{"slug": "agentbrew-offline-tool-use-agent-learning-from-raw-real-world-trajectories", "title": "AgentBrew: Offline Tool-Use Agent Learning from Raw Real-World Trajectories", "summary": "AgentBrew, an offline training framework from researchers publishing on arXiv (2609.05837v1), learns tool-use policies from a single batch of raw interaction trajectories without task verifiers or iterative on-policy rollouts. On three real-world MCP applications — GitHub, Notion, and PostgreSQL — AgentBrew improved Qwen3-32B by +8.7 Acc / +9.7 Score on average, surpassing Qwen3-235B (+2.3 / +4.4) and outperforming rejection sampling (+5.9 / +10.3). The framework uses retrospective task inference to reconstruct an aligned instruction per trajectory and PMI-based credit assignment to weight policy training, with code available at https://github.com/alphatogo/AgentBrew.", "body_md": "arXiv:2609.05837v1 Announce Type: new \nAbstract: LLM-based agents are increasingly deployed in real-world applications through tool-use APIs, yet training them for specific environments remains fundamentally difficult: real-world applications provide no pre-defined tasks or verifiers, no faithful simulators, and limited budget for large-scale environment interaction. In this paper, we propose \\textbf{AgentBrew}, an offline training framework that learns effective tool-use policies from a single batch of raw interaction trajectories, without task verifiers or iterative on-policy rollouts. The agent first explores the target environment to collect a raw trajectory corpus without quality filtering. To extract training signal from this noisy corpus, \\emph{retrospective task inference} reconstructs an aligned instruction for each trajectory based on its actual outcome, and \\emph{PMI-Based credit assignment} decomposes the trajectory's total information about the inferred instruction into additive per-action credits via pointwise mutual information (PMI). These credits weight the policy training objective, amplifying informative actions while suppressing ineffective ones. On three real-world MCP applications (GitHub, Notion, PostgreSQL), AgentBrew improves Qwen3-32B by +8.7 Acc / +9.7 Score on average, surpassing Qwen3-235B (+2.3 / +4.4) and outperforming rejection sampling (+5.9 / +10.3). These results demonstrate that fine-grained offline learning can recover useful supervision from raw trajectories that filtering-based approaches would discard. The code is available at https://github.com/alphatogo/AgentBrew", "url": "https://wpnews.pro/news/agentbrew-offline-tool-use-agent-learning-from-raw-real-world-trajectories", "canonical_source": "https://www.machinebrief.com/news/agentbrew-offline-tool-use-agent-learning-from-raw-real-worl-25ly", "published_at": "2026-09-10 04:00:00+00:00", "updated_at": "2026-09-10 07:23:09.220107+00:00", "lang": "en", "topics": ["ai-agents", "ai-research", "ai-tools", "machine-learning", "natural-language-processing"], "entities": ["AgentBrew", "Qwen3-32B", "Qwen3-235B", "GitHub", "Notion", "PostgreSQL", "arXiv", "alphatogo"], "alternates": {"html": "https://wpnews.pro/news/agentbrew-offline-tool-use-agent-learning-from-raw-real-world-trajectories", "markdown": "https://wpnews.pro/news/agentbrew-offline-tool-use-agent-learning-from-raw-real-world-trajectories.md", "text": "https://wpnews.pro/news/agentbrew-offline-tool-use-agent-learning-from-raw-real-world-trajectories.txt", "jsonld": "https://wpnews.pro/news/agentbrew-offline-tool-use-agent-learning-from-raw-real-world-trajectories.jsonld"}}