New method makes deep RL agents more understandable.
problem Incomprehensible decision-making in NN-based RL agents limits their applications.
method Derives a secondary comprehensible agent from a NN-based RL agent.
result Empirical evaluation supports the possibility of building a comprehensible agent.
InvestorBench benchmarks LLM agents in financial tasks.
problem Lack of a comprehensive benchmark for LLM-based financial agents.
method Developed a benchmark with diverse financial tasks and datasets.
result Evaluated LLM agents' performance across various financial products and market environments.
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.
FinReflectKG builds a comprehensive financial knowledge graph from SEC filings, improving extraction quality.
problem Lack of large-scale, open-source financial knowledge graph datasets.
method Intelligent document parsing, table-aware chunking, schema-guided iterative extraction, reflection-driven feedback loop.
result Reflection-agent-based mode achieves best balance of efficiency, accuracy, and reliability.
FinRobot AI agent for equity research provides comprehensive insights.
problem Narrow focus and limited discretion in AI solutions for equity research.
method Multi-agent Chain of Thought system integrating quantitative and qualitative analyses.
result FinRobot delivers insights comparable to major brokerage firms.
Study uses AI agents to improve equity portfolio management.
problem Improving stock selection and portfolio management efficiency.
method Role-based multi-agent systems for equity research.
result Multi-agent approach outperforms benchmarks in stock selection.
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.
Study compares MAPF and MARL algorithms for warehouse automation.
problem Optimizing multi-agent pickup and delivery in warehouse settings.
method Compared conflict-based search (MAPF) and shared experience actor-critic (MARL).
result Comprehensive benchmarking of MAPF and MARL in a simulated warehouse environment.
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.
PEAR dynamically reconfigures agent roles to prevent persistent biases in multi-agent debates.
problem Persistent positional biases and sensitivity to role assignments in fixed topologies.
method Dynamic reconfiguration of agent roles and sparse topologies based on evolving agent states.
result Significantly improves average accuracy over debate baselines across multiple reasoning benchmarks.
This study benchmarks AI agents for personalized retail promotions using simulations.
problem Optimizing coupon targeting for sparse customer purchase events.
method Comprehensive simulations of customer shopping behaviors; training RL agents on batch data.
result Contextual bandit and deep RL methods outperform static policies in sparse reward environments.
New bounds on predicting agent behavior from behavior alone.
problem Predicting agent beliefs and intentions from observed behavior.
method Derivation of bounds on agent behavior in new environments under assumption of world model.
result Theoretical limits on predicting intentional agents from behavioral data.
We address microscopic, agent based, and macroscopic, stochastic, modeling of the financial markets combining it with the exogenous noise. The interplay between the endogenous dynamics of agents and the exogenous noise is the primary mechanism responsible for the observed long-range dependence and statistical propertie…
Interactive machine comprehension models learn through seeking relevant information.
problem Existing MRC models struggle with real-world applications due to static datasets.
method Reframe MRC datasets as interactive, partially observable environments.
result Interactive models can seek relevant information through sequential decision making.
Enhances anomaly detection in financial markets using AI agents.
problem Manual verification of financial market anomalies is time-consuming and error-prone.
method A multi-agent LLM framework for automated anomaly detection.
result Framework reduces human intervention and improves efficiency and accuracy.
The paper aims to develop a methodology to test memory systems in reinforcement learning agents.
problem Understanding and evaluating memory systems in reinforcement learning agents and their generalization.
method Construct diverse memory tasks, develop an agent architecture combining multiple memory systems, and perform ablations.
result The agent architecture can apply learned knowledge to holdout data that differs from the training data.
New method defends RL agents from poisoning attacks without MDP knowledge.
problem Poisoning attacks on RL systems can cause learning failures.
method Generic poisoning framework for online RL, Vulnerability-Aware Adversarial Critic Poison (VA2C-P).
result Successfully prevents RL agents from learning good policies or converging to target policies.
RL framework optimizes trading costs in noisy markets.
problem Optimal execution and placement in noisy markets.
method Dual-window Denoise PPO RL network, imitation learning, comprehensive market features, flexible action formulation.
result RL agents outperformed TWAP strategy in execution cost.
