11 citations · 12 across the 10 of their papers we have counts for
10 papers
Who&When Pro: Can LLMs Really Attribute Failures in AI Agents?
Jiale Liu, Huajun Xi, Shaokun Zhang +6
Automated failure attribution uses LLMs to identify where and why agentic systems fail. As agents become more capable, their failures become subtler, making automated attribution i…
When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs
Yifan Zeng, Yiran Wu, Yaolun Zhang +4
Multi-agent LLM workflows route inference through specialized roles to lift end-task accuracy, but jointly training those roles with reinforcement learning is unstable in ways that…
The Ranking Blind Spot: Decision Hijacking in LLM-based Text Ranking
Yaoyao Qian, Yifan Zeng, Yuchao Jiang +2
Large Language Models (LLMs) have demonstrated strong performance in information retrieval tasks like passage ranking. Our research examines how instruction-following capabilities…
SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinement
Chelsi Jain, Yiran Wu, Yifan Zeng +5
Document Visual Question Answering (DocVQA) is a practical yet challenging task, which is to ask questions based on documents while referring to multiple pages and different modali…
Divide, Optimize, Merge: Fine-Grained LLM Agent Optimization at Scale
Jiale Liu, Yifan Zeng, Shaokun Zhang +5
LLM-based optimization has shown remarkable potential in enhancing agentic systems. However, the conventional approach of prompting LLM optimizer with the whole training trajectori…
Memory-Augmented Agent Training for Business Document Understanding
Jiale Liu, Yifan Zeng, Malte Højmark-Bertelsen +3
Traditional enterprises face significant challenges in processing business documents, where tasks like extracting transport references from invoices remain largely manual despite t…
TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling
Jiahao Qiu, Yifu Lu, Yifan Zeng +9
Inference-time alignment enhances the performance of large language models without requiring additional training or fine-tuning but presents challenges due to balancing computation…
A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement
Hui Yuan, Yifan Zeng, Yue Wu +3
Reinforcement Learning from Human Feedback (RLHF) has become the predominant approach for language model (LM) alignment. At its core, RLHF uses a margin-based loss for preference o…
LLM-RankFusion: Mitigating Intrinsic Inconsistency in LLM-based Ranking
Yifan Zeng, Ojas Tendolkar, Raymond Baartmans +3
Ranking passages by prompting a large language model (LLM) can achieve promising performance in modern information retrieval (IR) systems. A common approach to sort the ranking lis…
AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks
Yifan Zeng, Yiran Wu, Xiao Zhang +2
Despite extensive pre-training in moral alignment to prevent generating harmful information, large language models (LLMs) remain vulnerable to jailbreak attacks. In this paper, we…