The PhD students who became the judges of the AI industry
Artificial intelligence models are multiplying fast, and competition is stiff. With so many players crowding the space, which one will be the best — and who decides that? Arena, formerly LM Arena, has emerged as the de facto public leaderboard...
Regularized Latent Dynamics Prediction is a Strong Baseline For Behavioral Foundation Models
arXiv:2603.15857v1 Announce Type: new Abstract: Behavioral Foundation Models (BFMs) produce agents with the capability to adapt to any unknown reward or task. These methods, however, are only able to produce near-optimal policies for the reward functions that are in the...
Selective Memory for Artificial Intelligence: Write-Time Gating with Hierarchical Archiving
arXiv:2603.15994v1 Announce Type: new Abstract: Retrieval-augmented generation stores all content indiscriminately, degrading accuracy as noise accumulates. Parametric approaches compress knowledge into weights, precluding selective updates. Neither mirrors biological memory, which gates encoding based on salience and archives rather than deletes...
Prose2Policy (P2P): A Practical LLM Pipeline for Translating Natural-Language Access Policies into Executable Rego
arXiv:2603.15799v1 Announce Type: new Abstract: Prose2Policy (P2P) is a LLM-based practical tool that translates natural-language access control policies (NLACPs) into executable Rego code (the policy language of Open Policy Agent, OPA). It provides a modular, end-to-end pipeline that performs policy...
Argumentative Human-AI Decision-Making: Toward AI Agents That Reason With Us, Not For Us
arXiv:2603.15946v1 Announce Type: new Abstract: Computational argumentation offers formal frameworks for transparent, verifiable reasoning but has traditionally been limited by its reliance on domain-specific information and extensive feature engineering. In contrast, LLMs excel at processing unstructured text, yet their opaque...
From Workflow Automation to Capability Closure: A Formal Framework for Safe and Revenue-Aware Customer Service AI
arXiv:2603.15978v1 Announce Type: new Abstract: Customer service automation is undergoing a structural transformation. The dominant paradigm is shifting from scripted chatbots and single-agent responders toward networks of specialised AI agents that compose capabilities dynamically across billing, service provision, payments, and...
Semi-Autonomous Formalization of the Vlasov-Maxwell-Landau Equilibrium
arXiv:2603.15929v1 Announce Type: new Abstract: We present a complete Lean 4 formalization of the equilibrium characterization in the Vlasov-Maxwell-Landau (VML) system, which describes the motion of charged plasma. The project demonstrates the full AI-assisted mathematical research loop: an AI reasoning...
Did You Check the Right Pocket? Cost-Sensitive Store Routing for Memory-Augmented Agents
arXiv:2603.15658v1 Announce Type: new Abstract: Memory-augmented agents maintain multiple specialized stores, yet most systems retrieve from all stores for every query, increasing cost and introducing irrelevant context. We formulate memory retrieval as a store-routing problem and evaluate it using coverage,...
VIGIL: Towards Edge-Extended Agentic AI for Enterprise IT Support
arXiv:2603.16110v1 Announce Type: new Abstract: Enterprise IT support is constrained by heterogeneous devices, evolving policies, and long-tail failure modes that are difficult to resolve centrally. We present VIGIL, an edge-extended agentic AI system that deploys desktop-resident agents to perform situated...
Protein Design with Agent Rosetta: A Case Study for Specialized Scientific Agents
arXiv:2603.15952v1 Announce Type: new Abstract: Large language models (LLMs) are capable of emulating reasoning and using tools, creating opportunities for autonomous agents that execute complex scientific tasks. Protein design provides a natural testbed: although machine learning (ML) methods achieve strong...
BANGLASOCIALBENCH: A Benchmark for Evaluating Sociopragmatic and Cultural Alignment of LLMs in Bangladeshi Social Interaction
arXiv:2603.15949v1 Announce Type: new Abstract: Large Language Models have demonstrated strong multilingual fluency, yet fluency alone does not guarantee socially appropriate language use. In high-context languages, communicative competence requires sensitivity to social hierarchy, relational roles, and interactional norms that are...
NLP Occupational Emergence Analysis: How Occupations Form and Evolve in Real Time -- A Zero-Assumption Method Demonstrated on AI in the US Technology Workforce, 2022-2026
arXiv:2603.15998v1 Announce Type: new Abstract: Occupations form and evolve faster than classification systems can track. We propose that a genuine occupation is a self-reinforcing structure (a bipartite co-attractor) in which a shared professional vocabulary makes practitioners cohesive as a group,...
Interpretable Context Methodology: Folder Structure as Agentic Architecture
arXiv:2603.16021v1 Announce Type: new Abstract: Current approaches to AI agent orchestration typically involve building multi-agent frameworks that manage context passing, memory, error handling, and step coordination through code. These frameworks work well for complex, concurrent systems. But for sequential workflows...
MAC: Multi-Agent Constitution Learning
arXiv:2603.15968v1 Announce Type: new Abstract: Constitutional AI is a method to oversee and control LLMs based on a set of rules written in natural language. These rules are typically written by human experts, but could in principle be learned automatically...
NextMem: Towards Latent Factual Memory for LLM-based Agents
arXiv:2603.15634v1 Announce Type: new Abstract: Memory is critical for LLM-based agents to preserve past observations for future decision-making, where factual memory serves as its foundational part. However, existing approaches to constructing factual memory face several limitations. Textual methods impose heavy...
