Papers

• CSPF: A Constrained Shared-Private Fusion Method for Non-Verifiable Preference Evaluation (2026)
  Hehao Zhang et al.
  5.01
• Web-Shepherd: Advancing PRMs for Reinforcing Web Agents (2025)
  Hyungjoo Chae et al.
  2.82
• Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL (2025)
  Mohammadreza Pourreza et al.
  2.71
• R^3-SQL: Ranking Reward and Resampling for Text-to-SQL (2026)
  Hojae Han et al.
  1.94
• SQL-Trail: Multi-Turn Reinforcement Learning with Interleaved Feedback for Text-to-SQL (2026)
  Harper Hua et al.
  1.67
• SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters (2025)
  Teng Xiao et al.
  1.06
• Exploring Chain-of-Thought Style Prompting for Text-to-SQL (2023)
  Chang-You Tai et al.
  —
• WEPO: Web Element Preference Optimization for LLM-based Web Navigation (2024)
  Jiarun Liu et al.
  —
• Advancing LLM Reasoning Generalists with Preference Trees (2024)
  Lifan Yuan et al.
  —
• Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs (2024)
  Xin Lai et al.
  —
• SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models (2024)
  Jiale Cheng et al.
  —