Research map / Multi-agent systems and games / Human-AI and goal-conditioned
MINT: Minimal Information Neuro-Symbolic Tree for Objective-Driven Knowledge-Gap Reasoning and Active Elicitation
Zeyu Fang, Mahdi Imani, Tian Lan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 MINT query elicitation instead of pure-LLM planning | MINT vs o3 / GPT-4o · MiniGrid (5 uncertain objects) | average reward: 7.81 -> 9.69 | Improved |
| use MINT instead of pure RL (DQN) under many unknown objects | DQN · MiniGrid (5 uncertain objects) | success rate (%): 15.2 -> 98.2 | Improved |
| cap number of queries per unknown object (MINT Limited vs Standard) (ablation) | MINT · MiniGrid (5 uncertain objects) | average reward: 9.69 -> 9.56 | No clear effect |
| cap number of queries (Limited vs Standard) (ablation) | MINT · Atari Pacman | return: 434.9 -> 411.1 return; 6.8 -> 3.8 queries | Mixed |
| replace expert-action queries (Query-A) with MINT binary queries | HITL-RL baseline · Atari Pacman | query times: 27.1 -> 6.8 | Improved |
| add MINT elicitation on top of LLM planning with fixed tree | LLM planner · NVIDIA Isaac hidden target (target 2) | success rate (%): 9 -> 95 (o3 vs MINT*) | Improved |
| add uncertain objects (0 to 5) for pure RL DQN | DQN · MiniGrid | average reward: 9.32 -> -2.01 | Hurt |
Closest papers by meaning
- Language Agent Tree Search Unifies Reasoning, Acting, and Planning in Language Models (ICML 2024 · similarity 0.86)
- Embodied Task Planning via Graph-Informed Action Generation with Large Language Models (ICML 2026 · similarity 0.85)
- Hierarchical Planning for Complex Tasks with Knowledge Graph-RAG and Symbolic Verification (ICML 2025 · similarity 0.85)
- PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Tasks (ICLR 2025 · similarity 0.85)
- From Assumptions to Actions: Turning LLM Reasoning into Uncertainty-Aware Planning for Embodied Agents (ICLR 2026 · similarity 0.85)
- SPIRAL: Symbolic LLM Planning via Grounded and Reflective Search (AAAI 2026 · similarity 0.85)
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.
