Autonomous AI is no longer a hard-to-reach concept, it enables the agents to move beyond executing tasks to independently addressing complex problems, adapting to change while handling the uncertainty of the environment. However, what makes the agents truly autonomous? It is agentic reasoning, that is crucial for foundation models to develop symbolic logic, statistical correlations, or large-scale pattern recognition to process information, draw inferences, and make decisions. However, it remains unclear why and how existing agentic reasoning approaches work, in comparison to biological reasoning, which instead is deeply rooted in neural mechanisms involving hierarchical cognition, multimodal integration, and dynamic interactions. In this work, we propose a novel neuroscience-inspired framework for agentic reasoning. Grounded in three neuroscience-based definitions and supported by mathematical and biological foundations, we propose a unified framework modeling reasoning from perception to action, encompassing four core types, perceptual, dimensional, logical, and interactive, inspired by distinct functional roles observed in the human brain. We apply this framework to systematically classify and analyze existing AI reasoning methods, evaluating their theoretical foundations, computational designs, and practical limitations. We also explore its implications for building more generalizable, cognitively aligned agents in physical and virtual environments. Finally, building on our framework, we outline future directions and propose new neural-inspired reasoning methods, analogous to chain-of-thought prompting. By bridging cognitive neuroscience and AI, this work offers a theoretical foundation and practical roadmap for advancing agentic reasoning in intelligent systems. The associated project can be found at: https://github.com/BioRAILab/Awesome-Neuroscience-Agent-Reasoning .

Interactive imitation learning makes an agent's control policy robust by stepwise supervisions from an expert. The recent algorithms mostly employ expert-agent switching systems to reduce the expert's burden by limitedly selecting the supervision timing. However, the precise selection is difficult and such a switching causes abrupt changes in actions, damaging the dynamic stability. This paper therefore proposes a novel method, so-called CubeDAgger, which improves robustness while reducing dynamic stability violations by making three improvements to a baseline method, EnsembleDAgger. The first improvement adds a regularization to explicitly activate the threshold for deciding the supervision timing. The second transforms the expert-agent switching system to an optimal consensus system of multiple action candidates. Third, autoregressive colored noise to the actions is introduced to make the stochastic exploration consistent over time. These improvements are verified by simulations, showing that the learned policies are sufficiently robust while maintaining dynamic stability during interaction.

In this paper, we study a new decision-making problem called the bandit max-min fair allocation (BMMFA) problem. The goal of this problem is to maximize the minimum utility among agents with additive valuations by repeatedly assigning indivisible goods to them. One key feature of this problem is that each agent's valuation for each item can only be observed through the semi-bandit feedback, while existing work supposes that the item values are provided at the beginning of each round. Another key feature is that the algorithm's reward function is not additive with respect to rounds, unlike most bandit-setting problems. Our first contribution is to propose an algorithm that has an asymptotic regret bound of $O(m\sqrt{T}\ln T/n + m\sqrt{T \ln(mnT)})$, where $n$ is the number of agents, $m$ is the number of items, and $T$ is the time horizon. This is based on a novel combination of bandit techniques and a resource allocation algorithm studied in the literature on competitive analysis. Our second contribution is to provide the regret lower bound of $Ω(m\sqrt{T}/n)$. When $T$ is sufficiently larger than $n$, the gap between the upper and lower bounds is a logarithmic factor of $T$.

DBSCAN, a well-known density-based clustering algorithm, has gained widespread popularity and usage due to its effectiveness in identifying clusters of arbitrary shapes and handling noisy data. However, it encounters challenges in producing satisfactory cluster results when confronted with datasets of varying density scales, a common scenario in real-world applications. In this paper, we propose a novel Adaptive and Robust DBSCAN with Multi-agent Reinforcement Learning cluster framework, namely AR-DBSCAN. First, we model the initial dataset as a two-level encoding tree and categorize the data vertices into distinct density partitions according to the information uncertainty determined in the encoding tree. Each partition is then assigned to an agent to find the best clustering parameters without manual assistance. The allocation is density-adaptive, enabling AR-DBSCAN to effectively handle diverse density distributions within the dataset by utilizing distinct agents for different partitions. Second, a multi-agent deep reinforcement learning guided automatic parameter searching process is designed. The process of adjusting the parameter search direction by perceiving the clustering environment is modeled as a Markov decision process. Using a weakly-supervised reward training policy network, each agent adaptively learns the optimal clustering parameters by interacting with the clusters. Third, a recursive search mechanism adaptable to the data's scale is presented, enabling efficient and controlled exploration of large parameter spaces. Extensive experiments are conducted on nine artificial datasets and a real-world dataset. The results of offline and online tasks show that AR-DBSCAN not only improves clustering accuracy by up to 144.1% and 175.3% in the NMI and ARI metrics, respectively, but also is capable of robustly finding dominant parameters.

Building on the recent empirical work of Kwa et al. (2025), I show that within their suite of research-engineering tasks the performance of AI agents on longer-duration tasks can be explained by an extremely simple mathematical model -- a constant rate of failing during each minute a human would take to do the task. This implies an exponentially declining success rate with the length of the task and that each agent could be characterised by its own half-life. This empirical regularity allows us to estimate the success rate for an agent at different task lengths. And the fact that this model is a good fit for the data is suggestive of the underlying causes of failure on longer tasks -- that they involve increasingly large sets of subtasks where failing any one fails the task. Whether this model applies more generally on other suites of tasks is unknown and an important subject for further work.

