Flagged for: agent, agentic, tool use, tool-use
Mid-training is increasingly recognized as a critical stage for shaping the capabilities of large language models. Recent work has shown that targeted mid-training can strengthen reasoning-intensive a...
Flagged for: agent, multi-agent, autonomous, reasoning
Autonomous vehicles require robust perception and decision-making capabilities to operate in diverse and unseen scenarios. While reinforcement learning and rule-based methods can provide effective con...
Flagged for: agent, multi-agent, reasoning, rlhf
LLM-based Multi-Agent Systems (MAS) achieve strong performance on complex reasoning tasks by coordinating multiple agents, but at the cost of substantial token consumption. Recent work on automatic to...
Flagged for: agent, multi-agent, autonomous, llm
Autonomous vehicles offload latency-sensitive perception tasks to nearby mobile edge computing (MEC) servers, where a missed safety-critical task is unsafe rather than merely degraded. Large language ...
Flagged for: agent, reasoning, embodied, llm
The convergence of large language models (LLMs), structured knowledge bases (KBs), and reasoning ability (RA) presents a promising trajectory toward general embodied intelligence (GEI). This paper rev...
Flagged for: agent, multi-agent, agentic, reasoning
Large language model (LLM)-based multi-agent systems (MAS) often exhibit complex failure modes, which frequently cause agents to produce incorrect outcomes. This motivates the task of Agent Failure At...
Flagged for: agent, multi-agent, agentic, reasoning
Accurate and responsible medical question answering (QA) is important in healthcare, where complex cases require factual knowledge and nuanced reasoning. Existing medical QA systems, typically based o...
Flagged for: agent, multi-agent, planning, llm
Multi-agent Large Language Model (LLM) systems often struggle to collaborate with new teammates whose strategies shift mid-task. Because agents execute multi-step or temporally extended skills, they f...
Flagged for: agent, multi-agent, interpret, llm
Methane field monitoring requires the integration of sampling design, meteorological interpretation, sensor processing, plume analysis, visualization, and reporting, but these steps are often distribu...
Flagged for: agent, agentic, reasoning, embodied
Indoor scene synthesis provides essential environments for embodied AI, robotic manipulation, and simulation-based policy learning. Recent code-based scene generation methods produce editable and exte...
Flagged for: agi, autonomy, llm, language model
As large language models (LLMs) are granted increasing autonomy, it is essential to investigate methods that can induce unsafe behavior. We propose a novel white-box attack inspired by locate-then-edi...
Flagged for: agi, agent, multi-agent, planning
In the Lifelong Multi-Agent Path Finding (L-MAPF) problem, agents must repeatedly move from one destination to another while avoiding obstacles and inter-agent collisions. Widely regarded as one of th...
Flagged for: agent, agentic, autonomous, reasoning
Large language models are pushing data science toward increasingly autonomous and agentic workflows, with recent systems already supporting multi-step and long-running analyses. As these workflows bec...
Flagged for: agent, agentic, autonomous, llm
The evolution of artificial intelligence has necessitated a fundamental shift from evaluating isolated Large Language Models (LLMs) to assessing autonomous agentic architectures. This paper explores t...
Flagged for: agent, agentic, chain of thought, interpretability
Many areas of AI research, such as language model interpretability and chain of thought faithfulness, seek to explain model behaviors. But what constitutes a "good" explanation? In this work, we evalu...
Flagged for: agi, agent, multi-agent, autonomous
Achieving human-level competitive intelligence and physical agility in humanoid robots remains a profound challenge, particularly in contact-rich and highly dynamic tasks such as boxing. While Multi-A...
Flagged for: agent, agentic, planning, ai safety
Job Safety Analysis (JSA) and pre-task planning can benefit from prior incident records, yet historical accident data is often stored as unstructured narratives that are difficult to consult at the po...
Flagged for: agent, reasoning, embodied, robot
Large Language Models (LLMs) have demonstrated capabilities in in-context learning, task decomposition, step-by-step reasoning, and code generation, driving their gradual evolution from text generatio...
Flagged for: agi, agent, reasoning, llm
Large Language Models (LLMs) have achieved remarkable progress in code generation, yet ensuring correctness in complex, repository-level tasks remains challenging. Existing approaches often use genera...
Flagged for: agent, agentic, autonomous, llm
Large Language Models (LLMs) are increasingly being deployed in cybersecurity operations to assist cybersecurity analysts with rapid decision-making against emerging threats. However, there is a main ...
