Latest Agentic AI & LLM Agents Research Papers
The newest Agentic AI & LLM Agents papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Agentic AI & LLM Agents so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.
Get the latest Agentic AI & LLM Agents papers in your inbox — free →Recent papers
- REALMS-CG: Resilient Ensemble of Autonomous LLM Multi-agent with Spectral clustering for Code GenerationAnonymous, Anonymous · Zenodo (CERN European Organ... · Sep 1, 2027
This contains the actual source code, prompts, scripts and all experiment results as described in the paper:REALMS-CG: Resilient Ensemble of Autonomous LLM Multi-agent with Spectral clustering for Code Generation.This data is provided as pa…
- Supervising the search process produces reliable and generalizable information-seeking agentsGuangzhi Xiong, Qiao Jin, Xiao Wang, Fang Yin et al. · Nature Communications · Oct 28, 2026
Abstract Large language models (LLMs) are transforming web search by shifting from document ranking to synthesizing answers, and are increasingly deployed as autonomous agentic search systems that iteratively interact with external knowledg…
- TimestralAdrien Petralia, Alexandre Gavaudan, Artjom Joosen, Etienne Goffinet et al. · arXiv · Oct 27, 2026
We introduce Timestral, a family of four time series foundation models for probabilistic forecasting, with 5M, 28M, 123M, and 209M parameters. Timestral sets a new state of the art on GIFT-Eval, TIME, and fev-bench, where Timestral-209M and…
- Which Hand Was Late? Diagnosis for Robot Failure Recovery in Bimanual Tool UseBaptiste Bonin, Caro Strickland, Audrey Durand · arXiv · Oct 27, 2026
Failure diagnosers for robot manipulation are increasingly vision--language models (VLMs), trained and evaluated on single-arm failures produced by perturbing a successful demonstration. Bimanual tool use adds failures of other kinds: a too…
- Concordat: Typed Sessions for LLM AgentsMilad Sikaroudi · arXiv · Oct 27, 2026
Agents built on large language models are increasingly allowed to take consequential actions: cancelling bookings, issuing refunds, changing accounts. The rules that govern those actions, such as "obtain the customer's explicit confirmation…
- M4Bench: Evaluating Procedural Specification for Clinical EHR Derivation AgentsHannes Ill, Rafi Al Attrach, Rajna Fani, Ahram Han et al. · arXiv · Oct 27, 2026
Clinical research over electronic health records depends on derived variables whose definitions sit outside the schema, in item codes, time windows, missingness rules, and output-grain choices that change cohorts and downstream conclusions.…
- The evolution of tool use in LLM agents: from single-tool call to multi-tool orchestrationHaoyuan Xu, Chang Li, Xinyan Ma, Xianhao Ou et al. · Artificial Intelligence Review · Oct 27, 2026
Tool use enables large language models (LLMs) to access external information, invoke software systems, and act in digital environments beyond what can be solved from model parameters alone. Early research mainly studied whether a model coul…
- Reva: Real-Time Vulnerability Detection through Contextual Probing of Large Language ModelsAmine Lbath, Massih-Reza Amini · arXiv · Oct 26, 2026
A vulnerability costs more to fix the later it is discovered. As coding agents generate code faster than developers can review it, software needs a first line of defense screening each new function in real time. LLM agents have recently bec…
- A Unified Arena for LLM Agents across Diverse EurogameFengrui Zhang, Xiang Li, Ruomeng Ding, Jiayi Yuan et al. · arXiv · Oct 26, 2026
Interactive environments offer a practical way to evaluate large language model (LLM) agents, and competitive games extend this evaluation to decisions shaped by competing goals and other agents' choices. Yet existing evaluations confined t…
- Free to Look, Free to Reason: Simple LLM Harnesses Outdiagnose Hand-Crafted Root Cause Analysis AgentsTingzhu Bi, Xun Zhang, Jinglin Li, Ping Wang et al. · arXiv · Oct 26, 2026
