Agent-RLVR: Training Software Engineering Agents via Guidance and Environment Rewards

Documenti analoghi

• Adaptive Guidance Accelerates Reinforcement Learning of Reasoning Models
  di: Nath, Vaskar, et al.
  Pubblicazione: (2025)
• Learning Goal-Conditioned Representations for Language Reward Models
  di: Nath, Vaskar, et al.
  Pubblicazione: (2024)
• Terminal-World: Scaling Terminal-Agent Environments via Agent Skills
  di: Cheng, Zihao, et al.
  Pubblicazione: (2026)
• Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains
  di: Gunjal, Anisha, et al.
  Pubblicazione: (2025)
• Agents in Software Engineering: Survey, Landscape, and Vision
  di: Wang, Yanlin, et al.
  Pubblicazione: (2024)