State-conditioned commitment depth in a vision-language policy Pareto-dominates fixed-depth baselines on Sliding Puzzle and Sokoban, raising solve rates by up to 12.5 points while using 25% fewer actions and beating larger models.
Visual sketchpad: Sketching as a visual chain of thought for multimodal language models
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
ToolsRL trains MLLMs via a tool-specific then accuracy-focused RL curriculum to master visual tools for complex reasoning tasks.
ReFineVLA adds teacher-generated reasoning steps to VLA training and reports state-of-the-art success rates on SimplerEnv WidowX and Google Robot benchmarks.
MAG-3D is a training-free multi-agent framework that coordinates planning, grounding, and coding agents with off-the-shelf VLMs to achieve grounded 3D reasoning and state-of-the-art benchmark results.
UnAC improves LMM performance on visual reasoning benchmarks by combining adaptive visual prompting, image abstraction, and gradual self-checking.
citing papers explorer
-
When to Re-Commit: Temporal Abstraction Discovery for Long-Horizon Vision-Language Reasoning
State-conditioned commitment depth in a vision-language policy Pareto-dominates fixed-depth baselines on Sliding Puzzle and Sokoban, raising solve rates by up to 12.5 points while using 25% fewer actions and beating larger models.
-
Visual Reasoning through Tool-supervised Reinforcement Learning
ToolsRL trains MLLMs via a tool-specific then accuracy-focused RL curriculum to master visual tools for complex reasoning tasks.
-
ReFineVLA: Multimodal Reasoning-Aware Generalist Robotic Policies via Teacher-Guided Fine-Tuning
ReFineVLA adds teacher-generated reasoning steps to VLA training and reports state-of-the-art success rates on SimplerEnv WidowX and Google Robot benchmarks.
-
MAG-3D: Multi-Agent Grounded Reasoning for 3D Understanding
MAG-3D is a training-free multi-agent framework that coordinates planning, grounding, and coding agents with off-the-shelf VLMs to achieve grounded 3D reasoning and state-of-the-art benchmark results.
-
UnAC: Adaptive Visual Prompting with Abstraction and Stepwise Checking for Complex Multimodal Reasoning
UnAC improves LMM performance on visual reasoning benchmarks by combining adaptive visual prompting, image abstraction, and gradual self-checking.