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: agent, reasoning, deceptive, llm
As large language models (LLMs) are deployed as agents in high-stakes settings, such as medical and legal systems, understanding their deceptive capabilities is fundamental to safety. Controlled socia...
Flagged for: agent, multi-agent, reasoning, llm
Multi-agent LLM pipeline systems break down the task among multiple roles for better reasoning, but are benchmarked mainly with large-scale commercial models. In this study, we investigate Parishad, a...
Flagged for: agi, world model, agent, planning
World models offer a promising route toward robot planning by enabling agents to imagine and verify the consequences of actions before execution. However, current video-based world models often strugg...
Flagged for: agent, autonomous, deceptive, llm
Large language model (LLM) agents automate penetration testing through an observation-action loop, selecting actions based on observations returned by tools. This dependence allows defenders to inject...
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, autonomous, reasoning
Autonomous LLM agents processing mixed-confidentiality data face severe security risks from prompt injection attacks and reasoning errors. While dynamic Information Flow Control (IFC) provides structu...
Flagged for: foundation model, agent, alignment, embodied
Multimodal foundation models learned to see and to speak by consuming the whole internet. Embodied agents admit no such shortcut, since they require data that couple observations with physical states ...
Flagged for: agent, reasoning, interpret, robot
While vision-language-action models have demonstrated impressive zero-shot manipulation capabilities, they remain fundamentally black box policies that are difficult to interpret, adapt, or correct wh...
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...
Flagged for: agent, agentic, reasoning, llm
Brain network analysis is crucial for understanding cognition and neurological disorders, yet existing deep learning methods mainly treat connectome analysis as a graph-to-logit classification problem...
Flagged for: agi, llm, language model, retrieval
Historical documents act as invaluable knowledge archives but often suffer from illegibility due to physical deterioration and damage. While existing restoration methods based on masked language model...
Flagged for: agi, agent, agentic, reasoning
Production AI agents' failures are less often due to an inability to reason well and more often because they cannot manage what is in their reasoning context: conversation histories, large prompts, la...
Flagged for: agent, tool use, reasoning, llm
Large language model (LLM)-based agents increasingly rely on reasoning, tool use, and iterative execution, yet existing agent frameworks still operate largely in isolation. While recent memory-based a...
Flagged for: agi, foundation model, agent, agentic
Creating dynamic and physically realistic 4D worlds from natural language descriptions is both fascinating and challenging. Traditional computer graphics methods rely on manual creation, requiring ext...
Flagged for: agi, interpret, llm, language model
Large Language Models (LLMs) have demonstrated remarkable ability in generating personalized content by leveraging user histories and contextual cues. However, most existing personalization approaches...
Flagged for: agi, agent, reasoning, llm
Long-horizon tasks require sustained perception, reasoning, and exploration, and are a persistent challenge for large language model (LLM) agents. This gap is reflected in their limited performance on...
Flagged for: alignment, value alignment, llm, language model
With the wide application of large language models (LLMs) in real-world scenarios, the value implication of their outputs is crucial. However, existing evaluation benchmarks suffer from insufficient c...
Flagged for: agi, llm, language model, retrieval
Hypergraph-based RAG systems surpass traditional graph-based approaches by organizing complex n-ary atomic facts among entities, rather than relying solely on binary relationships. Despite the advance...
Flagged for: agi, reasoning, robot, language model
Vision-language models have shown strong potential for social robot navigation by leveraging rich semantic understanding of complex environments and human behaviors. However, large scale VLMs are diff...
Flagged for: world model, foundation model, agent, agentic
Real-to-sim conversion for robotic interaction with objects remains labor-intensive because it requires more than visual reconstruction: a streamlined real2sim process must recover scene geometries an...
Flagged for: agi, alignment, llm, language model
Can large language models with substantially different parameter spaces be merged by direct weighted averaging, without training or semantic alignment? Existing heterogeneous fusion methods typically ...
Flagged for: agent, multi-agent, llm, language model
Researchers need to answer ad-hoc questions about the contents of domain-specific archives but often lack the expertise to write structured queries on the metadata. We show that when domain vocabulary...
Flagged for: agent, multi-agent, alignment, retrieval
Financial question answering over U.S. Securities and Exchange Commission (SEC) filings requires retrieving and synthesizing heterogeneous evidence dispersed across long, standardized, and highly redu...
Flagged for: agent, agentic, autonomous, tool use
Agentic artificial intelligence systems, capable of autonomous perception, planning, tool use, and multi-step action, are increasingly proposed for critical engineering domains where decisions carry p...
Flagged for: agent, multi-agent, agentic, autonomous
Enterprise Resource Planning (ERP) systems record transactions reliably but still delegate almost all operational decision-making to human specialists, because classical rule-based automation cannot r...
Flagged for: agent, multi-agent, agentic, autonomous
Agentic Artificial Intelligence (AI), enabled by Large Language Models, marks a shift from rule-based automation toward autonomous, goal-driven control of Next-Generation Networks (NGNs). Existing sur...
Flagged for: agent, agentic, tool-use, reasoning
Large language models (LLMs) are improving rapidly as reflected in benchmark scores, yet these AI benchmarks largely test capabilities such as factual recall, narrow question answering, mathematical p...
Flagged for: autonomous, planning, interpretability, interpret
Autonomous robots operating in dynamic environments require behaviour planning systems that combine reactivity, interpretability, and adaptability. While Large Language Models have been successfully i...