A Context Alignment Pre-processor for Enhancing the Coherence of Human-LLM Dialog
arXiv:2603.16052v1 Announce Type: new Abstract: Large language models (LLMs) have made remarkable progress in generating fluent text, but they still face a critical challenge of contextual misalignment in long-term and dynamic dialogue. When human users omit premises, simplify references, or...
Adaptive Theory of Mind for LLM-based Multi-Agent Coordination
arXiv:2603.16264v1 Announce Type: new Abstract: Theory of Mind (ToM) refers to the ability to reason about others' mental states, and higher-order ToM involves considering that others also possess their own ToM. Equipping large language model (LLM)-driven agents with ToM has...
Morphemes Without Borders: Evaluating Root-Pattern Morphology in Arabic Tokenizers and LLMs
arXiv:2603.15773v1 Announce Type: new Abstract: This work investigates how effectively large language models (LLMs) and their tokenization schemes represent and generate Arabic root-pattern morphology, probing whether they capture genuine morphological structure or rely on surface memorization. Arabic morphological system provides...
Are Large Language Models Truly Smarter Than Humans?
arXiv:2603.16197v1 Announce Type: new Abstract: Public leaderboards increasingly suggest that large language models (LLMs) surpass human experts on benchmarks spanning academic knowledge, law, and programming. Yet most benchmarks are fully public, their questions widely mirrored across the internet, creating systematic...
POaaS: Minimal-Edit Prompt Optimization as a Service to Lift Accuracy and Cut Hallucinations on On-Device sLLMs
arXiv:2603.16045v1 Announce Type: new Abstract: Small language models (sLLMs) are increasingly deployed on-device, where imperfect user prompts--typos, unclear intent, or missing context--can trigger factual errors and hallucinations. Existing automatic prompt optimization (APO) methods were designed for large cloud LLMs and...
MoLoRA: Composable Specialization via Per-Token Adapter Routing
arXiv:2603.15965v1 Announce Type: new Abstract: Multi-adapter serving systems route entire sequences to a single adapter, forcing a choice when requests span multiple domains. This assumption fails in two important settings: (1) multimodal generation, where text and image tokens require different...
SEAHateCheck: Functional Tests for Detecting Hate Speech in Low-Resource Languages of Southeast Asia
arXiv:2603.16070v1 Announce Type: new Abstract: Hate speech detection relies heavily on linguistic resources, which are primarily available in high-resource languages such as English and Chinese, creating barriers for researchers and platforms developing tools for low-resource languages in Southeast Asia, where...
Parametric Social Identity Injection and Diversification in Public Opinion Simulation
arXiv:2603.16142v1 Announce Type: new Abstract: Large language models (LLMs) have recently been adopted as synthetic agents for public opinion simulation, offering a promising alternative to costly and slow human surveys. Despite their scalability, current LLM-based simulation methods fail to capture...
Polyglot-Lion: Efficient Multilingual ASR for Singapore via Balanced Fine-Tuning of Qwen3-ASR
arXiv:2603.16184v1 Announce Type: new Abstract: We present Polyglot-Lion, a family of compact multilingual automatic speech recognition (ASR) models tailored for the linguistic landscape of Singapore, covering English, Mandarin, Tamil, and Malay. Our models are obtained by fine-tuning Qwen3-ASR-0.6B and Qwen3-ASR-1.7B...
Structured Semantic Cloaking for Jailbreak Attacks on Large Language Models
arXiv:2603.16192v1 Announce Type: new Abstract: Modern LLMs employ safety mechanisms that extend beyond surface-level input filtering to latent semantic representations and generation-time reasoning, enabling them to recover obfuscated malicious intent during inference and refuse accordingly, and rendering many surface-level obfuscation...
Is Semi-Automatic Transcription Useful in Corpus Creation? Preliminary Considerations on the KIParla Corpus
arXiv:2603.16258v1 Announce Type: new Abstract: This paper analyses the implementation of Automatic Speech Recognition (ASR) into the transcription workflow of the KIParla corpus, a resource of spoken Italian. Through a two-phase experiment, 11 expert and novice transcribers produced both manual...
PashtoCorp: A 1.25-Billion-Word Corpus, Evaluation Suite, and Reproducible Pipeline for Low-Resource Language Development
arXiv:2603.16354v1 Announce Type: new Abstract: We present PashtoCorp, a 1.25-billion-word corpus for Pashto, a language spoken by 60 million people that remains severely underrepresented in NLP. The corpus is assembled from 39 sources spanning seven HuggingFace datasets and 32 purpose-built...
RECOVER: Robust Entity Correction via agentic Orchestration of hypothesis Variants for Evidence-based Recovery
arXiv:2603.16411v1 Announce Type: new Abstract: Entity recognition in Automatic Speech Recognition (ASR) is challenging for rare and domain-specific terms. In domains such as finance, medicine, and air traffic control, these errors are costly. If the entities are entirely absent from...
IndexRAG: Bridging Facts for Cross-Document Reasoning at Index Time
arXiv:2603.16415v1 Announce Type: new Abstract: Multi-hop question answering (QA) requires reasoning across multiple documents, yet existing retrieval-augmented generation (RAG) approaches address this either through graph-based methods requiring additional online processing or iterative multi-step reasoning. We present IndexRAG, a novel approach...