Root cause analysis (RCA) of microservice failures has attracted many LLM agents whose investigation is hand-crafted, through standard operating procedures, fixed stages and role agents. Each is evaluated on its own data against few baselin…
- Agentic AI-Based Online Shopping Assistantsakshi nigade · Zenodo (CERN European Organ... · Oct 26, 2026
Project Description The Agentic AI-Based Online Shopping Assistant is an intelligent system designed to help users find, compare, and select suitable products from online marketplaces. It uses Large Language Models (LLMs) to understand user…
- Fabric: An Agentic AI Workspace for Natural-Language Data Analysis and Multi-Tool Task ExecutionPrajwal Anil Kanade Sakshi Mahendra Pawar, Shivam Santosh Wajage Rutika Ashok Padir · International Journal of Ad... · Oct 26, 2026
Agentic artificial intelligence systems combine language-model interaction with tools that perform operations beyond text generation. In data analytics, an integrated workspace must support dataset handling, analytical computation, visualiz…
- The Agent Internet A New Evolutionary Phase of the Web and Its Global ImpactA. Shaji George, B.Roshini, Dr.T.Baskar · Zenodo (CERN European Organ... · Oct 25, 2026
Large language model (LLM) based software agents are transitioning from one shot assistants to long term actors that plan, negotiate and accomplish tasks with multiple services. This transformation is resulting in what researchers call the …
- From Description to Interactive VR Scene: An LLM Agent for Authoring Immersive ExperiencesR. Chen, Allison Andreyev, Xuan Wang, Jianan Jiang et al. · OpenAlex · Oct 25, 2026
- Restart, Don't Persist: Optimal Restart Strategies for Heavy- Tailed LLM Agent Runs By Swarajkumar GawaliSwarajkumar Gawali · OpenAlex · Oct 24, 2026
- Agentic and generative AI for intelligent autonomous vulnerability assessment and penetration testing: A systematic analysisSamuel Roy Anthony Truss, Mohamed Chahine Ghanem, Mohammed Amin Almaiah, Marco Ortolani et al. · Computer Science Review · Oct 24, 2026
Context: Vulnerability Assessment and Penetration Testing (VAPT) is increasingly challenged by the scale, heterogeneity, and dynamic nature of modern digital infrastructures, particularly across enterprise IT, operational technology (OT), i…
- SceneBloom: Agentic Indoor Environment Generation with Realistic and Diverse Layouts for Embodied LearningYuhan Liu, Lianhui Qin, Shenji Wan · arXiv · Oct 23, 2026
Training generalizable embodied agents requires realistic, varied, and simulation-ready indoor environments. Language-guided methods support semantic planning and object-level reasoning, but precise spatial grounding remains difficult. Visu…
- Do "True" and "False" Add Up to One? Complement Consistency in LLM-Agent Opinion SimulationsAnouar Imel, Jin Qi · arXiv · Oct 23, 2026
In LLM-agent opinion simulations, each agent reports the probability that a claim is true after seeing its own previous probability and the probabilities reported by its neighbors, and that number becomes its state in the next round. If the…
- Reimagining Enterprise RAG for Multi-Agent Systems: A Knowledge Layer That Organizes Before It RetrievesGarima Agrawal, Prasun Das, Akshay Sarvade, Priyanka L et al. · arXiv · Oct 23, 2026
Enterprises are deploying agentic AI across the software development lifecycle, and they need the behavioral logic of the systems they act on, not stakeholder documentation. A seven-agent reverse-engineering pipeline recovered this logic, p…
- Semantic Representation for Agentic Self-Play in Automated LaboratoriesYves Delley, John Coller, Zachary Cutts, Alexander Daryin et al. · arXiv · Oct 23, 2026
Navigating complex, high-dimensional biological search spaces necessitates scalable physical and computational intelligence to explore beyond local optima through iterative self-play across ideation, experimentation, and automation. Transla…
- ActionRAG: Evidence-Refining Graph Diffusion for Long-Term Memory in LLM AgentsNavyansh Mahla, Sashank Vandrangi · arXiv · Oct 23, 2026