Machine Learning (ML) algorithms are deeply embedded in var ious aspects of modern life, influencing everything from enhancing daily conveniences and sh aping online purchasing behavior to making critical decisions in areas such as hiring, loan appr ovals, college admissions, and probation rulings. Given the high stakes of these decisions, individu als often have strong incentives to strategically modify the data they provide to these algorithms to s ecure more favorable outcomes. For instance, individuals might open additional credit accoun ts or take other steps to improve their credit scores before applying for a loan. In the context of co llege admissions, applicants may retake standardized tests like the GRE, enroll in test preparation courses, or even switch schools to boost their class rankings, all in efforts to present themselves as m ore competitive candidates. Such instances of "strategic adaptation" have been extensi vely documented across disciplines including Economics, CS, and Public Policy Bj orkegren et al. [ 2020 ], Dee et al. [ 2019 ], Dranove et al. [ 2003 ], Greenstone et al. [ 2022 ], Gonzalez-Lira and Mobarak [ 2019 ], Chang et al. [ 2024 ]. The challenge arises when decision-makers deploying ML algorithms fail to account for these adaptations, potentially undermining the original goals of the policies the algorithms are intended to support. For example, in college admissions, a student's decision to change schools solely to improve their class ranking may not necessarily reflect a substantive impr ovement in their qualifications. This literature review was recently published in SIGEcom Ex changes.

Artificial Intelligence (AI) systems are increasingly placed in positions where their decisions have real consequences, e.g., moderating online spaces, conducting research, and advising on policy. Ensuring they operate in a safe and ethically acceptable fashion is thus critical. However, most solutions have been a form of one-size-fits-all "alignment". We are worried that such systems, which overlook enduring moral diversity, will spark resistance, erode trust, and destabilize our institutions. This paper traces the underlying problem to an often-unstated Axiom of Rational Convergence: the idea that under ideal conditions, rational agents will converge in the limit of conversation on a single ethics. Treating that premise as both optional and doubtful, we propose what we call the appropriateness framework: an alternative approach grounded in conflict theory, cultural evolution, multi-agent systems, and institutional economics. The appropriateness framework treats persistent disagreement as the normal case and designs for it by applying four principles: (1) contextual grounding, (2) community customization, (3) continual adaptation, and (4) polycentric governance. We argue here that adopting these design principles is a good way to shift the main alignment metaphor from moral unification to a more productive metaphor of conflict management, and that taking this step is both desirable and urgent.

Continuous authentication systems leveraging free - text keyboard dynamics offer a promising additional layer of security in a multifactor authentication setup that can be used in a transparent way with no impact on user experience. This study investigates t he efficacy of behavioral biometrics by employing an Agent - Based Model (ABM) to simulate diverse typing profiles across mechanical and membrane keyboards. Specifically, we generated synthetic keystroke data from five unique agents, capturing features relat ed to dwell time, flight time, and error rates within sliding 5 - second windows updated every second. Two machine learning approaches, One - Class Support V ector Machine (OC - SVM) and Random Forest (RF), were evaluated for user verification. Results revealed a stark contrast in performance: while One - Class SVM failed to differentiate individual users within each group, Random Forest achieved robust intra - keyboard user recognition (Accuracy > 0.7) but struggled to generalize across keyboards for the same user, h ighlighting the significant impact of keyboard hardware on typing behavior. These findings suggest that: (1) keyboard - specific user profiles may be necessary for reliable authentication, and (2) ensemble methods like RF outperform One - Class SVM in capturing fine - grained user - specific patterns. Keywords: keyboard dynamics, continuous authentication, agent - based modeling, One - Class SVM, Random Forest, behavioral biometrics.

Computational Fluid Dynamics (CFD) is an essential simulation tool in various engineering disciplines, but it often requires substantial domain expertise and manual configuration, creating barriers to entry. We present Foam-Agent, a multi-agent framework that automates complex OpenFOAM-based CFD simulation workflows from natural language inputs. Our innovation includes (1) a hierarchical multi-index retrieval system with specialized indices for different simulation aspects, (2) a dependency-aware file generation system that provides consistency management across configuration files, and (3) an iterative error correction mechanism that diagnoses and resolves simulation failures without human intervention. Through comprehensive evaluation on the dataset of 110 simulation tasks, Foam-Agent achieves an 83.6% success rate with Claude 3.5 Sonnet, significantly outperforming existing frameworks (55.5% for MetaOpenFOAM and 37.3% for OpenFOAM-GPT). Ablation studies demonstrate the critical contribution of each system component, with the specialized error correction mechanism providing a 36.4% performance improvement. Foam-Agent substantially lowers the CFD expertise threshold while maintaining modeling accuracy, demonstrating the potential of specialized multi-agent systems to democratize access to complex scientific simulation tools. The code is public at https://github.com/csml-rpi/Foam-Agent

This research introduces an innovative AI-driven multi-agent framework specifically designed for creating immersive audiobooks. Leveraging neural text-to-speech synthesis with FastSpeech 2 and VALL-E for expressive narration and character-specific voices, the framework employs advanced language models to automatically interpret textual narratives and generate realistic spatial audio effects. These sound effects are dynamically synchronized with the storyline through sophisticated temporal integration methods, including Dynamic Time Warping (DTW) and recurrent neural networks (RNNs). Diffusion-based generative models combined with higher-order ambisonics (HOA) and scattering delay networks (SDN) enable highly realistic 3D soundscapes, substantially enhancing listener immersion and narrative realism. This technology significantly advances audiobook applications, providing richer experiences for educational content, storytelling platforms, and accessibility solutions for visually impaired audiences. Future work will address personalization, ethical management of synthesized voices, and integration with multi-sensory platforms.