Empirical Comparison of Agent Communication Protocols for Task Orchestration
arXiv:2603.22823v1 Announce Type: new Abstract: Context. Nowadays, artificial intelligence agent systems are transforming from single-tool interactions to complex multi-agent orchestrations. As a result, two competing communication protocols have emerged: a tool integration protocol that standardizes how agents invoke external tools,...
Describe-Then-Act: Proactive Agent Steering via Distilled Language-Action World Models
arXiv:2603.23149v1 Announce Type: new Abstract: Deploying safety-critical agents requires anticipating the consequences of actions before they are executed. While world models offer a paradigm for this proactive foresight, current approaches relying on visual simulation incur prohibitive latencies, often exceeding several...
Intelligence Inertia: Physical Principles and Applications
arXiv:2603.22347v1 Announce Type: new Abstract: While Landauer's principle establishes the fundamental thermodynamic floor for information erasure and Fisher Information provides a metric for local curvature in parameter space, these classical frameworks function effectively only as approximations within regimes of sparse...
Beyond Preset Identities: How Agents Form Stances and Boundaries in Generative Societies
arXiv:2603.23406v1 Announce Type: new Abstract: While large language models simulate social behaviors, their capacity for stable stance formation and identity negotiation during complex interventions remains unclear. To overcome the limitations of static evaluations, this paper proposes a novel mixed-methods framework...
PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments
arXiv:2603.23231v1 Announce Type: new Abstract: Empowering large language models with long-term memory is crucial for building agents that adapt to users' evolving needs. However, prior evaluations typically interleave preference-related dialogues with irrelevant conversations, reducing the task to needle-in-a-haystack retrieval while...
LLM Olympiad: Why Model Evaluation Needs a Sealed Exam
arXiv:2603.23292v1 Announce Type: new Abstract: Benchmarks and leaderboards are how NLP most often communicates progress, but in the LLM era they are increasingly easy to misread. Scores can reflect benchmark-chasing, hidden evaluation choices, or accidental exposure to test content --...
CoMaTrack: Competitive Multi-Agent Game-Theoretic Tracking with Vision-Language-Action Models
arXiv:2603.22846v1 Announce Type: new Abstract: Embodied Visual Tracking (EVT), a core dynamic task in embodied intelligence, requires an agent to precisely follow a language-specified target. Yet most existing methods rely on single-agent imitation learning, suffering from costly expert data and...
Optimizing Small Language Models for NL2SQL via Chain-of-Thought Fine-Tuning
arXiv:2603.22942v1 Announce Type: new Abstract: Translating Natural Language to SQL (NL2SQL) remains a critical bottleneck for democratization of data in enterprises. Although Large Language Models (LLMs) like Gemini 2.5 and other LLMs have demonstrated impressive zero-shot capabilities, their high inference...
LGSE: Lexically Grounded Subword Embedding Initialization for Low-Resource Language Adaptation
arXiv:2603.22629v1 Announce Type: new Abstract: Adapting pretrained language models to low-resource, morphologically rich languages remains a significant challenge. Existing vocabulary expansion methods typically rely on arbitrarily segmented subword units, resulting in fragmented lexical representations and loss of critical morphological information....
Memory Bear AI Memory Science Engine for Multimodal Affective Intelligence: A Technical Report
arXiv:2603.22306v1 Announce Type: new Abstract: Affective judgment in real interaction is rarely a purely local prediction problem. Emotional meaning often depends on prior trajectory, accumulated context, and multimodal evidence that may be weak, noisy, or incomplete at the current moment....
PhySe-RPO: Physics and Semantics Guided Relative Policy Optimization for Diffusion-Based Surgical Smoke Removal
arXiv:2603.22844v1 Announce Type: new Abstract: Surgical smoke severely degrades intraoperative video quality, obscuring anatomical structures and limiting surgical perception. Existing learning-based desmoking approaches rely on scarce paired supervision and deterministic restoration pipelines, making it difficult to perform exploration or reinforcement-driven...
Less is More: Adapting Text Embeddings for Low-Resource Languages with Small Scale Noisy Synthetic Data
arXiv:2603.22290v1 Announce Type: new Abstract: Low-resource languages (LRLs) often lack high-quality, large-scale datasets for training effective text embedding models, hindering their application in tasks like retrieval-augmented generation (RAG) and semantic search. In this work, we challenge the prevailing assumption that...
RelayS2S: A Dual-Path Speculative Generation for Real-Time Dialogue
arXiv:2603.23346v1 Announce Type: new Abstract: Real-time spoken dialogue systems face a fundamental tension between latency and response quality. End-to-end speech-to-speech (S2S) models respond immediately and naturally handle turn-taking, backchanneling, and interruption, but produce semantically weaker outputs. Cascaded pipelines (ASR ->...
Can LLM Agents Generate Real-World Evidence? Evaluating Observational Studies in Medical Databases
arXiv:2603.22767v1 Announce Type: new Abstract: Observational studies can yield clinically actionable evidence at scale, but executing them on real-world databases is open-ended and requires coherent decisions across cohort construction, analysis, and reporting. Prior evaluations of LLM agents emphasize isolated steps...
Improving Safety Alignment via Balanced Direct Preference Optimization
arXiv:2603.22829v1 Announce Type: new Abstract: With the rapid development and widespread application of Large Language Models (LLMs), their potential safety risks have attracted widespread attention. Reinforcement Learning from Human Feedback (RLHF) has been adopted to enhance the safety performance of...
