10 papers
On-Policy Parameter Update Direction Underlies Generalization in LLM Post-Training
Shufan Shen, Zhongni Hou, Junshu Sun +5
The strong generalization performance of on-policy post-training paradigms has motivated studies of their parameter update behaviors. However, these studies treat the observed beha…
Tool Retrievers Are Underestimated: Annotation Expansion Reveals True Capability
Yanyu Zhu, Chenheng Zhang, Shaoshen Chen +8
In open-world scenarios with massive and evolving tool repositories, tool-augmented large language models rely on a retriever to surface relevant tools for a given query. Because s…
ATLAS: Dual-Horizon Diagnostic Evaluation for Industrial Tool-Use Agents
Wei Chen, Peilun Zhou, Zhaoyu Hu +8
Large language model (LLM) agents are increasingly deployed in user-facing services that require iterative tool use under dynamic business conditions. Reliable evaluation is essent…
Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents
Miao Su, Yucan Guo, Zhongni Hou +8
Memory enables Large Language Model (LLM) agents to perceive, store, and use information from past dialogues, which is essential for personalization. However, existing methods fail…
LocalSearchBench: Benchmarking Agentic Search in Real-World Local Life Services
Hang He, Chuhuai Yue, Chengqi Dong +12
Recent advances in large reasoning models LRMs have enabled agentic search systems to perform complex multi-step reasoning across multiple sources. However, most studies focus on g…
ViPER: Empowering the Self-Evolution of Visual Perception Abilities in Vision-Language Model
Juntian Zhang, Song Jin, Chuanqi Cheng +8
The limited capacity for fine-grained visual perception presents a critical bottleneck for Vision-Language Models (VLMs) in real-world applications. Addressing this is challenging…
TagPR: Tag-Guided Process Supervision for Personalization Reasoning in Large Language Models
Song Jin, Juntian Zhang, Ruyu Lyu +7
Recent advancements have endowed Large Language Models with impressive general reasoning capabilities. However, these reasoning models often perform worse than non-reasoning models…
Beyond Static Testbeds: An Interaction-Centric Agent Simulation Platform for Dynamic Recommender Systems
Song Jin, Juntian Zhang, Yuhan Liu +6
Evaluating and iterating upon recommender systems is crucial, yet traditional A/B testing is resource-intensive, and offline methods struggle with dynamic user-platform interaction…
PolarQuant: Leveraging Polar Transformation for Efficient Key Cache Quantization and Decoding Acceleration
Songhao Wu, Ang Lv, Xiao Feng +5
The KV cache in large language models is a dominant factor in memory usage, limiting their broader applicability. Quantizing the cache to lower bit widths is an effective way to re…
Semantic Convergence: Harmonizing Recommender Systems via Two-Stage Alignment and Behavioral Semantic Tokenization
Guanghan Li, Xun Zhang, Yufei Zhang +3
Large language models (LLMs), endowed with exceptional reasoning capabilities, are adept at discerning profound user interests from historical behaviors, thereby presenting a promi…