Related papers: PRISM: : Planning and Reasoning with Intent in Sim…

Programmatic video generation through code offers geometric precision and temporal coherence beyond pixel-level diffusion models, yet rigorously evaluating whether language models can produce spatially correct animated outputs remains an…

This paper explores the spatial reasoning capability of large language models (LLMs) over textual input through a suite of five tasks aimed at probing their spatial understanding and computational abilities. The models were tested on both…

Recent advances in vision-language models (VLMs) have shown promise for human-level embodied intelligence. However, existing benchmarks for VLM-driven embodied agents often rely on high-level commands or discretized action spaces, which are…

Language model (LM)-based agents have demonstrated promising capabilities in automating complex tasks from natural language instructions, yet they continue to struggle with long-horizon planning and reasoning. To address this, we propose an…

Planning is central to agents and agentic AI. The ability to plan, e.g., creating travel itineraries within a budget, holds immense potential in both scientific and commercial contexts. Moreover, optimal plans tend to require fewer…

With the rapid progress of large language models (LLMs), financial information retrieval has become a critical industrial application. Extracting task-relevant information from lengthy financial filings is essential for both operational and…

Hallucinations pose critical risks for large language model (LLM)-based agents, often manifesting as hallucinative actions resulting from fabricated or misinterpreted information within the cognitive context. While recent studies have…

Leveraging Multi-modal Large Language Models (MLLMs) to create embodied agents offers a promising avenue for tackling real-world tasks. While language-centric embodied agents have garnered substantial attention, MLLM-based embodied agents…

Coding agents represent a new paradigm in automated software engineering, combining the reasoning capabilities of Large Language Models (LLMs) with tool-augmented interaction loops. However, coding agents still have severe limitations.…

Embodied intelligence, a grand challenge in artificial intelligence, is fundamentally constrained by the limited spatial understanding and reasoning capabilities of current models. Prevailing efforts to address this through enhancing…

We present PRISM (Policy Reuse via Interpretable Strategy Mapping), a framework that grounds reinforcement learning agents' decisions in discrete, causally validated concepts and uses those concepts as a zero-shot transfer interface between…

While Multimodal Large Language Models (MLLMs) have achieved impressive performance on semantic tasks, their spatial intelligence--crucial for robust and grounded AI systems--remains underdeveloped. Existing benchmarks fall short of…

Large Language Models are increasingly proposed as cognitive components for robotic systems, yet their opaque decision processes make it difficult to explain success or failure in closed-loop embodied tasks. Following an empirical AI…

Automated interpretability research aims to identify concepts encoded in neural network features to enhance human understanding of model behavior. Within the context of large language models (LLMs) for natural language processing (NLP),…

As LLMs are increasingly deployed as agents, agentic reasoning - the ability to combine tool use, especially search, and reasoning - becomes a critical skill. However, it is hard to disentangle agentic reasoning when evaluated in complex…

This study focuses on using large language models (LLMs) as a planner for embodied agents that can follow natural language instructions to complete complex tasks in a visually-perceived environment. The high data cost and poor sample…

Embodied agents face significant challenges when tasked with performing actions in diverse environments, particularly in generalizing across object types and executing suitable actions to accomplish tasks. Furthermore, agents should exhibit…

Large language models (LLMs) are revolutionizing education, with LLM-based agents playing a key role in simulating student behavior. A major challenge in student simulation is modeling the diverse learning patterns of students at various…

Large language models have demonstrated remarkable capabilities across diverse reasoning tasks, yet their performance on algorithmic reasoning remains limited. To handle this limitation, we propose PRIME (Policy-Reinforced Iterative…

As data-science agents shift from co-pilots to auto-pilots, silent misframing becomes a critical failure mode. Agents quietly commit to plausible but unintended task framings, producing clean, executable artifacts that hide their incorrect…