Engineering
SHAPE of Chain-of-Thought in Math Reasoning
SHAPE is an analytical framework examining chain-of-thought reasoning in LLMs through two mathematics-education lenses: semantic spaces (different mathematical interpretations) and…
Engineering
LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation
LightNav-0 is a compact embodied-navigation model that leverages the spatial reasoning of pretrained vision-language models through a unified interface combining…
Engineering
Super Library Agent: Joint Generation and Maintenance of Multiple Applications Beyond the Single Codebase
Super Library Agent lets LLM coding agents sequentially generate multiple related applications while maintaining a shared library of reusable components,…
Engineering
Evaluating the Hidden Costs of Personalization in Large Language Models
This paper introduces PRISK, a dynamic evaluation framework with automated data generation and tailored metrics that systematically assesses unintended consequences…
Engineering
Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents
AutoSciRub generates task-specific evaluation rubrics before autonomous research agents execute scientific workflows, decomposing underspecified instructions into atomic scientific goals, grounding…
Engineering
Matrix-Game 3.5: Enhancing Real-Time Streaming Interactive World Models with Patch Memory
Matrix-Game 3.5 is an interactive world model advancing real-time streaming generation through a geometry-aware memory framework with patch-memory and tiled-PRoPE…
Engineering
Lies We Can See: Joint Verbal and Non-Verbal Deception by VLM Agents in Embodied Social Interactions
This paper introduces MineAmongUs, a 3D multimodal sandbox environment based on Among Us in which AI agents attempt deception through…
Engineering
Keep-or-Drop? Adaptive Tokenizer for Compact Video Representation
KATok is a transformer-based VAE with an adaptive token selector for more efficient video compression, evaluating each token’s informativeness and…
Engineering
Chain-of-Thought Faithfulness of Reasoning Models Varies with Where and How Preference Cues Are Delivered
This paper introduces FACE-Eval, a 5,100-sample benchmark testing how chain-of-thought faithfulness varies based on whether preference cues originate from the…
Engineering
PaperBanana-Interact: Scientific Diagram Refinement with Multi-Turn Human Feedback
PaperBanana-Interact is a multi-agent system for refining scientific diagrams through iterative human feedback, accompanied by MTPaperBananaBench, a benchmark of 292…
Engineering
Scaffolding Foundation Models into Physical-World Agents Pushes the Frontier of Long-Horizon Navigation
NavMCP integrates vision-language models with navigation foundation models through three communication channels — intent, observation, and memory — to enable…
Engineering
MNIST-PRO: MNIST is Back as a Partially Observable World for AI Agents
MNIST-PRO transforms classic MNIST digit recognition into a sequential, glimpse-based search task under partial observability, evaluating how multimodal models construct…