Paper

Chat

• Inference-only MCTS where expansion is sampling N children, evaluation is self-generated LM score + self-consistency score (max % agree)

• Also on failure, generates Reflection to inform subsequent expansions

• Paper

• Like RAP, uses MCTS over LLM, but uses actual envs

• Comparisons

  • More systematic exploration of possibilities vs ReAct
  • Better grounding through environment feedback vs ToT
  • More reliable feedback through actual interaction vs RAP's simulated outcomes

• "Since our method is based on Monte Carlo Tree Search and is model-free, one limitation of LATS on decision-making tasks is that it requires the agent to be able to revert to earlier states in the environments... this reversion property is feasible in many real-world applications (despite being not universally applicable in all possible environments)"