Exploring Big Five Personality and AI Capability Effects in LLM-Simulated Negotiation Dialogues. arxiv.org/abs/2506.15928

Dual-Objective Reinforcement Learning with Novel Hamilton-Jacobi-Bellman Formulations. arxiv.org/abs/2506.16016

Consistency Verification in Ontology-Based Process Models with Parameter Interdependencies. arxiv.org/abs/2506.16087

Geometric Learning in Black-Box Optimization: A GNN Framework for Algorithm Performance Prediction. arxiv.org/abs/2506.16144

Large Language Models are Near-Optimal Decision-Makers with a Non-Human Learning Behavior. arxiv.org/abs/2506.16163

Evaluating Generalization and Representation Stability in Small LMs via Prompting. arxiv.org/abs/2506.17289

Individual Causal Inference with Structural Causal Model. arxiv.org/abs/2506.17300

Resource Rational Contractualism Should Guide AI Alignment. arxiv.org/abs/2506.17434

OmniReflect: Discovering Transferable Constitutions for LLM agents via Neuro-Symbolic Reflections. arxiv.org/abs/2506.17449

From Unstructured Communication to Intelligent RAG: Multi-Agent Automation for Supply Chain Knowledge Bases. arxiv.org/abs/2506.17484

Kaleidoscopic Teaming in Multi Agent Simulations. arxiv.org/abs/2506.17514

Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Models. arxiv.org/abs/2506.17585

Taming the Untamed: Graph-Based Knowledge Retrieval and Reasoning for MLLMs to Conquer the Unknown. arxiv.org/abs/2506.17589

Measuring and Augmenting Large Language Models for Solving Capture-the-Flag Challenges. arxiv.org/abs/2506.17644

PhysUniBench: An Undergraduate-Level Physics Reasoning Benchmark for Multimodal Models. arxiv.org/abs/2506.17667

Beyond Syntax: Action Semantics Learning for App Agents. arxiv.org/abs/2506.17697

AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction. arxiv.org/abs/2506.17784

Efficient Strategy Synthesis for MDPs via Hierarchical Block Decomposition. arxiv.org/abs/2506.17792

Reflective Verbal Reward Design for Pluralistic Alignment. arxiv.org/abs/2506.17834

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack). arxiv.org/abs/2506.17846