increasing sentence-level accuracy from 0.747 to 0.796 while improving boundary localization and LLM-span delineation.
Qing Yang, Zhen-Yun Mao, Zi-Xiang Luo et al.· 0 citations
A Chinese Human-AI Collaborative Text Detection Benchmark (C-HAT-Bench), a unified benchmark that links human-written source texts from five domains to variants produced using six generative models under Prefix-Conditioned Continuation as a reference setting and three collaborative production modes.
Qing Yang, Zi-Xiang Luo, Zhen-Yun Mao et al.· arXiv.org· 0 citations
This paper examines Data Agents from a harness-centric perspective, introducing a taxonomy of Data Agents and associated data environments, and identifying four open reliability problems: inactive semantic calibration, missing clarification, missing experience transfer, and the missing verification-repair repository.
Hua-Chi Zhou, Yu-Jing Zhang, Jia-He Du et al.· 0 citations
The Trajectory-guided Forget-Recover Network (TFR-Net) is proposed, which separates persistent target-related channels from transient hotspots and suppresses only the persistent ones, and achieves a more favorable trade-off between unlearning effectiveness and retained utility than representative baselines.
Ze-Zheng Wu, Xing-He Cheng, Qing-Gang Zhang et al.· 0 citations
HVM-GraphRAG uses a holistic view to guide graph construction, thereby reducing noisy and conflicting graph updates and building reliable indices between concept-level graph nodes and supporting multimodal chunks and enabling the answering model to better integrate heterogeneous evidence.
Xingbo He, Yi-Li Wang, Wenqi Fan et al.· arXiv.org· 1 citation
Graph Engineering is introduced, an emerging paradigm for next-generation agent systems that provides a unified foundation for organizing complex objectives, orchestrating heterogeneous agents, modeling system dynamics, and enabling scalable agent evolution.
Yu-Yuan Feng, Zhi-Shang Xiang, Chao Yang et al.· 5 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.