# Learning and Leveraging Verifiers to Improve Planning Capabilities of Pre-trained Language Models

arXiv: https://arxiv.org/abs/2305.17077 · HTML: https://mlsanity.com/paper/2305.17077/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 9 of its 15 references that are in the map.
- First posted on arXiv 26 May 2023.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [Generating Natural Language Proofs with Verifier-Guided Search](https://mlsanity.com/paper/2205.12443/) (2022)
- [Plansformer: Generating Symbolic Plans using Transformers](https://mlsanity.com/paper/2212.08681/) (2022)
- [Discovering Underlying Plans Based on Shallow Models](https://mlsanity.com/paper/1803.02208/) (2018)

## Built on by (most cited first, 10 of 10)

- [AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation](https://mlsanity.com/paper/2408.00764/) (2024)
- [LLMs as Planning Formalizers: A Survey for Leveraging Large Language Models to Construct Automated Planning Models](https://mlsanity.com/paper/2503.18971/) (2025)
- [Learning adaptive planning representations with natural language guidance](https://mlsanity.com/paper/2312.08566/) (2023)
- [LLaMAR: Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments](https://mlsanity.com/paper/2407.10031/) (2024)
- [SELF-[IN]CORRECT: LLMs Struggle with Discriminating Self-Generated Responses](https://mlsanity.com/paper/2404.04298/) (2024)
- [Conveyor: Efficient Tool-aware LLM Serving with Tool Partial Execution](https://mlsanity.com/paper/2406.00059/) (2024)
- [DKPROMPT: Domain Knowledge Prompting Vision-Language Models for Open-World Planning](https://mlsanity.com/paper/2406.17659/) (2024)
- [Enhance Multimodal Consistency and Coherence for Text-Image Plan Generation](https://mlsanity.com/paper/2506.11380/) (2025)
- [Direct-Inverse Prompting: Analyzing LLMs' Discriminative Capacity in Self-Improving Generation](https://mlsanity.com/paper/2407.11017/) (2024)
- [A complementary study on PlanGPT: Evaluation with defined Performance Metrics and comparison with a planner](https://mlsanity.com/paper/2606.10489/) (2026)

## Abstract (arXiv)

There have been wide spread claims in the literature about the emergent reasoning capabilities of Pretrained Large Language Models. However, recent studies, have found that their ability to plan remains questionable. Through our experiments using GPT-2, we empirically demonstrate that the performance of a finetuned baseline remains poor because it violates pre-conditions of actions in the plans that it generates. To improve the planning capabilities of a finetuned LLM, we train a verifier, which can classify actions as being valid or invalid in a particular state. By randomly sampling actions from the same dataset, we generate examples of invalid actions which are then used to train a verifier which can check for action applicability. In the presence of diverse sampling from a generator and a verifier which can prune invalid trajectories, we show significant gains in the success rate on the Blocksworld domain. Additionally, we show that finetuning the GPT-2 generator itself to create the verifier generalizes better than finetuning the base GPT-2. Lastly, we investigate the role of the sampling temperature which can be used to control the exploration-exploitation tradeoff.