The paper proposes Continuous Reasoning for Vision-Language-Action (VLA) models, arguing that effective reasoning must be a shared, verifiable internal latent space rather than discrete text tokens, l…

This paper evaluates the causal reasoning abilities of large language models and finds that they rely heavily on lexical pattern matching rather than structural reasoning.

The paper introduces pause-and-think-T, a reasoning-centric dataset and benchmark that enables compact Vision-Language Models to perform visually grounded, context-aware action suggestion, matching la…

This paper introduces interpretability-guided, training-free interventions that systematically improve the accuracy and controllability of latent reasoning in LLMs by leveraging structural and causal…

The paper introduces MindClaw, a closed-loop framework that enables embodied agents to perform real-time mental-state reasoning and intervene with precision, significantly outperforming standard VLM b…

The paper formally addresses the challenging question of cross-domain transferability of latent predictive models by proposing a structured framework that quantifies the relationship between source an…

This paper localizes the attention heads within LLMs responsible for specific reasoning steps, finding that specialized heads handle factual retrieval while higher layers manage global information int…

The paper argues that for embodied AI to be safe and effective, world models must be physically viable, requiring a structural shift from mere observation prediction to representing the underlying phy…

The paper proposes Visual Gradient Steering (VGS), a method that decomposes the distillation loss into language and visual components and steers the optimization to prioritize visual grounding, signif…

The paper introduces a multilingual benchmark (MentalMap) to test if LLMs build internal spatial world models from text, finding a universal 'L3 reasoning cliff' suggesting that text-only working memo…

This paper introduces MCTS-Guided Group Relative Policy Optimization (M-GRPO) to enhance LLM spatial reasoning by improving the decomposition of complex tasks into optimal sub-tasks.

The paper introduces SpatialAct, a challenging benchmark that reveals a significant 'reasoning-to-action gap,' showing that current VLMs struggle to maintain coherent spatial understanding and perform…

The paper investigates how LLMs allocate their internal computational depth during multi-turn agentic planning, finding that agents progressively recruit deeper layers and shift toward corrective upda…

The paper introduces ForeSci, a novel benchmark that evaluates LLM agents' ability to make forward-looking research judgments using only historical evidence, finding that explicit evidence organizatio…

The paper systematically evaluates concept-based explainability in MLLMs, finding that forcing models to generate formal explanations degrades predictive accuracy, suggesting that explaining is genuin…

The paper introduces ERGeoBench, a comprehensive diagnostic benchmark designed to evaluate the fine-grained capabilities of multimodal large language models (MLLMs) for embodied geo-localization acros…

PhyDrawGen is a neuro-symbolic pipeline that generates physically accurate diagrams from natural language by explicitly enforcing physical laws and geometric constraints, significantly outperforming c…

This paper synthesizes over 150 scattered studies and reports to provide the first comprehensive primer on post-training reasoning data, organizing the field around data objects, utility, construction…