Flagged for: agi, agent, multi-agent, robot
Multi-agent reinforcement learning (MARL) has become a prominent research direction, particularly within collective robotics, where the ARGoS simulator is widely used to study emergent swarm behavior....
Flagged for: recursive self-improvement, self-improving, agent, interpret
Artificial intelligence is beginning to automate scientific discovery, yet physical robot-policy research still relies on scientists and engineers to interpret experimental failures and decide how con...
Flagged for: agent, multi-agent, reasoning, embodied
Long-horizon embodied agents must maintain task-relevant information, coordinate heterogeneous robots, and adapt their decisions as execution unfolds. Existing benchmarks investigate dynamic task exec...
Flagged for: agent, multi-agent, agentic, llm
The fast pace in which protocols, frameworks, and technologies are being proposed for LLM-based agents results in a complex scenario for anyone aiming to create state-of-the-art AI solutions. Without ...
Flagged for: agi, artificial general intelligence, recursive self-improvement, agent
As claims about recursive self-improvement (RSI) and artificial general intelligence (AGI) proliferate, we ask a simple question: do frontier AI models have a sense of data, i.e., can they reliably se...
Flagged for: agent, agentic, interpret, robot
General-purpose service robots need navigation systems that can handle diverse human requests in unfamiliar environments, combining task generality with scene generality. Some existing methods fine-tu...
Flagged for: foundation model, agent, multi-agent, agentic
Large foundation models have accelerated progress toward general-purpose agents that interact with humans and other agents through language and multimodal signals. However, robust multi-agent decision...
Flagged for: world model, reasoning, embodied, llm
Multimodal large language models (MLLMs) struggle with spatial, embodied, physical, and temporal reasoning. We hypothesize that these failures reflect a shared deficit in visual transition reasoning, ...
Flagged for: agent, agentic, interpret, llm
Over 90% of disease-associated variants from genome-wide association studies fall in noncoding regulatory regions, yet their functional interpretation remains a central open problem in genomic medicin...
Flagged for: recursive self-improvement, agent, multi-agent, reasoning
Recursive self-improvement (RSI) of a model on non-verifiable tasks, such as open-ended research, faces a supervision bottleneck when its outputs exceed what even human experts can reliably assess, le...
Flagged for: recursive self-improvement, world model, agent, language model
AI research agents automate the cycle of proposing, implementing, and evaluating experiments, opening a path toward recursive self-improvement. Yet their ability to propose experiments outpaces their ...
Flagged for: recursive self-improvement, world model, agent, llm
Learning to act in unfamiliar environments requires agents to infer how the world works and revise that understanding as new evidence arrives. Yet limited observations can support multiple world model...
Flagged for: agent, multi-agent, agentic, llm
Analog/RF circuits remain the critical interface between digital computation and the physical world, and emerging standards from Wi-Fi 7 to 6G place stringent demands on them, yet analog/RF design rem...
Flagged for: foundation model, agent, agentic, autonomous
Robot foundation models provide strong visuomotor control, yet their performance can degrade when object positions or task instructions change. Further improvements often require post-training on subs...
Flagged for: agent, agentic, tool use, language model
Large language models are increasingly applied to tasks grounded in long, heterogeneous information sources. Conventional Retrieval-Augmented Generation (RAG) relies on fixed similarity-based retrieva...
Flagged for: agent, tool use, reasoning, llm
Security operations centers (SOCs) must triage large volumes of alerts, most of which are benign, while missed attacks can remain uninvestigated. Tool-using large language model (LLM) agents can retri...
Flagged for: agent, agentic, reasoning, language model
Test-time scaling (TTS) improves the reasoning capabilities of large language models by allocating additional inference computation. Existing approaches to improving TTS efficiency largely optimize ac...
Flagged for: agent, agentic, reasoning, llm
Retrieval-augmented generation (RAG) is a widely used approach for grounding large language models (LLMs) in external knowledge. However, configuring a pipeline is an expensive hyperparameter optimiza...
Flagged for: agent, multi-agent, agentic, reasoning
Large language model (LLM)-based multi-agent systems (MAS) have become a promising paradigm for complex information-seeking and reasoning tasks by enabling collaborative problem solving among speciali...
Flagged for: self-improving, agent, reasoning, embodied
Self-improving policies continually expose new failure patterns, changing what their judges must be able to verify. However, current fixed judges constrain both optimization feedback and the discovery...
