{"id":"2505.03792","title":"Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning","url":"https://codeofpaper.com/paper/2505.03792","arxiv_url":"https://arxiv.org/abs/2505.03792","published":"2025-05-01","code":"community","best":{"full_name":"langfengQ/CoSo","url":"https://github.com/langfengQ/CoSo","tier":"high_confidence_community","stars":15,"license":"Apache-2.0","framework":null,"language":"Python","last_commit":"2025-06-12T04:44:59"},"most_starred_community":null,"implementations":[{"full_name":"langfengQ/CoSo","url":"https://github.com/langfengQ/CoSo","tier":"high_confidence_community","stars":15,"license":"Apache-2.0","framework":null,"language":"Python","last_commit":"2025-06-12T04:44:59"}],"possible_matches":0}