pith. sign in

Xianfeng Tang

Identifiers

  • name variant Xianfeng Tang 0.60 · backfill

Papers (13)

  1. Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts cs.AI · 2026 · author #5
  2. From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models cs.CL · 2026 · author #4
  3. Firefly: Illuminating Large-Scale Verified Tool-Call Data Generation from Real APIs cs.SE · 2026 · author #6
  4. Trajectory2Task: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User Intents cs.CL · 2026 · author #8
  5. Agentic Reasoning for Large Language Models cs.AI · 2026 · author #23
  6. WEBSERV: A Full-Stack and RL-Ready Web Environment for Training Web Agents at Scale cs.LG · 2025 · author #9
  7. Can Large Language Models Adequately Perform Symbolic Reasoning Over Time Series? cs.AI · 2025 · author #3
  8. To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems cs.CR · 2025 · author #3
  9. SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models cs.CL · 2025 · author #5
  10. Retrieval-Augmented Generation with Graphs (GraphRAG) cs.IR · 2024 · author #10
  11. Joint Modeling of Dense and Incomplete Trajectories for Citywide Traffic Volume Inference cs.LG · 2019 · author #1
  12. Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Prediction cs.LG · 2018 · author #2
  13. Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction cs.LG · 2018 · author #4

Mentions

  • 2606.05922 #5 · arxiv_oai · confidence 0.70 Xianfeng Tang
  • 2605.20177 #4 · arxiv_oai · confidence 0.70 Xianfeng Tang
  • 2605.17558 #6 · arxiv_oai · confidence 0.70 Xianfeng Tang
  • 2510.16252 #9 · arxiv_oai · confidence 0.70 Xianfeng Tang
  • 2501.00309 #10 · arxiv_oai · confidence 0.70 Xianfeng Tang
  • 2504.11468 #5 · arxiv_oai · confidence 0.70 Xianfeng Tang
  • 2601.12538 #23 · arxiv_oai · confidence 0.70 Xianfeng Tang

Frequent Coauthors