Flagged for: agent, multi-agent, agentic, scaling
Multi-modal retrieval-augmented generation (RAG) is a key technique for visually rich long document understanding. Existing multi-modal RAG methods are progressively advancing toward multi-agent syste...
Flagged for: agi, agent, agentic, llm
As agentic tasks grow in complexity, LLM agents increasingly rely on experiential memory to reuse procedural knowledge across tasks. Effective memory design must jointly address what to store, how mem...
Flagged for: agent, agentic, planning, reasoning
Vision-language Models (VLMs) excel at 2D grounding, spatial reasoning and agentic tool-based planning in static scenes. However, consider asking a home robot "Is my medication still in the cabinet?" ...
Flagged for: agent, agentic, autonomous, tool use
Large language model (LLM) agents are evolving from conversational assistants into autonomous systems that execute long-horizon tasks through reasoning, tool use, code generation, and workspace manipu...
Flagged for: agent, agentic, reasoning, llm
Spreadsheets are widely used to organize, analyze, and manipulate semi-structured data, yet automated spreadsheet reasoning remains challenging for large language models (LLMs). Real-world workbooks o...
Flagged for: agent, multi-agent, alignment, llm
Large language model based multi-agent systems usually communicate in text, i.e., using discrete tokens. However, text introduces a discrete bottleneck. Converting the sender's continuous hidden state...
Flagged for: agent, multi-agent, agentic, language model
Long-form research reports generated by large language models drift, contradict themselves, and lose provenance: the same metric appears with different values, and rumor is quoted as confidently as an...
Flagged for: agi, agent, planning, reasoning
Unmanned Aerial Vehicle Vision-Language Navigation (UAV-VLN) requires agents to follow language instructions, infer spatial structure from sparse multi-view observations, and execute feasible 3D motio...
Flagged for: agent, agentic, reasoning, interpret
Digital twins are increasingly used to monitor and simulate the behavior of cyber-physical systems. Even with skilled operators, interpreting anomalies detected within digital twin pipelines is challe...
Flagged for: agent, agentic, rlhf, llm
Modern reinforcement learning (RL) post-training pipelines for large language models (LLMs) increasingly combine rollout workloads across multiple domains and feedback paradigms. Prefix-aware routing ...
Flagged for: agi, reasoning, llm, language model
Large language models (LLMs) are increasingly deployed as mobile assistants, where a key challenge is leveraging personal information scattered across multiple applications (apps) to complete user ins...
Flagged for: agent, agentic, autonomy, planning
Advances in advanced artificial intelligence tools have sparked research in robot autonomy, but the development of such systems has largely focused on execution rather than verifying the feasibility a...
Flagged for: agent, multi-agent, reasoning, alignment
Aligning large language models (LLMs) with human values remains a major challenge, especially for trustworthy AI. While existing approaches such as RLHF, CAI, and their variants have achieved promisin...
Flagged for: agent, multi-agent, reasoning, ai safety
The malicious use of generative artificial intelligence to create highly realistic deepfake videos raises serious ethical concerns and poses substantial challenges to AI safety. However, existing deep...
Flagged for: agent, multi-agent, interpret, embodied
Large Language Models (LLMs) are increasingly used as high-level planners in embodied multi-robot systems, enabling robots to interpret natural language instructions and coordinate executable actions....
Flagged for: agi, alignment, llm, language model
Preference alignment often makes large language models (LLMs) overconfident and poorly calibrated. Traditional post-hoc temperature scaling is inherently domain-dependent: a temperature fitted on one ...
Flagged for: alignment, value alignment, llm, language model
As Large Language Models (LLMs) are increasingly used as a primary source of information and advice, understanding their alignment to humans in terms of values becomes a pressing concern. A growing li...
Flagged for: foundation model, alignment, embodied, robot
Open-source robotics and foundation models have lowered the barrier to embodied AI, yet language-guided laboratory automation still requires reliable alignment from instructions and observations to sa...
Flagged for: agent, multi-agent, reasoning, llm
Electronic health record (EHR) feature engineering is a major bottleneck in clinical research and AI, accounting for 39-45% of data scientists' workload. This is especially pronounced in heart failure...
Flagged for: agi, agent, agentic, llm
With increasingly diverse and heterogeneous information sources, effectively leveraging multimodal data is becoming pivotal for high-quality financial trading. Although recent advancements in Large La...