Flagged for: agent, multi-agent, autonomous, robot
Swarm robotics presents a robust and cost-effective paradigm for advanced automation in complex, dynamic environments, such as those encountered in search and rescue or environmental monitoring. A fun...
Flagged for: agent, agentic, planning, robot
LLM agents that orchestrate frozen vision-language-action (VLA) policies improve across episodes through text memory, which records what the agent did but not how the task is done. A demonstration vid...
Flagged for: agent, agentic, tool use, reasoning
LLM agents increasingly execute complex workflows involving multi-turn reasoning, tool use, and parallel agents. Efficient serving requires decisions that span two layers with complementary informatio...
Flagged for: agent, agentic, tool-use, llm
Large language model (LLM) agents are increasingly capable of acting in complex tool-use environments, yet they often fail to recognize when tasks are infeasible and no valid solution exists. Recent w...
Flagged for: agent, multi-agent, reasoning, llm
While medical multimodal large language models (Med-MLLMs) advance medical visual question answering (VQA), existing clinical workflow-inspired multi-agent frameworks suffer from interaction patterns ...
Flagged for: agent, multi-agent, agentic, autonomous
Agentic AI is emerging as a promising paradigm for automating complex cybersecurity decisions, yet its use in enforcing zero trust introduces significant challenges in safety, reliability, and policy ...
Flagged for: agent, agentic, llm, language model
The unprecedented computational scale of modern artificial intelligence depends on complex, multi-billion-transistor Systems-on-Chip, yet the workflows that verify these chips remain stubbornly manual...
Flagged for: agent, agentic, reasoning, embodied
Natural face-to-face human--robot interaction requires a robot to understand an evolving social situation, decide when to engage, and express its intent through coordinated physical behavior. Yet exis...
Flagged for: agi, foundation model, agent, reasoning
Accurate 3D detection is essential for mobile embodied agents, while Vision Foundation Models (VFMs) offer transferable visual and geometric priors. Yet existing VFM-based 3D detectors rely on narrow-...
Flagged for: reasoning, alignment, llm, language model
Reasoning traces improve large language models (LLMs), but current models are trained to reason mostly in English. It has been shown that forcing a model to reason in another language degrades accurac...
Flagged for: agent, multi-agent, agentic, llm
Large language models (LLMs) are increasingly used in software engineering, including agentic systems that coordinate multiple agents, but impose higher computational and environmental costs. In this ...
Flagged for: alignment, value alignment, llm, language model
Large language models (LLMs) are increasingly deployed in public health, finance, and governance, requiring both accuracy and societal value alignment. Despite recent advances, LLMs often perpetuate o...
Flagged for: agent, agentic, reasoning, llm
Large Language Models (LLMs) increasingly support Uncrewed Aerial Vehicle (UAV) swarm operations such as data collection scheduling, where the model reads structured sensor reports and decides which s...
Flagged for: agent, multi-agent, reasoning, llm
Emerging multi-agent LLMs demand privacy-preserving edge deployment, yet current inference systems struggle with these collaborative workflows. Specifically, the memory-bound decode phase causes sever...
Flagged for: agi, agent, agentic, reasoning
Unmanned aerial vehicle (UAV) swarms increasingly rely on language-model agents to provide adaptive mission-level reasoning in uncertain environments. Fully distributed control, in which each UAV host...
Flagged for: agent, multi-agent, reasoning, interpret
Personalized interpretation of health checkup results requires reasoning across longitudinal records, medical knowledge, lifestyle guidance, and healthcare navigation. We present a multi-agent large l...
Flagged for: agi, reasoning, llm, language model
While Large Language Models (LLMs) have demonstrated striking capabilities on frontier mathematical problems, it remains unclear whether they possess the structural mathematical understanding underlyi...
Flagged for: agent, tool use, reasoning, llm
Large language model (LLM) agents increasingly combine reasoning, tool use, and action, but most evidence comes from episodic tasks with relatively immediate feedback and reset failures. Long-running ...
Flagged for: agent, multi-agent, llm, language model
Large language models (LLMs) have recently been applied in systems research as a tool to reduce human-intensive engineering effort through cost-efficient automation. Decades of research have produced ...
Flagged for: agi, recursive self-improvement, agent, agentic
Recent advances in large language models have made automatic game generation increasingly feasible, yet reliably improving generated games beyond a playable version remains challenging. Naive iterativ...