Flagged for: agi, foundation model, agent, embodied
Humanoid control requires natural whole-body coordination, precise real-time responses to control signals, and robust generalization across diverse environmental contexts, making it a cornerstone for ...
Flagged for: agent, multi-agent, alignment, rlhf
The formation of political coalitions is a complex negotiation driven by both concrete policy objectives and deep-seated ideological convictions. While Large Language Models (LLMs) open new avenues fo...
Flagged for: agent, agentic, planning, reasoning
Multi-step retrosynthesis planning seeks to decompose a target molecule into commercially available building blocks through a sequence of feasible reactions. The vast combinatorial search space makes ...
Flagged for: agent, agentic, reasoning, llm
Large language models (LLMs) have demonstrated strong reasoning performance, but their tendency to hallucinate limits their reliability in knowledge-intensive tasks requiring up-to-date and grounded i...
Flagged for: agi, agent, multi-agent, language model
Recent advances in Tool-Integrated Large Language Models have made web search a core capability of information-seeking agents. However, as interaction histories grow, agents increasingly struggle to t...
Flagged for: agi, interpretability, interpret, embodied
World-action models (WAMs) are emerging as a promising foundation for embodied control: rather than predicting actions alone, they learn representations that couple action generation with future world...
Flagged for: agi, reasoning, llm, language model
Given the current trend to employ large language models (LLMs) in almost any imaginable context, LLM-generated text detection and authorship attribution have become a pressing issue. Prior work has pr...
Flagged for: agent, reasoning, interpret, embodied
Vision-language models (VLMs) are increasingly used as the reasoning backbone of embodied agents, enabling robots to interpret visual scenes, follow language instructions, and plan multi-step actions....
Flagged for: agent, agentic, reasoning, language model
Retrieval systems are trained and evaluated on a static idea of usefulness: hand a document and a question to a reader model, see whether the answer improves, and score the document accordingly. The i...
Flagged for: agi, agent, multi-agent, agentic
Multimodal Large Language Models (MLLMs) are increasingly deployed for nuanced content safety and moderation tasks, yet they remain vulnerable to adversarial attacks and out-of-distribution edge cases...
Flagged for: agent, multi-agent, agentic, autonomous
The rapid proliferation of Agentic Artificial Intelligence fundamentally disrupts traditional customer loyalty paradigms. As AI evolves from passive recommendation algorithms to autonomous, goal-direc...
Flagged for: agent, multi-agent, autonomous, reasoning
Recent advances in Large Language Models have fueled autonomous AI agents capable of tackling complex scientific tasks, yet existing automated research systems remain predominantly focused on empirica...
Flagged for: agi, agent, autonomous, llm
As Large Language Models (LLMs) are increasingly deployed as autonomous agents in high-stakes domains, understanding contextual factors that may modulate their decision-making becomes critical. While ...
Flagged for: agent, reasoning, embodied, llm
Visual Language Navigation (VLN) aims to enable an embodied agent to navigate complex environments by following natural language instructions. Recent approaches build semantic spatial maps and leverag...
Flagged for: agi, alignment, llm, language model
Unequal availability of human preference data across languages poses a significant challenge for aligning large language models in multilingual settings. To address the lack of sufficient data in low-...
Flagged for: agi, reasoning, llm, language model
Math reasoning has achieved significant progress with the rapid advancement of Multimodal Large Language Models (MLLMs), however analytic geometry remains largely underexplored, primarily due to the s...
Flagged for: artificial general intelligence, world model, agent, embodied
Artificial general intelligence ultimately requires agents that can reason and act in the physical world. Action models, vision-language-action policies, and world models have advanced this goal, whil...
Flagged for: agent, agentic, tool use, reasoning
Large language model agents are increasingly executed not by a single model call, but by an execution harness that manages observation, context, control, action, state, and verification. At the same t...
Flagged for: agent, multi-agent, autonomy, llm
Exploration is essential for reliable autonomy in multi-agent systems, yet it remains unclear whether large language model (LLM) agents can explore effectively when interacting with one another. We sh...
Flagged for: agent, agentic, autonomous, llm
Agentic AI systems are reshaping communications and networking by deploying autonomous intelligent agents capable of collaborative learning while maintaining data privacy at network edges. Within dist...
Flagged for: agent, agentic, tool use, reasoning
Large language model (LLM) agents are increasingly used in trading systems, where model reasoning, tool use, and continual decisions incur costs that are expected to produce trading value. Existing ev...
Flagged for: agent, agentic, tool use, tool-use
Agentic LLM systems that generate code through multi-turn tool use face a fundamental context problem: each session starts from zero, discarding the configuration choices, domain constraints, data sch...
Flagged for: agent, embodied, robot, robotics
Embodied agent teams powered by heterogeneous large language models (LLMs) are being widely deployed in physical artificial intelligence such as smart factories, warehouses, and service robotics. To e...
Flagged for: agent, multi-agent, autonomous, reasoning
Large language models (LLMs) demonstrate remarkable reasoning capabilities, yet their stateless architecture fundamentally limits deployment in long-horizon research workflows requiring multi-session ...
Flagged for: agent, multi-agent, reasoning, llm
Large language model (LLM) based multi-agent systems enable complex problem solving through coordinated reasoning and action, but their distributed structure also introduces new challenges in diagnosi...
Flagged for: agent, multi-agent, alignment, llm
We report a pre-registered, two-part experiment on small economies of frontier language-model agents (Claude Opus 4.8), testing two quantitative predictions about coupled multi-agent systems: an infor...