Session Risk Memory (SRM): Temporal Authorization for Deterministic Pre-Execution Safety Gates
arXiv:2603.22350v1 Announce Type: new Abstract: Deterministic pre-execution safety gates evaluate whether individual agent actions are compatible with their assigned roles. While effective at per-action authorization, these systems are structurally blind to distributed attacks that decompose harmful intent across multiple individually-compliant...
LLM-guided headline rewriting for clickability enhancement without clickbait
arXiv:2603.22459v1 Announce Type: new Abstract: Enhancing reader engagement while preserving informational fidelity is a central challenge in controllable text generation for news media. Optimizing news headlines for reader engagement is often conflated with clickbait, resulting in exaggerated or misleading phrasing...
Graph-Aware Late Chunking for Retrieval-Augmented Generation in Biomedical Literature
arXiv:2603.22633v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) systems for biomedical literature are typically evaluated using ranking metrics like Mean Reciprocal Rank (MRR), which measure how well the system identifies the single most relevant chunk. We argue that for full-text...
Functional Component Ablation Reveals Specialization Patterns in Hybrid Language Model Architectures
arXiv:2603.22473v1 Announce Type: new Abstract: Hybrid language models combining attention with state space models (SSMs) or linear attention offer improved efficiency, but whether both components are genuinely utilized remains unclear. We present a functional component ablation framework applied to two...
How Utilitarian Are OpenAI's Models Really? Replicating and Reinterpreting Pfeffer, Kr\"ugel, and Uhl (2025)
arXiv:2603.22730v1 Announce Type: new Abstract: Pfeffer, Kr\"ugel, and Uhl (2025) report that OpenAI's reasoning model o1-mini produces more utilitarian responses to the trolley problem and footbridge dilemma than the non-reasoning model GPT-4o. I replicate their study with four current OpenAI...
Towards Automated Community Notes Generation with Large Vision Language Models for Combating Contextual Deception
arXiv:2603.22453v1 Announce Type: new Abstract: Community Notes have emerged as an effective crowd-sourced mechanism for combating online deception on social media platforms. However, its reliance on human contributors limits both the timeliness and scalability. In this work, we study the...
When AI Shows Its Work, Is It Actually Working? Step-Level Evaluation Reveals Frontier Language Models Frequently Bypass Their Own Reasoning
arXiv:2603.22816v1 Announce Type: new Abstract: Language models increasingly "show their work" by writing step-by-step reasoning before answering. But are these reasoning steps genuinely used, or decorative narratives generated after the model has already decided? Consider: a medical AI writes "The...
Avoiding Over-smoothing in Social Media Rumor Detection with Pre-trained Propagation Tree Transformer
arXiv:2603.22854v1 Announce Type: new Abstract: Deep learning techniques for rumor detection typically utilize Graph Neural Networks (GNNs) to analyze post relations. These methods, however, falter due to over-smoothing issues when processing rumor propagation structures, leading to declining performance. Our investigation...
EchoKV: Efficient KV Cache Compression via Similarity-Based Reconstruction
arXiv:2603.22910v1 Announce Type: new Abstract: The increasing memory demand of the Key-Value (KV) cache poses a significant bottleneck for Large Language Models (LLMs) in long-context applications. Existing low-rank compression methods often rely on irreversible parameter transformations, sacrificing the flexibility to...
Multilingual KokoroChat: A Multi-LLM Ensemble Translation Method for Creating a Multilingual Counseling Dialogue Dataset
arXiv:2603.22913v1 Announce Type: new Abstract: To address the critical scarcity of high-quality, publicly available counseling dialogue datasets, we created Multilingual KokoroChat by translating KokoroChat, a large-scale manually authored Japanese counseling corpus, into both English and Chinese. A key challenge in...
DariMis: Harm-Aware Modeling for Dari Misinformation Detection on YouTube
arXiv:2603.22977v1 Announce Type: new Abstract: Dari, the primary language of Afghanistan, is spoken by tens of millions of people yet remains largely absent from the misinformation detection literature. We address this gap with DariMis, the first manually annotated dataset of...
Knowledge Access Beats Model Size: Memory Augmented Routing for Persistent AI Agents
arXiv:2603.23013v1 Announce Type: new Abstract: Production AI agents frequently receive user-specific queries that are highly repetitive, with up to 47\% being semantically similar to prior interactions, yet each query is typically processed with the same computational cost. We argue that...
Why AI-Generated Text Detection Fails: Evidence from Explainable AI Beyond Benchmark Accuracy
arXiv:2603.23146v1 Announce Type: new Abstract: The widespread adoption of Large Language Models (LLMs) has made the detection of AI-Generated text a pressing and complex challenge. Although many detection systems report high benchmark accuracy, their reliability in real-world settings remains uncertain,...
Decoding AI Authorship: Can LLMs Truly Mimic Human Style Across Literature and Politics?
arXiv:2603.23219v1 Announce Type: new Abstract: Amidst the rising capabilities of generative AI to mimic specific human styles, this study investigates the ability of state-of-the-art large language models (LLMs), including GPT-4o, Gemini 1.5 Pro, and Claude Sonnet 3.5, to emulate the...