Costa, L., & Oliveira e Souza Filho, J. (2025). LLM Agents for Search via Reinforcement Learning with Trajectory-Level Self-Evaluation. In Anais do XXII Encontro Nacional de InteligĂȘncia Artificial e Computacional, (pp. 1221-1232). Porto Alegre: SBC. doi:10.5753/eniac.2025.14460