📄 TAPE: Tool-Guided Adaptive Planning and Constrained Execution in Language Model Agents
👥 Authors: Jongwon Jeong, Jungtaek Kim, Kangwook Lee
📅 Published: 2026-02-23
🔥 Upvotes: 3
🎯 What This Research Is About
Language Model (LM) agents have demonstrated remarkable capabilities in solving tasks that require multiple interactions with the environment. However, they remain vulnerable in environments where a single error often leads to irrecoverable failure, particularly under strict feasibility constraints. We systematically analyze existing agent frameworks, identifying imperfect planning and stochastic execution as the primary causes. To address these challenges, we propose Tool-guided Adaptive Planning with constrained Execution (TAPE). TAPE enhances planning capability by aggregating multiple plans into a graph and employing an external solver to identify a feasible path. During execution, TAPE employs constrained decoding to reduce sampling noise, while adaptively re-planning whenever environmental feedback deviates from the intended state. Experiments across Sokoban, ALFWorld, MuSiQue, and GSM8K-Hard demonstrate that TAPE consistently outperforms existing frameworks, with particularly large gains on hard settings, improving success rates by 21.0 percentage points on hard settings on average, and by 20.0 percentage points for weaker base models on average. Code and data available at here.
💡 Why This Matters
- Enhanced Reliability: TAPE addresses a critical vulnerability in LM agents by preventing premature tool execution in environments where actions have sequential dependencies.
- Adaptive Planning: The framework uses tool signatures to guide the planning process, ensuring agents understand constraints before taking action.
- Practical Applications: This approach is particularly valuable for real-world scenarios like database management, API interactions, and multi-step workflows where mistakes can be costly.
Curated from Hugging Face daily papers by AI Curator