9 papers
A Stackelberg Framework for Resource-Aware LLM Agents: Learning, Repair, and Conditional Guarantees
Baoxun Wang
Large language model (LLM) agents increasingly operate as multi-turn systems that must allocate context, prompt verbosity, and tool access under finite computational budgets. Stati…
Discovery under Hypothesis Redundancy: A Geometric Theory of Discovery Bottlenecks
Li Xia, Baoxun Wang
Scientific discovery saturates when new hypotheses cease to provide independent information, even if the nominal hypothesis space remains large. We study hybrid discovery systems t…
GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
V Team, Wenyi Hong, Xiaotao Gu +94
We present GLM-5V-Turbo, a step toward native foundation models for multimodal agents. As foundation models are increasingly deployed in real environments, agentic capability depen…
ToolSample: Dual Dynamic Sampling Methods with Curriculum Learning for RL-based Tool Learning
Zihao Feng, Xiaoxue Wang, Bowen Wu +4
While reinforcement learning (RL) is increasingly used for LLM-based tool learning, its efficiency is often hampered by an overabundance of simple samples that provide diminishing…
Empowering LLMs in Task-Oriented Dialogues: A Domain-Independent Multi-Agent Framework and Fine-Tuning Strategy
Zihao Feng, Xiaoxue Wang, Bowen Wu +6
Task-oriented dialogue systems based on Large Language Models (LLMs) have gained increasing attention across various industries and achieved significant results. Current approaches…
RAIDEN-R1: Improving Role-awareness of LLMs via GRPO with Verifiable Reward
Zongsheng Wang, Kaili Sun, Bowen Wu +3
Role-playing conversational agents (RPCAs) face persistent challenges in maintaining role consistency. To address this, we propose RAIDEN-R1, a novel reinforcement learning framewo…