AI Agents

persistent memory system for AI agents — single SQLite file, no external server, no API keys. free and opensource - BrainCTL

Every agent I build forgets everything between sessions. I got tired of it and built brainctl. pip install brainctl, then: from agentmemo...

Why does Multi-Agent RL fail to act like a real society in Spatial Game Theory? [P] [R]

Hey everyone, I’m building a project for my university Machine Learning course called "Social network analysis using iterated game theory...

AWS turns its S3 storage service into a file system for AI agents

[2601.20538] Interpreting Emergent Extreme Events in Multi-Agent Systems

This paper presents a framework for interpreting emergent extreme events in multi-agent systems, focusing on the origins and drivers of t...

[2511.19628] Optimization and Regularization Under Arbitrary Objectives

This article explores the limitations of Markov Chain Monte Carlo (MCMC) methods in optimization and regularization under arbitrary objec...

[2601.15235] Tracing 3D Anatomy in 2D Strokes: A Multi-Stage Projection Driven Approach to Cervical Spine Fracture Identification

This article presents a novel approach for identifying cervical spine fractures using a multi-stage projection method that combines 2D im...

[2601.15109] An Agentic Operationalization of DISARM for FIMI Investigation on Social Media

This article presents a framework-agnostic, agent-based operationalization of the DISARM framework to investigate Foreign Information Man...

[2601.12522] Improved Bug Localization with AI Agents Leveraging Hypothesis and Dynamic Cognition

The paper presents CogniGent, a novel AI technique for bug localization that enhances traditional methods by leveraging causal reasoning ...

[2601.02158] FormationEval, an open multiple-choice benchmark for petroleum geoscience

FormationEval introduces a benchmark for evaluating language models in petroleum geoscience, featuring 505 questions across multiple doma...

[2510.12272] Heterogeneous RBCs via Deep Multi-Agent Reinforcement Learning

This paper presents MARL-BC, a framework that combines deep multi-agent reinforcement learning with real business cycle models, addressin...

[2512.17979] Adaptive Agents in Spatial Double-Auction Markets: Modeling the Emergence of Industrial Symbiosis

This paper presents an agent-based model to explore how adaptive agents in spatial double-auction markets can foster industrial symbiosis...

[2512.20352] Multi-LLM Thematic Analysis with Dual Reliability Metrics: Combining Cohen's Kappa and Semantic Similarity for Qualitative Research Validation

This paper presents a novel framework for validating qualitative research using multi-LLM thematic analysis, integrating Cohen's Kappa an...

[2512.14166] IntentMiner: Intent Inversion Attack via Tool Call Analysis in the Model Context Protocol

The paper introduces IntentMiner, a novel approach to detect Intent Inversion Attacks in Large Language Models (LLMs) by analyzing tool c...

[2512.15829] Emergent human-like working memory from artificial neurons with intrinsic plasticity

The paper presents IPNet, a neuromorphic architecture that mimics human-like working memory through intrinsic plasticity, achieving high ...

[2512.13697] Writing in Symbiosis: Mapping Human Creative Agency in the AI Era

This article explores the evolving relationship between human creativity and AI, particularly in writing, highlighting how authors adapt ...

[2512.05430] ArtistMus: A Globally Diverse, Artist-Centric Benchmark for Retrieval-Augmented Music Question Answering

ArtistMus introduces a benchmark for music question answering, leveraging a diverse dataset to enhance retrieval-augmented generation mod...

[2512.04552] RRPO: Robust Reward Policy Optimization for LLM-based Emotional TTS

The paper presents Robust Reward Policy Optimization (RRPO), a novel framework designed to enhance emotional text-to-speech (TTS) systems...

[2509.02522] Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR

The paper presents PACS, a novel framework for Reinforcement Learning with Verifiable Rewards (RLVR), addressing challenges like sparse r...

[2511.01228] Importance Ranking in Complex Networks via Influence-aware Causal Node Embedding

This paper presents a novel framework for ranking node importance in complex networks using influence-aware causal node embedding, enhanc...

[2508.15555] HEAS: Hierarchical Evolutionary Agent Simulation Framework for Cross-Scale Modeling and Multi-Objective Search

The HEAS framework integrates agent-based modeling with evolutionary optimization, enabling cross-scale modeling and multi-objective sear...

[2508.10765] Memorisation and forgetting in a learning Hopfield neural network: bifurcation mechanisms, attractors and basins

This article explores the mechanisms of memorization and forgetting in Hopfield neural networks, revealing how bifurcations affect memory...

[2506.06964] Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization

This article presents a novel approach to offline reinforcement learning (RL) using reward-weighted fine-tuning, enhancing conversation o...

[2510.04455] Inverse Mixed-Integer Programming: Learning Constraints then Objective Functions

This article presents a novel two-stage approach to inverse mixed-integer programming that learns both constraints and objective function...