Neural Architecture Search has shown potential to automate the design of neural networks. Deep Reinforcement Learning based agents can learn complex architectural patterns, as well as explore a vast and compositional search space. On the other hand, evolutionary algorithms offer higher sample efficiency, which is criti…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,742 papers · 148 categories
Trend · papers per month
48 results for “agentic architecture”
Many potential applications of reinforcement learning in the real world involve interacting with other agents whose numbers vary over time. We propose new neural policy architectures for these multi-agent problems. In contrast to other methods of training an individual, discrete policy for each agent and then enforcing…
AI agents manage portfolios, improving on human oversight.
problem Improving strategic asset allocation for institutional investors.
method 50 specialized agents produce capital market assumptions, construct portfolios, critique, and vote on each other's output.
result Meta-agent compares forecasts with realized returns and improves agent performance.
BGANs enable multi-agent learning with distributed private datasets.
problem Learning from distributed private datasets in multi-agent scenarios.
method Brainstorming GAN architecture for fully distributed learning.
result BGANs generate high-quality data samples with lower JSD and FID.
VALAN is a framework for navigation agents in photo-realistic environments.
problem Developing agents for indoor navigation tasks.
method Deep reinforcement learning with SEED RL architecture.
result VALAN framework can solve a variety of RL problems.
New approach treats coordination as an architectural layer to improve LLM-based multi-agent systems.
problem Coordination defects lead to high failure rates in LLM-based multi-agent systems.
method Treats coordination as a configurable architectural layer separable from agent logic and information access.
result Configurations leave distinguishable signatures, enabling architectural reasoning and Pareto frontiers.
Motivated by recent advance of machine learning using Deep Reinforcement Learning this paper proposes a modified architecture that produces more robust agents and speeds up the training process. Our architecture is based on Asynchronous Advantage Actor-Critic (A3C) algorithm where the total input dimensionality is halv…
Recent advances in Neural Architecture Search (NAS) have produced state-of-the-art architectures on several tasks. NAS shifts the efforts of human experts from developing novel architectures directly to designing architecture search spaces and methods to explore them efficiently. The search space definition captures pr…
Paper develops framework for AI agents in financial markets.
problem Systemic implications of AI in finance depend on agent architectures.
method Four-layer architecture and AFMM model for analysis.
result AI agents can improve market efficiency and resilience.
Deep Sets improve reinforcement learning agent's object-centered navigation and generalization.
problem Improving reinforcement learning agents' ability to generalize to unseen objects and goals.
method Combining object-wise permutation invariant networks (Deep Sets) and gated-attention mechanisms.
result Agent demonstrates strong generalization to out-of-distribution goals in a procedurally-generated 2D world.
Survey examines agentic AI in finance, highlighting its autonomy and challenges.
problem Autonomous AI systems in finance and their implications.
method Systematic review of research, technical architectures, market applications, and governance frameworks.
result Agentic AI offers enhanced market efficiency but introduces new risks.
We propose a targeted communication architecture for multi-agent reinforcement learning, where agents learn both what messages to send and whom to address them to while performing cooperative tasks in partially-observable environments. This targeting behavior is learnt solely from downstream task-specific reward withou…
NeuroMAS treats multi-agent systems as neural networks for scalable, trainable coordination.
problem Designing multi-agent systems as hand-designed workflows is inefficient and inflexible.
method NeuroMAS treats multi-agent systems as a neural network architecture with reinforcement learning for scalable coordination.
result NeuroMAS improves significantly over multi-agent baselines and can be scaled progressively.
Deep Reinforcement Learning has been shown to be very successful in complex games, e.g. Atari or Go. These games have clearly defined rules, and hence allow simulation. In many practical applications, however, interactions with the environment are costly and a good simulator of the environment is not available. Further…
A new Python-C++ framework for agent-based simulation.
problem Understanding market dynamics and effects of delays.
method User-friendly Python API with efficient C++ implementation, message-driven architecture.
result Investigated the role of order processing delay in financial markets.
Advanced simulation paradigm of human behaviour unveils complex financial systemic projectionq-fin.TR
New simulation model predicts financial market dynamics with high accuracy.
problem Extreme difficulty in financial market projections due to human behavioural complexity.
method Agent-based modeling with a hierarchical knowledge architecture to simulate diverse human groups.
result Simulator achieves 13.29% deviation in crisis scenarios and lower mean square error under normal conditions.
