9 citations · 9 across the 16 of their papers we have counts for
15 papers · 1 filter
MetaCascade: End-to-End Attacks on Agent Skills via Metadata-Only Poisoning
Junhao Wen, Ping Deng, Qizhi Chen +2
As a key extension mechanism for agent systems, Agent Skills package specialized capabilities for reuse by LLM agents. An agent first retrieves candidate skills based on skill docu…
GRUET: Quantifying Uncertainty of Agentic Reasoning-and-Acting Processes
Shuang Liang, Xin-Yu Hu, Shao-Qun Zhang
Agents have attracted considerably increasing attention due to the power of executing both Reasoning and Acting (ReAct) in open and dynamic environments. The ReAct process typicall…
Visual Graph Reasoning via Knowledge Compilation
Rongzheng Wang, Zhe Wang, Ke Qin +6
Visual graph reasoning requires answering graph-theoretic questions directly from graph images, where graph topology and state are conveyed visually rather than given in symbolic f…
GUT: Quantifying and Optimizing the Reasoning Uncertainty of LLMs via Graph Complexity
Shuang Liang, Xin-Yu Hu, Xiang-Jun Ou +1
Recent years have witnessed great advances in the reasoning ability of Large Language Models (LLMs). However, the reasoning processes of LLMs often exhibit uncertainty, where LLMs…
LEEPS: Latent-Guided Explore-Exploit Prompt Sampling for Efficient RLVR in Large Language Models
Shuang Liang, Haoyang Zhou, Yifan Gong +2
Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models, but prompt groups with identical rollout rewards consume generat…
The Origins of Stochasticity: Comprehensive Investigations on Uncertainty Quantification for Large Language Models
Xiang-Jun Ou, Shuang Liang, Xin-Yu Hu +3
Recent advancements in Large Language Models (LLMs) have enabled sophisticated reasoning and content generation, yet their inherent stochasticity poses significant challenges for e…
Stop When Further Reasoning Won't Help: Attention-State Adaptive Generation in Reasoning Models
Jiakai Li, Ke Qin, Rongzheng Wang +4
By incorporating test-time compute scaling, large reasoning models (LRMs) can solve complex problems through explicit chain-of-thought (CoT) reasoning processes. However, they ofte…
TAD: Temporal-Aware Trajectory Self-Distillation for Fast and Accurate Diffusion LLM
Haoyang Zhou, Li Kong, Shijie Ren +4
Diffusion large language models (dLLMs) offer a promising paradigm for parallel text generation, but in practice they face an accuracy-parallelism trade-off, where increasing token…
Reason Only When Needed: Efficient Generative Reward Modeling via Model-Internal Uncertainty
Chao Xue, Yao Wang, Mengqiao Liu +11
Recent advancements in the Generative Reward Model (GRM) have demonstrated its potential to enhance the reasoning abilities of LLMs through Chain-of-Thought (CoT) prompting. Despit…
OpsLLM: Construction of Large Language Model for Software Operations with Multi-stage Learning
Jingkai He, Pengfei Chen, Chenghui Wu +7
In the field of software operations, Large Language Models (LLMs) have attracted increasing attention. However, existing research has not yet achieved efficient and effective endto…
Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models
Chao Xue, Yao Wang, Mengqiao Liu +11
Supervised Fine-Tuning (SFT) is the standard approach for adapting large language models (LLMs) to downstream tasks. However, we observe a persistent failure mode: even after conve…
Parameter Importance is Not Static: Evolving Parameter Isolation for Supervised Fine-Tuning
Zekai Lin, Chao Xue, Di Liang +8
Supervised Fine-Tuning (SFT) of large language models often suffers from task interference and catastrophic forgetting. Recent approaches alleviate this issue by isolating task-cri…
KEPo: Knowledge Evolution Poison on Graph-based Retrieval-Augmented Generation
Qizhi Chen, Chao Qi, Yihong Huang +5
Graph-based Retrieval-Augmented Generation (GraphRAG) constructs the Knowledge Graph (KG) from external databases to enhance the timeliness and accuracy of Large Language Model (LL…
When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG
Junchen Li, Liang Xu, Qizhi Chen +6
Retrieval-Augmented Generation (RAG) systems are vulnerable to blocking attacks, in which poisoned documents cause large language models (LLMs) to refuse benign queries. Existing a…
Rethinking LLM-Driven Heuristic Design: Generating Efficient and Specialized Solvers via Dynamics-Aware Optimization
Rongzheng Wang, Yihong Huang, Muquan Li +6
Large Language Models (LLMs) have advanced the field of Combinatorial Optimization through automated heuristic generation. Instead of relying on manual design, this LLM-Driven Heur…