Related papers: RMBench: Memory-Dependent Robotic Manipulation Ben…

Large language model (LLM) agents accumulate rich episodic trajectories while solving real-world tasks, but it remains unclear whether such experience can be distilled into reusable procedural skills. We introduce SkillEvolBench, a…

Many real-world systems, such as transportation systems, ecological systems, and Internet systems, are complex systems. As an important tool for studying complex systems, computational experiments can map them into artificial society models…

Temporal context is essential for robotic manipulation because such tasks are inherently non-Markovian, yet mainstream VLA models typically overlook it and struggle with long-horizon, temporally dependent tasks. Cognitive science suggests…

It has been arduous to assess the progress of a policy learning algorithm in the domain of hierarchical task with high dimensional action space due to the lack of a commonly accepted benchmark. In this work, we propose a new light-weight…

Referring perception, which aims at grounding visual objects with multimodal referring guidance, is essential for bridging the gap between humans, who provide instructions, and the environment where intelligent systems perceive. Despite…

Large language models (LLMs) have recently emerged as promising tools for solving challenging robotic tasks, even in the presence of action and observation uncertainties. Recent LLM-based decision-making methods (also referred to as…

Generating plans of action, and reasoning about change have long been considered a core competence of intelligent agents. It is thus no surprise that evaluating the planning and reasoning capabilities of large language models (LLMs) has…

Machine unlearning aims to erase requested data from trained models without full retraining. For Reasoning Multimodal Large Language Models (RMLLMs), this is uniquely challenging: intermediate chain-of-thought steps can still leak sensitive…

LLM-powered embodied agents have shown success on conventional object-rearrangement tasks, but providing personalized assistance that leverages user-specific knowledge from past interactions presents new challenges. We investigate these…

In high-stake scenarios like medical treatment and auto-piloting, it's risky or even infeasible to collect online experimental data to train the agent. Simulation-based training can alleviate this issue, but may suffer from its inherent…

Persistent memory is turning language-model-based agents from stateless participants in isolated interactions into state-bearing components of LLM-based multi-agent systems. As memory becomes durable, reloadable, and behavior-shaping across…

LLM-based shopping agents increasingly rely on long purchase histories and multi-turn interactions for personalization, yet naively appending raw history to prompts is often ineffective due to noise, length, and relevance mismatch. We…

Multimodal emotion recognition plays a crucial role in enhancing user experience in human-computer interaction. Over the past few decades, researchers have proposed a series of algorithms and achieved impressive progress. Although each…

Large language models (LLMs) demonstrate strong potential as agents for tool invocation due to their advanced comprehension and planning capabilities. Users increasingly rely on LLM-based agents to solve complex missions through iterative…

Multimodal large language models are increasingly deployed as long-horizon agents, where memory must do more than recall: it must track an evolving world, revise what has gone stale, and surface the right evidence at decision time. Existing…

Embodied intelligence aims to enable robots to learn, reason, and generalize robustly across complex real-world environments. However, existing approaches often struggle with partial observability, fragmented spatial reasoning, and…

Micromobility, which utilizes lightweight mobile machines moving in urban public spaces, such as delivery robots and mobility scooters, emerges as a promising alternative to vehicular mobility. Current micromobility depends mostly on human…

Big science initiatives are trying to reconstruct and model the brain by attempting to simulate brain tissue at larger scales and with increasingly more biological detail than previously thought possible. The exponential growth of parallel…

Memory-augmented conversational agents enable personalized interactions using long-term user memory and have gained substantial traction. However, existing benchmarks primarily focus on whether agents can recall and apply user information,…

The evolution of recommender systems has shifted from traditional collaborative filtering to LLM-based agentic systems, which rely on semantic user and item memories to make predictions. However, existing agents maintain these memories in…