34 papers
Private Direct Preference Optimization for LLM Alignment
Yangfan Jiang, Fei Wei, Ergute Bao +3
Direct preference optimization (DPO) is now a standard method for aligning large language models (LLMs) using human preference data. Each DPO example contains a prompt and a pair o…
From Atomic Actions to Standard Operating Procedures: Iterative Tool Optimization for Self-Evolving LLM Agents
Haipeng Ding, Yuexiang Xie, Zhewei Wei +2
Tool utilization enables Large Language Model (LLM) agents to interact with the real world and resolve complex tasks. However, existing agent frameworks predominantly rely on stati…
Connect the Dots: Training LLMs for Long-Lifecycle Agents with Cross-Domain Generalization Via Reinforcement Learning
Yanxi Chen, Weijie Shi, Yuexiang Xie +4
This work presents a general framework for training large language models (LLMs) to "Connect the Dots" (CoD), a meta-capability required by long-lifecycle agents: as an LLM-based A…
Beyond Domains: Reusing Web Skills via Transferable Interaction Patterns
Shiqi He, Yue Cui, Feijie Wu +5
Large language model (LLM) web agents are usually deployed as tool callers: each turn, the model reads a fresh page observation and emits one structured tool action. When every act…
Branch-and-Browse: Efficient and Controllable Web Exploration with Tree-Structured Reasoning and Action Memory
Shiqi He, Yue Cui, Xinyu Ma +3
Autonomous web agents powered by large language models (LLMs) show strong potential for performing goal-oriented tasks such as information retrieval, report generation, and online…
Retrieval Heads are Dynamic
Yuping Lin, Zitao Li, Yue Xing +6
Recent studies have identified "retrieval heads" in Large Language Models (LLMs) responsible for extracting information from input contexts. However, prior works largely rely on st…