8 papers · 1 filter
Data Strategies for Large Language Models: A Unified Perspective on the Training Lifecycle
Yuanjian Xu, Jianing Hao, Tianze Sun +7
Data strategy plays a central role in training large language models (LLMs). It governs the selection, weighting, and scheduling of training data, thereby determining the capabilit…
AgentPerturb: Evaluating LLM Agent Robustness under Controlled Interaction Perturbations
Yuanjian Xu, Jinyi Han, Jianing Hao +5
Real-world tasks are often complex and noisy, posing substantial challenges for LLM agents. Yet existing evaluations lack a systematic framework for jointly characterizing potentia…
Skill-Use: Can LLMs Actually Use Skills in Agentic Harnesses?
Jinyi Han, Yuanjian Xu, Ying Liao +6
Large language model (LLM) agents increasingly rely on skills, structured documents that specify when to act, which procedure to follow, and which tools are allowed. Existing evalu…
From Outcomes to Actions: Leveraging Hindsight for Long-Horizon Language Agent Training
Zishang Jiang, Tingyun Li, Jinyi Han +7
Reinforcement learning (RL) has become a widely adopted technique for improving large language models (LLMs) on complex tasks. Despite this progress, existing RL methods still face…
ADaPT: Token-Level Decoupling for Efficient Large Reasoning Models
Tingyun Li, Zishang Jiang, Jinyi Han +8
Large reasoning models rely on long chain-of-thought to achieve strong performance, but applying such reasoning uniformly incurs high computational cost. Existing efficiency-orient…
GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0)
Jiaqing Liang, Jinyi Han, Weijia Li +15
Long-horizon large language model (LLM) agents are fundamentally limited by context. As interactions become longer, tool descriptions, retrieved memories, and raw environmental fee…
Not All Negative Samples Are Equal: LLMs Learn Better from Plausible Reasoning
Zixiang Di, Jinyi Han, Shuo Zhang +8
Learning from negative samples holds great promise for improving Large Language Model (LLM) reasoning capability, yet existing methods treat all incorrect responses as equally info…
Structured Reasoning for Large Language Models
Jinyi Han, Zixiang Di, Zishang Jiang +4
Large language models (LLMs) achieve strong performance by generating long chains of thought, but longer traces always introduce redundant or ineffective reasoning steps. One typic…