Chenchen Zhang
3 papers · Latest:
Natural Language Processing
Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces
This paper surveys Reinforcement Learning for LLM-based multi-agent systems, analyzing orchestration traces, reward design, credit assignment, and learning decisions.
2605.02801
Software EngineeringWebCompass: Towards Multimodal Web Coding Evaluation for Code Language Models
WebCompass is a new multimodal benchmark for evaluating large language models' end-to-end web coding capabilities across generation, editing, and repair tasks.
2604.18224
Natural Language ProcessingFrom Reasoning to Agentic: Credit Assignment in Reinforcement Learning for Large Language Models
This paper surveys 47 credit assignment methods in RL for LLMs, offering a taxonomy and resources while highlighting challenges in agentic vs. reasoning tasks.
2604.09459
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.