5 papers
Contrastive Branch Policy Optimization
Ying Wang, Changlin Qiu, Bang Lin +4
Reinforcement learning with verifiable rewards (RLVR) enables language models to learn multi-turn interaction with external tools, yet its sparse outcome rewards provide no signal…
Bidirectional Context Self-Distillation for Reinforcement Learning of Skill-Based LLM Agents
Tianjun Pan, Yuan Li, Hongda Wang +8
External natural-language skills provide large language model (LLM) agents with reusable and editable guidance for solving complex tasks. Yet their effectiveness depends not only o…
MerchantBench: Benchmarking LLM Agents for Long-Term Coherence in E-Commerce Operations
Qiming Shi, Yulong Tao, Linbo Jin +10
Large language model agents are increasingly evaluated as autonomous tool users, yet most benchmarks focus on bounded tasks with immediate success criteria. Real-world deployments…
SKILL-KD: Contrastive Skill Distillation for LLM Agents
Qiming Shi, Yibo Dou, Jiawen Zhu +5
Skill-based prompting has become a practical mechanism for improving large language model (LLM) agents, yet existing skill acquisition methods often treat skills as experience summ…
Beyond Solution-Centric Search: Adaptive Inquiry and Knowledge Revision for Autonomous ML Engineering
Shaokang Fu, Yulong Tao, Linbo Jin +7
Long-horizon autonomous research tasks such as machine learning engineering require systems to make interdependent decisions under a limited budget. Existing LLM-based agents typic…