{
  "id": "2407.14414",
  "version": "v1",
  "published": "2024-07-19T15:40:59.000Z",
  "updated": "2024-07-19T15:40:59.000Z",
  "title": "System-1.x: Learning to Balance Fast and Slow Planning with Language Models",
  "authors": [
    "Swarnadeep Saha",
    "Archiki Prasad",
    "Justin Chih-Yao Chen",
    "Peter Hase",
    "Elias Stengel-Eskin",
    "Mohit Bansal"
  ],
  "comment": "29 pages (10 tables)",
  "categories": [
    "cs.AI",
    "cs.CL",
    "cs.LG"
  ],
  "abstract": "Language models can be used to solve long-horizon planning problems in two distinct modes: a fast 'System-1' mode, directly generating plans without any explicit search or backtracking, and a slow 'System-2' mode, planning step-by-step by explicitly searching over possible actions. While System-2 is typically more effective, it is also more computationally expensive, making it infeasible for long plans or large action spaces. Moreover, isolated System-1 or 2 ignores the user's end goals, failing to provide ways to control the model's behavior. To this end, we propose the System-1.x Planner, a controllable planning framework with LLMs that is capable of generating hybrid plans and balancing between the two planning modes based on the difficulty of the problem at hand. System-1.x consists of (i) a controller, (ii) a System-1 Planner, and (iii) a System-2 Planner. Based on a user-specified hybridization factor (x) governing the mixture between System-1 and 2, the controller decomposes a problem into sub-goals, and classifies them as easy or hard to be solved by either System-1 or 2, respectively. We fine-tune all three components on top of a single base LLM, requiring only search traces as supervision. Experiments with two diverse planning tasks -- Maze Navigation and Blocksworld -- show that our System-1.x Planner outperforms a System-1 Planner, a System-2 Planner trained to approximate A* search, and also a symbolic planner (A*). We demonstrate the following key properties of our planner: (1) controllability: increasing the hybridization factor (e.g., System-1.75 vs 1.5) performs more search, improving performance, (2) flexibility: by building a neuro-symbolic variant with a neural System-1 and a symbolic System-2, we can use existing symbolic methods, and (3) generalizability: by being able to learn from different search algorithms, our method is robust to the choice of search algorithm.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2024-07-19T15:40:59.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "language models",
      "balance fast",
      "slow planning",
      "search algorithm",
      "hybridization factor"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 29,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}