# MINT: Minimal Information Neuro-Symbolic Tree for Objective-Driven Knowledge-Gap Reasoning and Active Elicitation

arXiv: https://arxiv.org/abs/2602.05048 · HTML: https://mlsanity.com/paper/2602.05048/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 35 of its 63 references that are in the map.
- First posted on arXiv 4 Feb 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 30 of 35)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents](https://mlsanity.com/paper/2201.07207/) (2022)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [TravelPlanner: A Benchmark for Real-World Planning with Language Agents](https://mlsanity.com/paper/2402.01622/) (2024)
- [On the Utility of Learning about Humans for Human-AI Coordination](https://mlsanity.com/paper/1910.05789/) (2019)
- [Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks](https://mlsanity.com/paper/2306.13831/) (2023)
- [Programmatically Interpretable Reinforcement Learning](https://mlsanity.com/paper/1804.02477/) (2018)
- [Visualizing and Understanding Atari Agents](https://mlsanity.com/paper/1711.00138/) (2017)
- [SmartPlay: A Benchmark for LLMs as Intelligent Agents](https://mlsanity.com/paper/2310.01557/) (2023)
- [Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs](https://mlsanity.com/paper/2110.05038/) (2021)
- [Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability](https://mlsanity.com/paper/2107.06277/) (2021)
- [SDRL: Interpretable and Data-efficient Deep Reinforcement Learning Leveraging Symbolic Planning](https://mlsanity.com/paper/1811.00090/) (2018)
- [Help me write a poem: Instruction Tuning as a Vehicle for Collaborative Poetry Writing](https://mlsanity.com/paper/2210.13669/) (2022)
- [Estimating Risk and Uncertainty in Deep Reinforcement Learning](https://mlsanity.com/paper/1905.09638/) (2019)
- [Memory-based Deep Reinforcement Learning for POMDPs](https://mlsanity.com/paper/2102.12344/) (2021)
- [A Review of Uncertainty for Deep Reinforcement Learning](https://mlsanity.com/paper/2208.09052/) (2022)
- [Think, Act, and Ask: Open-World Interactive Personalized Robot Navigation](https://mlsanity.com/paper/2310.07968/) (2023)
- [LLM A*: Human in the Loop Large Language Models Enabled A* Search for Robotics](https://mlsanity.com/paper/2312.01797/) (2023)
- [Lipschitz Lifelong Reinforcement Learning](https://mlsanity.com/paper/2001.05411/) (2020)
- [End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations](https://mlsanity.com/paper/2403.12451/) (2024)
- [Language and Sketching: An LLM-driven Interactive Multimodal Multitask Robot Navigation Framework](https://mlsanity.com/paper/2311.08244/) (2023)
- [InSPO: Unlocking Intrinsic Self-Reflection for LLM Preference Optimization](https://mlsanity.com/paper/2512.23126/) (2025)
- [Asking for Knowledge: Training RL Agents to Query External Knowledge Using Language](https://mlsanity.com/paper/2205.06111/) (2022)
- [Symbolic Visual Reinforcement Learning: A Scalable Framework with Object-Level Abstraction and Differentiable Expression Search](https://mlsanity.com/paper/2212.14849/) (2022)
- [Decision Making for Human-in-the-loop Robotic Agents via Uncertainty-Aware Reinforcement Learning](https://mlsanity.com/paper/2303.06710/) (2023)
- [Learning from Random Demonstrations: Offline Reinforcement Learning with Importance-Sampled Diffusion Models](https://mlsanity.com/paper/2405.19878/) (2024)
- [Lipschitz Lifelong Monte Carlo Tree Search for Mastering Non-Stationary Tasks](https://mlsanity.com/paper/2502.00633/) (2025)
- [A Neurosymbolic Framework for Interpretable Cognitive Attack Detection in Augmented Reality](https://mlsanity.com/paper/2508.09185/) (2025)

## Built on by (most cited first, 4 of 4)

- [NonZero: Interaction-Guided Exploration for Multi-Agent Monte Carlo Tree Search](https://mlsanity.com/paper/2605.00751/) (2026)
- [Reasoning Knowledge-Gap in Drone Planning via LLM-based Active Elicitation](https://mlsanity.com/paper/2603.07824/) (2026)
- [TIPS: Topological Ill-Posedness Probing and Steering in Large Language Models](https://mlsanity.com/paper/2606.23590/) (2026)
- [FlowEdit: Information-Theoretic Control of LLM Reasoning Flows for Ill-posed Problems Involving Conflicts](https://mlsanity.com/paper/2607.20500/) (2026)

## Abstract (arXiv)

Joint planning through language-based interactions is a key area of human-AI teaming. Planning problems in the open world often involve various aspects of incomplete information and unknowns, e.g., objects involved, human goals/intents -- thus leading to knowledge gaps in joint planning. We consider the problem of discovering optimal interaction strategies for AI agents to actively elicit human inputs in object-driven planning. To this end, we propose Minimal Information Neuro-Symbolic Tree (MINT) to reason about the impact of knowledge gaps and leverage self-play with MINT to optimize the AI agent's elicitation strategies and queries. More precisely, MINT builds a symbolic tree by making propositions of possible human-AI interactions and by consulting a neural planning policy to estimate the uncertainty in planning outcomes caused by remaining knowledge gaps. Finally, we leverage LLM to search and summarize MINT's reasoning process and curate a set of queries to optimally elicit human inputs for best planning performance. By considering a family of extended Markov decision processes with knowledge gaps, we analyze the return guarantee for a given MINT with active human elicitation. Our evaluation on three benchmarks involving unseen/unknown objects of increasing realism shows that MINT-based planning attains near-expert returns by issuing a limited number of questions per task while achieving significantly improved rewards and success rates.