AI Trends

Rethinking Evaluation for LLM Hallucination Detection: A Desiderata, A New RAG-based Benchmark, New Insights

arXiv cs.AI · May 13, 2026

arXiv:2605.11330v1 Announce Type: new Abstract: Hallucination, broadly referring to unfaithful, fabricated, or inconsistent content generated by LLMs, has wide-ranging implications. Therefore, a large body of effort has…

IPI-proxy: An Intercepting Proxy for Red-Teaming Web-Browsing AI Agents Against Indirect Prompt Injection

arXiv cs.AI · May 13, 2026

arXiv:2605.11868v1 Announce Type: cross Abstract: Web-browsing AI agents are increasingly deployed in enterprise settings under strict whitelists of approved domains, yet adversaries can still influence them by embeddin…

Rethinking Supervision Granularity: Segment-Level Learning for LLM-Based Theorem Proving

arXiv cs.AI · May 13, 2026

arXiv:2605.11905v1 Announce Type: new Abstract: Automated theorem proving with large language models in Lean 4 is commonly approached through either step-level tactic prediction with tree search or whole-proof generatio…

Seir\^enes: Adversarial Self-Play with Evolving Distractions for LLM Reasoning

arXiv cs.AI · May 13, 2026

arXiv:2605.11636v1 Announce Type: new Abstract: We present Seir\^enes, a self-play RL framework that transforms contextual interference from a failure mode of LLM reasoning into an internal training signal for co-evolvi…

Hierarchical Multi-Scale Graph Neural Networks: Scalable Heterophilous Learning with Oversmoothing and Oversquashing Mitigation

arXiv cs.AI · May 13, 2026

arXiv:2605.10975v1 Announce Type: cross Abstract: Graphs with heterophily, where adjacent nodes carry different labels, are prevalent in real-world applications, from social networks to molecular interactions. However,…

OLIVIA: Online Learning via Inference-time Action Adaptation for Decision Making in LLM ReAct Agents

arXiv cs.AI · May 13, 2026

arXiv:2605.11169v1 Announce Type: new Abstract: Large language model agents interleave reasoning, action selection, and observation to solve sequential decision-making tasks. In deployed settings where agents repeatedly…

PIVOT: Bridging Planning and Execution in LLM Agents via Trajectory Refinement

arXiv cs.AI · May 13, 2026

arXiv:2605.11225v1 Announce Type: new Abstract: Large language model (LLM)-based agents frequently generate seemingly coherent plans that fail upon execution due to infeasible actions, constraint violations, and compoun…

Rethinking LLMOps for Fraud and AML: Building a Compliance-Grade LLM Serving Stack

arXiv cs.AI · May 13, 2026

arXiv:2605.11232v1 Announce Type: new Abstract: Fraud detection and anti-money-laundering (AML) compliance are high-value domains for large language models (LLMs), but their serving requirements differ sharply from gene…

The Semantic Training Gap: Ontology-Grounded Tool Architectures for Industrial AI Agent Systems

arXiv cs.AI · May 13, 2026

arXiv:2605.11234v1 Announce Type: new Abstract: Large language model (LLM)-based AI agents are increasingly deployed in manufacturing environments for analytics, quality management, and decision support. These agents de…

Unlocking LLM Creativity in Science through Analogical Reasoning

arXiv cs.AI · May 13, 2026

arXiv:2605.11258v1 Announce Type: new Abstract: Autonomous science promises to augment scientific discovery, particularly in complex fields like biomedicine. However, this requires AI systems that can consistently gener…