LLM agents need long-term memory that can recover precise and mutually consistent evidence from growing interaction histories, particularly when answers depend on relations among facts rather than isolated semantic matches. Current memory p…
- Agentic Hazard Mapper: Emulating Expert Map-Making with AI Agents for Risk CommunicationSidi Wu, Lifeng Lin, Yizi Chen, Anna Yokokubo et al. · arXiv · Oct 23, 2026
Hazard maps are essential tools for public risk communication, preparedness, and evacuation planning, yet effective cartographic design is not always ensured due to limited access to cartographic expertise across local governments and commu…
- Ontology-Guided Knowledge Graph Construction from Structured Metadata and Climate Science PublicationsAayush Acharya, Qi Zhang, Eduard Dragut, Longin Jan Latecki · arXiv · Oct 23, 2026
The rapid expansion of scientific literature far outpaces the speed of manual curation, creating a fundamental bottleneck in extracting structured knowledge from scientific texts. To address this, we introduce an agentic, ontology-guided fr…
- EpiSEM-Bench: Evaluating Safety and Evidence Recovery in LLM Agents under Missing EvidenceQijin Zhang, Hanzhen Wang, Yuehan Zhao, Haoyu Dai et al. · arXiv · Oct 22, 2026
Tool-using language model agents rely on environmental facts to decide whether an action is permitted. When a tool response omits a safety-relevant fact, an agent may carry out a prohibited action even though the user request is benign and …
- Training Small Language Models for Transferable Tool SelectionZhaoyi Zhou, Akshayaa Magesh, Jeongyeol Kwon, Artem Kuriksha et al. · arXiv · Oct 22, 2026
As LLM agents operate over corpora of more than ten thousand tools, selecting the right tool for a complex multi-step user instruction becomes a central bottleneck. Tool descriptions cannot all fit in context, and relevance-based retrievers…
- Adaptive Skill Granularity for Coding Agents: Runtime Routing and Macro-to-Micro RecoveryDingxuan Zhang, Yanhui Jiang, Jun Wang, Hefeng Zhou · arXiv · Oct 22, 2026
Reusable skills allow large language model agents to package task-specific procedures, tool affordances, and execution guidance into modular units. Prior work has largely studied how agents retrieve, compose, or synthesize skills before exe…
- Within-person reciprocal processes between AI feedback literacy and agentic engagement: a three-wave random-intercept cross-lagged panel studyShuai Xu · Frontiers in Psychology · Oct 22, 2026
Artificial intelligence (AI) feedback has become a pervasive feature of university learning, yet whether students’ capacity to engage productively with such feedback co-develops with their broader learner agency remains poorly understood. D…
- Cyber Defence, Agentic AI, and the Sociotechnical Paradigm: A Survey of AI-Driven CybersecurityRupsingh Puransingh Mathwale · International Journal of Ap... · Oct 22, 2026
Artificial Intelligence (AI) and Large Language Models (LLMs) are reshaping cybersecurity, moving it from signature-based reactive security to agentic, self-evolving, and proactive operations. However, the fast deployment of autonomous agen…
- Choices Beyond the Objective: Semantic Degrees of Freedom as a Lens for Agent Safety and Emergent AlignmentTetyana Skreka-Davis · Zenodo (CERN European Organ... · Oct 22, 2026
Abstract Although we tend to treat an LLM instruction as a single point, it maps to a range of meanings, and I call this range its semantic degrees of freedom. In my view, the range is both plastic and instrumental to how we understand agen…
- A Prescriptive Design Framework for CRM-Integrated Agentic AI in Hospital Patient Services: Design Science Development and Empirical Proof-of-Concept EvaluationYohana Prihessy, Sfenrianto Sfenrianto · Inform Jurnal Ilmiah Bidang... · Oct 22, 2026
Hospital patient services (registration and appointment scheduling) often face fragmented systems, long handling times, and data-entry errors, while patients expect instant 24/7 digital interactions. This study uses Design Science Research …