Flagged for: agent, multi-agent, autonomous, llm
Recent autonomous machine learning engineering (MLE) agents have made significant progress on public leaderboards. Often motivated by progress stagnation over long-horizon cycles and limited Large Lan...
Flagged for: agent, multi-agent, llm, language model
Large language models (LLMs) are increasingly deployed as automated judges for AI-generated content, yet a single judge is unreliable and even a panel of judges leaves a hard residue: when judges disa...
Flagged for: agent, agentic, reasoning, interpret
Quantum algorithms and quantum hardware are advancing towards a promising paradigm for scientific applications. However, translating domain-specific problems into executable hybrid quantum-classical w...
Flagged for: agi, self-improving, world model, robot
Long-horizon robot manipulation reuses skills across many task compositions, but improving these compositions with additional end-to-end demonstrations is costly. A practical self-improving system mus...
Flagged for: agi, foundation model, reasoning, llm
Reasoning about the 3D world from multi-view images remains a fundamental challenge for Multimodal Large Language Models (MLLMs). While modern MLLMs handle single-image inputs effectively, they strugg...
Flagged for: agent, agentic, reasoning, robot
Vision-language-action (VLA) models have advanced robotic manipulation, but their zero-shot generalization in new tasks and environments remains limited, and their reliance on specialized training kee...
Flagged for: self-improving, agent, multi-agent, llm
Large language models (LLMs) can now improve themselves by revising the instructions they follow, and LLM agents are increasingly orchestrated to work together on complex problems. However, self-impro...
Flagged for: agent, multi-agent, reasoning, llm
As large language models (LLMs) evolve from standalone models into collaborative agents embedded in physical systems, their reasoning and execution are increasingly distributed across wireless edge no...
Flagged for: foundation model, agent, agentic, autonomous
Robots deployed in the physical world must be able to improve beyond their initial training as they encounter new situations and failures. For this improvement to scale across tasks, it must make effe...
Flagged for: recursive self-improvement, agent, multi-agent, llm
Recursive self-improvement (RSI) lets a system improve from its own outcomes; in LLM-based multi-agent systems, Agents refine one another within a task, and outcomes improve how they collaborate acros...
Flagged for: agi, self-improving, agent, agentic
Augmented dexterity has the potential to reduce the fatigue experienced by surgeons during repetitive surgical tasks. In this paper, we propose the first AGentic RObotics framework for SUrgical VIscoe...
Flagged for: agent, agentic, reasoning, llm
Large language models (LLMs) excel at structured, verifiable tasks, but their low-entropy bias can produce homogeneous and predictable outputs, limiting their utility for open-ended scientific ideatio...
Flagged for: agent, reasoning, embodied, llm
Recent zero-shot Vision-and-Language Navigation (VLN) methods increasingly rely on multimodal large language models (MLLMs) to reason over visual observations, navigation instructions, and candidate a...
Flagged for: agent, multi-agent, agentic, interpret
Large language model (LLM) agentic systems increasingly rely on models communicating with one another, yet existing uncertainty and multi-agent methods rarely estimate how a particular receiver will i...
Flagged for: agent, agentic, autonomous, llm
The collective behaviour of large language model (LLM) societies is not the sum of their individual outputs. It yields statistically distinct, sometimes-unpredictable phenomena, for which the tools we...
Flagged for: agi, world model, agent, multi-agent
World models improve sample efficiency by training policies on imagined trajectories, but their usefulness depends on learning representations that capture the information needed for future control. W...
Flagged for: agent, multi-agent, reasoning, llm
Multi-agent systems built on large language models (LLMs) are largely homogeneous, as their agents behave alike even across distinct LLMs. We show that when such agents act concurrently without commun...
Flagged for: agi, agent, multi-agent, llm
Multi-agent LLM systems are often expected to improve as team size increases, yet the scaling behavior may depend on task structure. Our central contribution is to introduce Steiner's taxonomy of grou...
Flagged for: agent, multi-agent, reasoning, alignment
LLM-based multi-agent systems can fail even when communication succeeds because agents do not correctly track their peers' roles, knowledge, or intentions. We investigate whether such inter-agent misa...
Flagged for: agent, multi-agent, alignment, llm
Large language models are increasingly deployed as interacting agents, making the persistence of their action policies across repeated interaction critical for reliable multi-agent operation. We inves...