MARLA uses deep reinforcement learning for multi-agent AHT, reducing Bayes risk.
problem Decentralized active hypothesis testing among multiple agents.
method MARLA algorithm using deep multi-agent reinforcement learning.
result MARLA outperforms single-agent learning in AHT problems.
VERAFI improves financial AI by verifying calculations and compliance.
problem Financial AI systems generate errors and violations during reasoning.
method VERAFI combines dense retrieval, reranking, and automated reasoning policies.
result VERAFI achieves 94.7% factual correctness, 81% relative improvement.
This study models AI traders' impact on financial markets using a multi-agent framework.
problem Lack of a comprehensive model to assess AI traders' effects on market price formation and volatility.
method Developed a multi-agent market model with microfoundations of the GARCH model.
result Validated the model through simulations and analyzed AI traders' impact.
Paper reviews the evolution of alpha from human insight to AI-powered systems.
problem Exceeding market benchmarks in finance.
method Five-stage taxonomy integrating representation learning, multimodal data fusion, and LLM agents.
result Unified framework for evaluating and developing next-gen alpha systems.
We are increasingly surrounded by artificially intelligent technology that takes decisions and executes actions on our behalf. This creates a pressing need for general means to communicate with, instruct and guide artificial agents, with human language the most compelling means for such communication. To achieve this i…
Study uses LLMs for financial sentiment analysis without fine-tuning.
problem Lack of prescriptive knowledge to leverage generative models in FSA.
method Proposes a design framework with heterogeneous LLM agents based on Minsky's theory.
result Framework yields better accuracies, especially with substantial discussions.
A novel fact-checking method using debate dynamics on knowledge graphs.
problem Fact-checking on knowledge graphs with user comprehension and interactive reasoning.
method Reinforcement learning agents debate on paths in the graph to classify facts as true or false.
result Interactive reasoning and user understanding of AI decisions on knowledge graphs.
Enhanced financial trading system using multi-agent LLMs with layered memory.
problem Inefficient prioritization of tasks in LLMs due to their memory processing.
method Introducing a multi-agent framework with layered memories and inter-agent debate.
result Superior automated trading accuracy and decision robustness.
A novel memory mechanism for reinforcement learning agents that stores past events in human-readable language.
problem Lack of interpretability in reinforcement learning agent's memory mechanisms.
method Uses CLIP to associate visual inputs with language tokens, then feeds these tokens to a pretrained language model.
result Significantly faster convergence on challenging continuous recognition tasks.
New algorithms tackle latent bandit problems with lower regret.
problem Learning optimal actions in a latent state setting.
method General algorithms based on UCBs and Thompson sampling, aware of model uncertainty.
result Our methods have lower regret than classic bandit policies when latent states are fewer than actions.
Hybrid model simulates market dynamics using neural stochastic background traders.
problem Lack of realistic LOB simulations that combine historical data and dynamic interactions.
method Neural stochastic background trader trained on historical LOB data, embedded in multi-agent simulation.
result Hybrid model recreates stylised market facts and financial herding behaviors.
The aim of this paper is to develop a general framework for training neural networks (NNs) in a distributed environment, where training data is partitioned over a set of agents that communicate with each other through a sparse, possibly time-varying, connectivity pattern. In such distributed scenario, the training prob…
CausalEvolve improves efficiency and discovery in open-ended scientific tasks.
problem Lack of targeted guidance and knowledge organization in evolve-based agents.
method Causal scratchpad that identifies and reasons about guiding factors for evolution.
result Effective improvement in evolutionary efficiency and better solutions.
Enhanced financial reward with shuffled feature CNN-DRL.
problem Improving reward in financial data using CNN-DRL.
method Applying shuffled features to financial data for CNN-DRL.
result Substantial enhancement in reward attainment.
New framework predicts cryptocurrency trends by analyzing news and market data.
problem Cryptocurrency market volatility and news sensitivity challenges prediction accuracy.
method Multi-agent system with three innovations: news analysis, fusion mechanism, and coordination architecture.
result Statistically significant improvements over state-of-the-art methods.
FedCM measures contributions in real-time for federated learning.
problem Fairly allocating contributions in federated learning systems.
method FedCM calculates impact based on current and previous rounds with attention aggregation.
result FedCM is more sensitive to data quality and quantity in real-time.