Agent-based modeling is a paradigm of modeling dynamic systems of interacting agents that are individually governed by specified behavioral rules. Training a model of such agents to produce an emergent behavior by specification of the emergent (as opposed to agent) behavior is easier from a demonstration perspective. W…
Meta-learning agents excel at rapidly learning new tasks from open-ended task distributions; yet, they forget what they learn about each task as soon as the next begins. When tasks reoccur - as they do in natural environments - metalearning agents must explore again instead of immediately exploiting previously discover…
Deep active inference agents learn complex environments using Monte-Carlo methods.
problem Understanding and modeling biological intelligence in complex, continuous state-spaces.
method Neural architecture for deep active inference agents using multiple forms of Monte-Carlo sampling.
result Deep active inference agents can learn environmental dynamics and plan future actions.
Proposes a new training algorithm for zero-sum games to avoid convergence issues.
problem Gradient-based training leads to weak convergence and cyclic dynamics in zero-sum architectures.
method Follow the perturbed leader algorithm with neural mediating agent.
result Guarantees convergence to mixed Nash equilibrium without cyclic behaviors.
Multi-simulator training has contributed to the recent success of Deep Reinforcement Learning by stabilizing learning and allowing for higher training throughputs. We propose Gossip-based Actor-Learner Architectures (GALA) where several actor-learners (such as A2C agents) are organized in a peer-to-peer communication t…
Dynamic portfolio optimization is the process of sequentially allocating wealth to a collection of assets in some consecutive trading periods, based on investors' return-risk profile. Automating this process with machine learning remains a challenging problem. Here, we design a deep reinforcement learning (RL) architec…
AI agents improve forecast combination in empirical economics.
problem Hidden researcher degrees of freedom in AI-generated code.
method Adapted agent-loop architecture to empirical economics, added holdout evaluation.
result Independent agent searches find better forecast methods than benchmarks.
Federated learning adapts to data and model drifts.
problem Performance guarantees in federated learning for dynamic problems.
method Random subset updates, non-stationary random walk model, tracking term.
result Performance depends on data variability, model variability, and learning rate.
Method models other agents' behaviors without requiring direct observation.
problem Understanding and interacting effectively with other agents in reinforcement learning.
method Extracts representations from local observations of the controlled agent using encoder-decoder architectures.
result The method achieves higher returns than baseline methods in multi-agent environments.
The Agentic Regulator: Risks for AI in Finance and a Proposed Agent-based Framework for Governancecs.CY
New AI governance framework tackles risks in finance.
problem Risks from evolving AI models in finance.
method Agent-based framework with modular governance architecture.
result Controls quarantine harmful behavior in real time.
A Layered Architecture for Active Perception: Image Classification using Deep Reinforcement Learningcs.LG
We propose a planning and perception mechanism for a robot (agent), that can only observe the underlying environment partially, in order to solve an image classification problem. A three-layer architecture is suggested that consists of a meta-layer that decides the intermediate goals, an action-layer that selects local…
New architecture tracks objects in cluttered scenes without supervision.
problem Learning to track objects in large scenes with many objects.
method Spatially invariant computations and representations.
result Outperforms competing methods in tracking objects in cluttered scenes.
AI agents improve forecast combination but require transparency.
problem AI coding agents increase flexibility in empirical economics, leading to hidden degrees of freedom.
method Adapted open-source agent-loop architecture to empirical economics workflow, adding post-search holdout evaluation.
result Multiple agent runs outperform standard benchmarks in rolling evaluation but not all on post-search holdout.
We investigate a classification problem using multiple mobile agents capable of collecting (partial) pose-dependent observations of an unknown environment. The objective is to classify an image over a finite time horizon. We propose a network architecture on how agents should form a local belief, take local actions, an…
Iterative Model-Based Reinforcement Learning Using Simulations in the Differentiable Neural Computercs.LG
We propose a lifelong learning architecture, the Neural Computer Agent (NCA), where a Reinforcement Learning agent is paired with a predictive model of the environment learned by a Differentiable Neural Computer (DNC). The agent and DNC model are trained in conjunction iteratively. The agent improves its policy in simu…
Generative tools mimic stock market traders using synthetic data.
problem Imitating trading behavior of stock market participants.
method Modified state-space model applied to limit order book data, trained on synthetic data generated from a heterogeneous agent-based model.
result Model's predicted distribution matches ground truths from the agent-based model.
Survey examines LLMs in financial trading.
problem Using LLMs to outperform professional traders in finance.
method Comprehensive review of current research on LLMs in financial trading.
result LLMs can potentially outperform professional traders in backtesting.
