Agents in the real world must make not only logical but also timely judgments. This requires continuous awareness of the dynamic environment: hazards emerge, opportunities arise, and other agents act, while the agent's reasoning is still unfolding. Despite advances in language model reasoning, existing approaches fail to account for this dynamic nature. We introduce real-time reasoning as a new problem formulation for agents in evolving environments and build Real-Time Reasoning Gym to demonstrate it. We study two paradigms for deploying language models in agents: (1) reactive agents, which employ language models with bounded reasoning computation for rapid responses, and (2) planning agents, which allow extended reasoning computation for complex problems. Our experiments show that even state-of-the-art models struggle with making logical and timely judgments in either paradigm. To address this limitation, we propose AgileThinker, which simultaneously engages both reasoning paradigms. AgileThinker consistently outperforms agents engaging only one reasoning paradigm as the task difficulty and time pressure rise, effectively balancing reasoning depth and response latency. Our work establishes real-time reasoning as a critical testbed for developing practical agents and provides a foundation for research in temporally constrained AI systems, highlighting a path toward real-time capable agents.

Malignant lymphoma subtype classification directly impacts treatment strategies and patient outcomes, necessitating classification models that achieve both high accuracy and sufficient explainability. This study proposes a novel explainable Multi-Instance Learning (MIL) framework that identifies subtype-specific Regions of Interest (ROIs) from Whole Slide Images (WSIs) while integrating cell distribution characteristics and image information. Our framework simultaneously addresses three objectives: (1) indicating appropriate ROIs for each subtype, (2) explaining the frequency and spatial distribution of characteristic cell types, and (3) achieving high-accuracy subtyping by leveraging both image and cell-distribution modalities. The proposed method fuses cell graph and image features extracted from each patch in the WSI using a Mixture-of-Experts (MoE) approach and classifies subtypes within an MIL framework. Experiments on a dataset of 1,233 WSIs demonstrate that our approach achieves state-of-the-art accuracy among ten comparative methods and provides region-level and cell-level explanations that align with a pathologist's perspectives.

Large Language Models (LLMs) have achieved significantly advanced capabilities in understanding and generating human language text, which have gained increasing popularity over recent years. Apart from their state-of-the-art natural language processing (NLP) performance, considering their widespread usage in many industries, including medicine, finance, education, etc., security concerns over their usage grow simultaneously. In recent years, the evolution of backdoor attacks has progressed with the advancement of defense mechanisms against them and more well-developed features in the LLMs. In this paper, we adapt the general taxonomy for classifying machine learning attacks on one of the subdivisions - training-time white-box backdoor attacks. Besides systematically classifying attack methods, we also consider the corresponding defense methods against backdoor attacks. By providing an extensive summary of existing works, we hope this survey can serve as a guideline for inspiring future research that further extends the attack scenarios and creates a stronger defense against them for more robust LLMs.

For mobile robots, navigating cluttered or dynamic environments often necessitates non-prehensile manipulation, particularly when faced with objects that are too large, irregular, or fragile to grasp. The unpredictable behavior and varying physical properties of these objects significantly complicate manipulation tasks. To address this challenge, this manuscript proposes a novel Reactive Pushing Strategy. This strategy allows a mobile robot to dynamically adjust its base movements in real-time to achieve successful pushing maneuvers towards a target location. Notably, our strategy adapts the robot motion based on changes in contact location obtained through the tactile sensor covering the base, avoiding dependence on object-related assumptions and its modeled behavior. The effectiveness of the Reactive Pushing Strategy was initially evaluated in the simulation environment, where it significantly outperformed the compared baseline approaches. Following this, we validated the proposed strategy through real-world experiments, demonstrating the robot capability to push objects to the target points located in the entire vicinity of the robot. In both simulation and real-world experiments, the object-specific properties (shape, mass, friction, inertia) were altered along with the changes in target locations to assess the robustness of the proposed method comprehensively.

Abstract--Assistance during eating is essential for those with severe mobility issues or eating risks. However, dependence on traditional human caregivers is linked to malnutrition, weight loss, and low self-esteem. For those who require eating assistance, a semi-autonomous robotic platform can provide independence and a healthier lifestyle. We demonstrate an essential capability of this platform: safe, comfortable, and effective transfer of a bite-sized food item from a utensil directly to the inside of a person's mouth. Our system uses a force-reactive controller to safely accommodate the user's motions throughout the transfer, allowing full reactivity until bite detection then reducing reactivity in the direction of exit. Additionally, we introduce a novel dexterous wrist-like end effector capable of small, unimposing movements to reduce user discomfort. We conduct a user study with 11 participants covering 8 diverse food categories to evaluate our system end-to-end, and we find that users strongly prefer our method to a wide range of baselines. To feed the user, it follows an arced trajectory and monitors force to detect a bite.

An intelligent agent operating in the real-world must balance achieving its goal with maintaining the safety and comfort of not only itself, but also other participants within the surrounding scene. This requires jointly reasoning about the behavior of other actors while deciding its own actions as these two processes are inherently intertwined - a vehicle will yield to us if we decide to proceed first at the intersection but will proceed first if we decide to yield. However, this is not captured in most self-driving pipelines, where planning follows prediction. In this paper we propose a novel data-driven, reactive planning objective which allows a self-driving vehicle to jointly reason about its own plans as well as how other actors will react to them. We formulate the problem as an energy-based deep structured model that is learned from observational data and encodes both the planning and prediction problems. Through simulations based on both real-world driving and synthetically generated dense traffic, we demonstrate that our reactive model outperforms a non-reactive variant in successfully completing highly complex maneuvers (lane merges/turns in traffic) faster, without trading off collision rate.

Complex environments provide structured yet variable sensory inputs. To best exploit information from these environments, organisms must evolve the ability to correctly anticipate consequences of unknown stimuli, and act on these predictions. We propose an evolutionary path for neural networks, leading an organism from reactive behavior to simple proactive behavior and from simple proactive behavior to induction-based behavior. Through in-vitro and in-silico experiments, we define the minimal conditions necessary in a network with spike-timing dependent plasticity for the organism to go from reactive to proactive behavior. Our results support the existence of small evolutionary steps and four necessary conditions allowing embodied neural networks to evolve predictive and inductive abilities from an initial reactive strategy. We extend these conditions to more general structures.

While the term Learning Analytics has been around for some time, it has been mostly restricted to data collecting from the Learning Management Systems, such as completions data. Learning Analytics has to evolve beyond simply reporting to making predictions. We discuss current trends in Learning Analytics and how xAPI, Artificial Intelligence will impact it.

Real-world artificial-intelligence applications are popping up in unexpected places--and much sooner than you might think. While winning a game of Go might be impressive, machine intelligence is also evolving to the point where it can be used by more people to do more things. That's how four engineers with almost zero knowledge of Japanese were able to create software, in just a few months, that can decipher handwriting in the language. The programmers at Reactive Inc. came up with an application that recognizes scrawled-out Japanese with 98.66 percent accuracy. The 18-month-old startup in Tokyo is part of a growing global community of coders and investors who are harnessing the power of neural networks to put AI to far more practical purposes than answering trivia or winning board games.