Flagged for: agi, agent, embodied, robot
Vision-language-action (VLA) models have demonstrated remarkable capabilities in robotic manipulation by leveraging pretrained vision-language models. However, existing post-training methods predomina...
Flagged for: agent, reasoning, alignment, language model
Search agents extend large language models beyond static parametric memory by enabling them to acquire and use ex ternal evidence during multi-step reasoning. For knowledge intensive tasks involving c...
Flagged for: agent, multi-agent, reasoning, llm
Orchestrated collectives of large language model (LLM) agents that debate and vote are an emerging form of computational intelligence: the intelligent behaviour resides in the \emph{interaction}, not ...
Flagged for: agent, multi-agent, planning, reasoning
We present a structured large-language-model (LLM) architecture for zero-shot human--robot coordination in a cooperative construction task with private goal views. Guided by a Dec-POMDP formulation, t...
Flagged for: agent, autonomous, tool-use, planning
Large Language Models (LLMs) have recently shown strong capabilities in reasoning, planning, and tool-use, enabling new forms of autonomous agents. However, LLM-based agents struggle with long-horizon...
Flagged for: agi, agent, agentic, llm
Agentic code generation has shown promise in automating and accelerating software development by utilizing Large Language Models (LLMs) to generate, test, and deploy code. For engineers and scientists...
Flagged for: agi, agent, agentic, humanoid
Humanoid robots have the potential to perform dexterous manipulation in human environments, yet acquiring diverse and generalizable skills remains costly due to expensive hardware data collection and ...
Flagged for: agent, autonomous, planning, alignment
Recent advances in Reinforcement Learning (RL) have substantially improved the capabilities of autonomous search agents, enabling sophisticated planning, and iterative retrieval over dynamic informati...
Flagged for: agent, multi-agent, agentic, llm
Large language models (LLMs) are integral to complex intellectual tasks, yet output quality remains constrained by user-provided prompts. Iterative multi-turn prompting often leads to context degradat...
Flagged for: agent, multi-agent, autonomous, planning
Large language models are increasingly integrated into autonomous robotic systems for task planning and control, but this integration exposes them to prompt injection attacks that can lead to unsafe d...
Flagged for: agent, multi-agent, agentic, llm
Multi-agent LLM pipelines orchestrate multiple specialized language model agents into structured workflows where intermediate outputs are passed across agents to solve complex tasks. This design intro...
Flagged for: agent, multi-agent, agentic, autonomous
Modern neuroscience relies on integrating multi-scale, multimodal datasets to uncover the neural principles underlying intelligence. However, analytical challenges posed by highly heterogeneous data a...
Flagged for: agi, world model, agent, planning
Building generalizable agents for diverse applications remains a fundamental challenge. While imitation learning-based policies succeed in specific training environments, they often fail to generalize...
Flagged for: world model, reasoning, embodied, robot
This exploratory study examines whether a large multimodal language model, GPT-5.1, can serve as the high-level controller of a physical mobile robot despite having no prior embodiment, no training in...
Flagged for: agi, agent, multi-agent, llm
This paper studies the behavior of language models in a multi-agent crowd simulation, focusing on how affect propagates among agents that perceive and appraise one another. Each agent perceives its ne...
Flagged for: agent, agentic, reasoning, llm
Large language models (LLMs) and AI agents have demonstrated strong potential for data integration in zero-shot and few-shot settings. However, they continue to face significant accuracy and cost chal...
Flagged for: agent, agentic, autonomous, reasoning
Large Language Models (LLMs) are increasingly deployed as autonomous agents, transitioning from static conversational interfaces to dynamic systems capable of complex reasoning, tool execution, and de...
Flagged for: agent, autonomous, reasoning, embodied
Multimodal Large Language Models (MLLMs) are emerging as core reasoning modules for embodied agents, yet it remains unclear how well general-purpose models can solve long-horizon embodied tasks from a...
Flagged for: agi, agent, multi-agent, llm
Communication allows large language model agents to pool evidence, but it also creates paths along which an erroneous claim can spread. We formulate a correction-aware network model that tracks suscep...
Flagged for: self-improving, agent, agentic, llm
Automating theoretical research is constrained not only by the generation of candidate results, but also by their reliable evaluation. A common approach is to close the research loop with a large lang...