DuoGate: Action and Context Control for Reliable Language Agents

LLM agents can report success without executing the actions a task requires. When runtime checks correct such failures, their explanations provide learning signals beyond the final task outcome. Using this feedback effectively requires deciding when an interaction warrants learning and which lessons to retain. We introduce DuoGate, a framework that connects action control with selective context adaptation through execution feedback. Its action branch checks selected proposals against available evidence, directs recovery toward detected gaps, and preserves correction feedback for learning. Its context branch uses outcomes and execution signals to select learning updates. For these updates, a reflection and curation workflow derives candidate guidance from the interaction and correction reasons. Separate admission checks screen this guidance before it enters a playbook for later prompts, so an intervention need not become a retained lesson. We evaluate DuoGate on AppWorld, ${\tau }^2$-Bench, and Terminal-Bench 2, finding higher mean completion than the adaptive context baseline across all three benchmarks. With MiniMax M2.7, DuoGate raises AppWorld task completion from the baseline's 60.7% to 69.2% and scenario completion from 41.7% to 54.2%. These results demonstrate the complementary benefits of action control and context adaptation, highlighting correction feedback as an effective signal for learning from execution. Code: https://anonymous.4open.science/r/DuoGate-56CF/.