IMPACT improves RL training speed without sacrificing sample efficiency.
problem Limited sample efficiency in scalable RL architectures.
method Proposes IMPACT, extending IMPALA with target networks, circular buffers, and truncated importance sampling.
result IMPACT achieves higher rewards and significantly reduces training time compared to IMPALA.
Transformers as Game Players: Provable In-context Game-playing Capabilities of Pre-trained Modelsstat.ML
Transformers learn to play games in-context, proving Nash equilibrium.
problem Understanding in-context game-playing capabilities of pre-trained transformers.
method Theoretical guarantees and constructional results for transformer architecture in multi-agent games.
result Pre-trained transformers can learn Nash equilibrium in-context for two-player zero-sum games.
A novel framework combines LLMs and RL for financial portfolio optimization.
problem Optimizing financial portfolios using sentiment analysis and market indicators.
method Hierarchical RL structure with base, meta, and super-agents.
result Achieved a 26% annualized return and Sharpe ratio of 1.2.
AgentNet is a graph neural network that learns to walk graphs intelligently, outperforming traditional methods.
problem Graph-level tasks, especially distinguishing and classifying graphs.
method AgentNet uses a computational model inspired by sublinear algorithms, where neural agents walk the graph and collectively decide the output.
result AgentNet can distinguish and separate graphs that are hard to distinguish, outperforming traditional graph neural networks.
Policy-gradient method controls multiple non-cohesive targets.
problem Controlling multiple non-cohesive targets in a decentralized manner.
method Proximal Policy Optimization for target selection and driving.
result Effective control of non-cohesive targets without prior dynamics knowledge.
QPLEX learns efficient multi-agent Q-values by enforcing IGM principle.
problem Scalable multi-agent reinforcement learning with IGM consistency.
method Dueling duplex network architecture to enforce IGM principle.
result QPLEX achieves high sample efficiency and benefits from offline data.
We present a data mining approach for profiling bank clients in order to support the process of detection of anti-money laundering operations. We first present the overall system architecture, and then focus on the relevant component for this paper. We detail the experiments performed on real world data from a financia…
How to Identify Investor's types in real financial markets by means of agent based simulationq-fin.TR
Paper uses agent-based simulation to identify investor types in financial markets.
problem Identifying investor types in real financial markets.
method Computational adaptation of PCA with agent-based simulation.
result A reduced set of investor models can approximate financial time series.
A variety of cooperative multi-agent control problems require agents to achieve individual goals while contributing to collective success. This multi-goal multi-agent setting poses difficulties for recent algorithms, which primarily target settings with a single global reward, due to two new challenges: efficient explo…
A System for Morphology-Task Generalization via Unified Representation and Behavior Distillationcs.LG
A method for a single policy to solve various tasks across diverse agent morphologies.
problem Generalizing a single policy to solve various tasks across diverse agent morphologies.
method Unified representation and behavior distillation using a morphology-task graph and Transformer architecture.
result Improves multi-task performances compared to baselines, suggesting a promising approach.
ESAC improves reinforcement learning by lookahead and intuition.
problem Designing efficient reinforcement learning architectures for intelligent agents.
method Integrates selector, tuner, model-learner, estimator, and lookahead into ESAC.
result ESAC outperforms other architectures in optimizing policies.
TradingAgents uses LLM-powered multi-agent framework for financial trading.
problem Lack of collaborative dynamics in multi-agent financial trading systems.
method Inspired by real-world trading firms, TradingAgents features specialized LLM-powered agents and a risk management team.
result Framework outperforms baseline models in trading performance metrics.
MPLP learns neural network weights by treating operations as message-passing agents.
problem Training neural networks using gradient-based methods.
method MPLP abstracts neural network operations as message-passing agents, updating internal states and passing messages.
result MPLP outperforms traditional gradient-based methods on simple feed-forward neural networks.
Hierarchical AI multi-agent framework optimizes equity portfolios in China's A-share market.
problem Optimizing equity portfolios in China's A-share market using AI and multi-agent systems.
method A hierarchical multi-agent design integrating macro, firm-level, and reinforcement learning approaches.
result Consistently outperforms benchmarks and state-of-the-art systems on risk-adjusted returns and drawdown control.
HabitatAgent offers a multi-agent system for transparent housing consultation.
problem Opaque reasoning and brittle multi-constraint handling in housing recommendation systems.
method HabitatAgent is a multi-agent architecture with specialized roles for memory, retrieval, generation, and validation.
result HabitatAgent achieves 95% accuracy in real user consultation scenarios, significantly outperforming a strong baseline.