Awesome Papers
LLMsQuantumSimSearchAI4CodeAgentsCVRoboticsCyberAI4SciSpeechRLMMGenAIGraphTSRecSysFL

← authors · overview

Xunliang Cai

33 papers · 203 citations
Most-cited papers
  • Exploring Reasoning Reward Model For Agents
    2026
  • Amemgym: Interactive Memory Benchmarking For Assistants In Long-horizon Conversations
    2026
  • Can RL Improve Generalization Of LLM Agents? An Empirical Study
    2026
Top co-authors
Lin Qiu · 2Xuezhi Cao · 2Chao Zhang · 1Hongyu Zang · 1Jiaqi Liu · 1Jiazheng Zhang · 1Peng Pei · 1Qi Gu · 1Qi Zhang · 1Shao Zhang · 1Shichun Liu · 1Tao Gui · 1
Topics
Code AgentsMulti-AgentEvaluationTool UseBrowser AgentsMemoryBenchmarks

Privacy · Terms

© 2026 Awesome Papers.