10 papers
CacheSpec: Finding the Sweet Spot for Small Models in Large Language Models
Jingquan Chen, Jie Feng, Jinghua Piao +2
Large language models (LLMs) are increasingly used for program-aided reasoning, agentic decision making, and structured task execution, but these settings often incur substantial i…
From Scoring to Acting: Outcome-Verified Comparative Self-Distillation for LLM Agents
Xu Xia, Jinghua Piao, Min Yang +3
Recent work on LLM agents is shifting from external capability elicitation to capability internalization, enabling agents to retain useful skills without retrieval at inference tim…
Libra: Taming Attention Workload Skew in Long-Context LLM Training with Bounded Sequence Pool
Yan Wang, Xiulong Yuan, Kaiming Yang +16
Long-context LLM training suffers from a load-balancing problem that sequence packing does not solve. Packing samples into fixed-token sequences balances memory and linear-cost ope…
InfoMem: Training Long-Context Memory Agents with Answer-Conditioned Information Gain
Tiancheng Han, Yong Li, Wuzhou Yu +2
Long-context tasks require LLMs to identify and preserve answer-relevant information from large contexts. Chunk-wise memory agents address this issue by sequentially reading docume…
SkillMaster: Toward Autonomous Skill Mastery in LLM Agents
Min Yang, Jinghua Piao, Xu Xia +4
Skills provide an effective mechanism for improving LLM agents on complex tasks, yet in existing agent frameworks, their creation, refinement, and selection are typically governed…
Accelerating Compound LLM Training Workloads with Maestro
Xiulong Yuan, Hongqing Chen, Jiaxuan Peng +16
Compound LLM training workloads-such as knowledge distillation and multimodal LLM (MLLM) training-are gaining prominence. These typically comprise heterogeneous components differin…
Enhancing Local Life Service Recommendation with Agentic Reasoning in Large Language Model
Shiteng Cao, Xiaochong Lan, Yuwei Du +4
Local life service recommendation is distinct from general recommendation scenarios due to its strong living need-driven nature. Fundamentally, accurately identifying a user's imme…
Towards Scalable Lightweight GUI Agents via Multi-role Orchestration
Ziwei Wang, Junjie Zheng, Leyang Yang +7
Autonomous Graphical User Interface (GUI) agents powered by Multimodal Large Language Models (MLLMs) enable digital automation on end-user devices. While scaling both parameters an…
AutoQual: An LLM Agent for Automated Discovery of Interpretable Features for Review Quality Assessment
Xiaochong Lan, Jie Feng, Yinxing Liu +2
Ranking online reviews by their intrinsic quality is a critical task for e-commerce platforms and information services, impacting user experience and business outcomes. However, qu…
The Thinking Spectrum: An Empirical Study of Tunable Reasoning in LLMs through Model Merging
Xiaochong Lan, Yu Zheng, Shiteng Cao +1
The growing demand for large language models (LLMs) with tunable reasoning capabilities in many real-world applications highlights a critical need for methods that can efficiently…