🌈 Recommendation Diversity - tomasz · Scour

CHEEM: Continual Learning by Reuse, New, Adapt and Skip -- A Hierarchical Exploration-Exploitation Approach 💬Prompt Engineering

arxiv.org·6d

Break suffocating routines by opening yourself up to seasons of serendipity 🧘Digital Minimalism

theglobeandmail.com

·6d

Rethinking Exploration in RLVR: From Entropy Regularization to Refinement via Bidirectional Entropy Modulation 💬Prompt Engineering

arxiv.org·1d

Towards Trustworthy Report Generation: A Deep Research Agent with Progressive Confidence Estimation and Calibration 🧠LLM Reasoning

arxiv.org·23h

Enhancing Multi-Robot Exploration Using Probabilistic Frontier Prioritization with Dirichlet Process Gaussian Mixtures 🤖AI Agents

arxiv.org·2d

Planning to Explore: Curiosity-Driven Planning for LLM Test Generation 💬Prompt Engineering

arxiv.org·23h

Hypothesis Graph Refinement: Hypothesis-Driven Exploration with Cascade Error Correction for Embodied Navigation 🦊Information Foraging

arxiv.org·1d

Edge-Oriented Orchestration of Energy Services Using Graph-Driven Swarm Intelligence 🔗Peer-to-Peer Networks

arxiv.org·1d

Locally Confident, Globally Stuck: The Quality-Exploration Dilemma in Diffusion Language Models 🔢Kolmogorov Complexity

arxiv.org·5d

SkillX: Automatically Constructing Skill Knowledge Bases for Agents 🧠LLM Reasoning

arxiv.org·1d

Asymptotically-Bounded 3D Frontier Exploration enhanced with Bayesian Information Gain 📊Bayesian Inference

arxiv.org·2d

Lipschitz Dueling Bandits over Continuous Action Spaces 🔢Kolmogorov Complexity

arxiv.org·6d

PATHFINDER: Multi-objective discovery in structural and spectral spaces 🦊Information Foraging

arxiv.org·1d

CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery 🤖AI Agents

arxiv.org·5d

OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration 💬Prompt Engineering

arxiv.org·2d

Cognibit: From Digital Exhaustion to Real-World Connection Through Gamified Territory Control and LLM-Powered Twin Networking 🤖Local LLMs

arxiv.org·1d

Cog-DRIFT: Exploration on Adaptively Reformulated Instances Enables Learning from Hard Reasoning Problems 🧠LLM Reasoning

arxiv.org·1d

Tight Bounds on Window Size and Time for Single-Agent Graph Exploration under T-Interval Connectivity 🕸️Graph Theory

arxiv.org·1d

BLADE: Better Language Answers through Dialogue and Explanations 🔬Explorable Explanations

arxiv.org·1d

Diffusion Policy with Bayesian Expert Selection for Active Multi-Target Tracking 📊Bayesian Inference

arxiv.org·1d

Loading more...