Introduces YesBut benchmark showing state-of-the-art multimodal models lag humans on interpreting humorous contradictions in comics.
hub
Language models, agent models, and world models: The law for machine reasoning and planning
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
SWM framework uses LLMs to model social belief dynamics from events via temporal pattern mining and ELBO optimization, outperforming time-series models on a new 12k-point benchmark from Kalshi and Polymarket prediction markets.
SR²AM achieves competitive Pass@1 accuracy on diverse tasks with 25.8-95.3% fewer reasoning tokens than much larger models by using self-regulated simulative planning trained via supervised learning and RL.
The paper maps agent memory research via three forms (token-level, parametric, latent), three functions (factual, experiential, working), and dynamics of formation/evolution/retrieval, plus benchmarks and future directions.
SiRA uses LLM world models for simulative reasoning to achieve up to 124% higher task completion and 32.2% navigation success versus reactive baselines in web environments.
Presents YesBut (V2) benchmark and shows state-of-the-art VLMs significantly underperform humans on tasks requiring comparative reasoning for contradictory humor in comics.
NormWear-2 encodes physiological signals and interventions into a shared latent space, models their joint evolution as a dynamical system, and uses chaos-theoretic balancing during pretraining to achieve superior multi-scale forecasting on diverse real-world datasets.
A comprehensive review of self-evolving AI agents that improve themselves over time, organized via a framework of inputs, agent system, environment, and optimizers, with domain-specific and safety discussions.
AppAgent lets large language models operate diverse smartphone apps via visual interactions and learns app usage from exploration or demonstrations.
A survey compiling RL methods, challenges, data resources, and applications for enhancing reasoning in large language models and large reasoning models since DeepSeek-R1.
This survey frames foundation agents using brain-inspired modular architectures and reviews challenges in evolution, collaboration, and safety.
citing papers explorer
-
Cracking the Code of Juxtaposition: Can AI Models Understand the Humorous Contradictions
Introduces YesBut benchmark showing state-of-the-art multimodal models lag humans on interpreting humorous contradictions in comics.
-
Building Social World Models with Large Language Models
SWM framework uses LLMs to model social belief dynamics from events via temporal pattern mining and ELBO optimization, outperforming time-series models on a new 12k-point benchmark from Kalshi and Polymarket prediction markets.
-
Efficient Agentic Reasoning Through Self-Regulated Simulative Planning
SR²AM achieves competitive Pass@1 accuracy on diverse tasks with 25.8-95.3% fewer reasoning tokens than much larger models by using self-regulated simulative planning trained via supervised learning and RL.
-
Memory in the Age of AI Agents
The paper maps agent memory research via three forms (token-level, parametric, latent), three functions (factual, experiential, working), and dynamics of formation/evolution/retrieval, plus benchmarks and future directions.
-
When 'YES' Meets 'BUT': Can Large Models Comprehend Contradictory Humor Through Comparative Reasoning?
Presents YesBut (V2) benchmark and shows state-of-the-art VLMs significantly underperform humans on tasks requiring comparative reasoning for contradictory humor in comics.
-
Toward World Modeling of Physiological Signals with Chaos-Theoretic Balancing and Latent Dynamics
NormWear-2 encodes physiological signals and interventions into a shared latent space, models their joint evolution as a dynamical system, and uses chaos-theoretic balancing during pretraining to achieve superior multi-scale forecasting on diverse real-world datasets.
-
A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems
A comprehensive review of self-evolving AI agents that improve themselves over time, organized via a framework of inputs, agent system, environment, and optimizers, with domain-specific and safety discussions.
-
AppAgent: Multimodal Agents as Smartphone Users
AppAgent lets large language models operate diverse smartphone apps via visual interactions and learns app usage from exploration or demonstrations.
-
Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems
This survey frames foundation agents using brain-inspired modular architectures and reviews challenges in evolution, collaboration, and safety.