Study of LQ MFGs in infinite-dimensional Hilbert spaces.
problem Mean field games in infinite-dimensional settings with stochastic dynamics.
method Analysis of coupled semilinear infinite-dimensional stochastic evolution equations, development of Nash equilibrium.
result Characterization of unique Nash equilibrium in the limit of many agents.
A new decentralized algorithm DESTINY solves optimization over Stiefel manifold with single communication round.
problem Decentralized optimization over the Stiefel manifold with private data.
method Gradient tracking with approximate augmented Lagrangian function.
result DESTINY achieves global convergence with a single communication round.
Proposes a new method for conversational agents using deep learning.
problem Building coherent and non-monotonous conversational agents with proper discourse and coverage.
method End-to-end multi-stream deep learning architecture leveraging contextual and syntactic information.
result Significantly improved next sentence prediction task.
SLM Lab is a framework for reproducible RL research with modular algorithms.
problem Reproducibility in deep reinforcement learning.
method Modular software framework for RL algorithms, synchronous/asynchronous execution, hyperparameter search, result analysis.
result Comprehensive benchmark and novel RL algorithms (e.g., discrete-AC variant, hybrid training method).
This paper uses deep RL to optimize market quotes from LOB data.
problem Optimizing quotes for market making from complex LOB data.
method Attn-LOB neural network with convolutional filters and attention mechanism for feature extraction; hybrid reward function for continuous action space.
result The RL agent outperforms traditional methods in market making tasks.
PyFi uses adversarial agents to train VLMs on financial image understanding.
problem Training VLMs to understand complex financial questions.
method PyFi-600K dataset and adversarial MCTS mechanism.
result Fine-tuned VLMs improve by 19.52% and 8.06% on financial question accuracy.
WebGUM learns web navigation from multimodal data, outperforming previous methods.
problem Limited generalization from domain-specific models in web navigation.
method Instruction-following multimodal agent trained on vision-language foundation models.
result Significant improvement in web navigation performance on benchmarks.
COKE reduces communication in decentralized kernel learning.
problem Decentralized kernel learning challenges due to data-dependent decision variables.
method Random feature approximation and ADMM for iterative optimization; communication-censored algorithm.
result COKE achieves faster convergence and reduced communication load.
Model-free reinforcement learning agents outperform traditional portfolio management models in asset allocation.
problem Optimizing asset allocation in financial markets with limited historical data.
method Developed and compared model-based and model-free reinforcement learning agents (DSRQN, MSM) for trading efficiency.
result Model-free reinforcement learning agents achieve superior performance in asset allocation, outperforming traditional models by 9.2% in annualized cumulative returns and 13.4% in annualized Sharpe Ratio.
FinReflectKG - EvalBench benchmarks financial KG extraction from SEC 10-K filings.
problem Lack of universal benchmark and evaluation framework for financial KG construction.
method Agentic and holistic evaluation principles, deterministic commit-then-justify judging protocol, binary and ordinal evaluations.
result Reflection-based extraction outperforms single-pass extraction in comprehensiveness, precision, and relevance.
The study addresses biases in evaluating molecular optimization methods and proposes methods to reduce these biases.
problem Biases in in silico evaluation of molecular optimization methods.
method Discussion and empirical investigation of bias reduction methods for predictor misspecification and sample reuse.
result Empirical investigation of bias reduction methods for predictor misspecification and sample reuse.
Survey of RL methods for control systems with time delays.
problem Time delays in cyber-physical systems degrade RL performance and stability.
method Categorizes and analyzes five major families of RL methods for time delays.
result Identifies key trade-offs and practical guidelines for selecting RL methods.
Paper validates ABM using stylized financial facts.
problem Validate ABM-generated financial data against real-world data.
method Compare ABM results with stylized financial facts.
result Model successfully replicates stylized financial facts.
FinAgent tackles financial trading with multimodal data and advanced AI.
problem Challenges in handling multimodal financial data and limited generalizability.
method Multimodal foundational agent with tool augmentation, dual-level reflection, and diversified memory retrieval.
result Significantly outperforms state-of-the-art baselines in financial trading tasks.