Research map / Multi-agent systems and games / LLM agents
AdaPlanner: Adaptive Planning from Feedback with Language Models
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use adaptive closed-loop plan refinement rather than fixed-plan feedback adaptation | LLM agents · ALFWorld | success rate: 91.79 vs. 88.06 | Helped |
| Use adaptive closed-loop plan refinement rather than fixed-plan feedback adaptation | LLM agents · MiniWoB++ with feedback | success rate: 91.11 vs. 81.56 | Helped |
| Remove the code interface and use natural-language plans and actions (ablation) | AdaPlanner · ALFWorld | success rate: 81% to 46% | Hurt |
| Remove the code interface and use natural-language plans and actions (ablation) | AdaPlanner · MiniWoB++ | success rate: 93% to 66% | Hurt |
| Add skill discovery that stores successful plans as few-shot exemplars (ablation) | AdaPlanner · ALFWorld | success rate | Helped |
| Add skill discovery that stores successful plans as few-shot exemplars (ablation) | AdaPlanner · MiniWoB++ | success rate | Helped |
| Increase the number of closed-loop plan refinements (ablation) | AdaPlanner · ALFWorld | success rate | Helped |
Closest papers by meaning
- LLMs Can Plan Only If We Tell Them (ICLR 2025 · similarity 0.90)
- From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systems (ICML 2024 · similarity 0.89)
- AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learning (NeurIPS 2024 · similarity 0.89)
- Reason for Future, Act for Now: A Principled Architecture for Autonomous LLM Agents (ICML 2024 · similarity 0.89)
- Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks (ICML 2025 · similarity 0.89)
- Language Control Diffusion: Efficiently Scaling through Space, Time, and Tasks (ICLR 2024 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.