6 papers
CurES: From Gradient Analysis to Efficient Curriculum Learning for Reasoning LLMs
Yongcheng Zeng, Zexu Sun, Bokai Ji +7
Curriculum learning plays a crucial role in enhancing the training efficiency of large language models (LLMs) on reasoning tasks. However, existing methods often fail to adequately…
STRUCTUREDAGENT: Planning with AND/OR Trees for Long-Horizon Web Tasks
ELita Lobo, Xu Chen, Jingjing Meng +5
Recent advances in large language models (LLMs) have enabled agentic systems for sequential decision-making. Such agents must perceive their environment, reason across multiple tim…
Solving the Granularity Mismatch: Hierarchical Preference Learning for Long-Horizon LLM Agents
Heyang Gao, Zexu Sun, Erxue Min +4
Large Language Models (LLMs) as autonomous agents are increasingly tasked with solving complex, long-horizon problems. Aligning these agents via preference-based offline methods li…
AgentSkiller: Scaling Generalist Agent Intelligence through Semantically Integrated Cross-Domain Data Synthesis
Zexu Sun, Bokai Ji, Hengyi Cai +4
Large Language Model agents demonstrate potential in solving real-world problems via tools, yet generalist intelligence is bottlenecked by scarce high-quality, long-horizon data. E…
Cog-Rethinker: Hierarchical Metacognitive Reinforcement Learning for LLM Reasoning
Zexu Sun, Yongcheng Zeng, Erxue Min +3
Contemporary progress in large language models (LLMs) has revealed notable inferential capacities via reinforcement learning (RL) employing verifiable reward, facilitating the deve…
Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding
Ziheng Li, Zexu Sun, Jinman Zhao +8
Reinforcement learning with verifiable rewards (RLVR) has achieved remarkable success in enhancing the reasoning capabilities of large language models (LLMs). However, existing RLV…