ShipTraj-R1: Reinforcing Ship Trajectory Prediction in Large Language Models via Group Relative Policy Optimization
arXiv:2603.02939v1 Announce Type: new Abstract: Recent advancements in reinforcement fine-tuning have significantly improved the reasoning ability of large language models (LLMs). In particular, methods such as group relative policy optimization (GRPO) have demonstrated strong capabilities across various fields. However, applying...
Architecting Trust in Artificial Epistemic Agents
arXiv:2603.02960v1 Announce Type: new Abstract: Large language models increasingly function as epistemic agents -- entities that can 1) autonomously pursue epistemic goals and 2) actively shape our shared knowledge environment. They curate the information we receive, often supplanting traditional search-based...
OrchMAS: Orchestrated Reasoning with Multi Collaborative Heterogeneous Scientific Expert Structured Agents
arXiv:2603.03005v1 Announce Type: new Abstract: Multi-agent large language model frameworks are promising for complex multi step reasoning, yet existing systems remain weak for scientific and knowledge intensive domains due to static prompts and agent roles, rigid workflows, and homogeneous model...
REGAL: A Registry-Driven Architecture for Deterministic Grounding of Agentic AI in Enterprise Telemetry
arXiv:2603.03018v1 Announce Type: new Abstract: Enterprise engineering organizations produce high-volume, heterogeneous telemetry from version control systems, CI/CD pipelines, issue trackers, and observability platforms. Large Language Models (LLMs) enable new forms of agentic automation, but grounding such agents on private telemetry...
TikZilla: Scaling Text-to-TikZ with High-Quality Data and Reinforcement Learning
arXiv:2603.03072v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to assist scientists across diverse workflows. A key challenge is generating high-quality figures from textual descriptions, often represented as TikZ programs that can be rendered as scientific images....
RAPO: Expanding Exploration for LLM Agents via Retrieval-Augmented Policy Optimization
arXiv:2603.03078v1 Announce Type: new Abstract: Agentic Reinforcement Learning (Agentic RL) has shown remarkable potential in large language model-based (LLM) agents. These works can empower LLM agents to tackle complex tasks via multi-step, tool-integrated reasoning. However, an inherent limitation of existing...
No Memorization, No Detection: Output Distribution-Based Contamination Detection in Small Language Models
arXiv:2603.03203v1 Announce Type: new Abstract: CDD, or Contamination Detection via output Distribution, identifies data contamination by measuring the peakedness of a model's sampled outputs. We study the conditions under which this approach succeeds and fails on small language models ranging...
AI-for-Science Low-code Platform with Bayesian Adversarial Multi-Agent Framework
arXiv:2603.03233v1 Announce Type: new Abstract: Large Language Models (LLMs) demonstrate potentials for automating scientific code generation but face challenges in reliability, error propagation in multi-agent workflows, and evaluation in domains with ill-defined success metrics. We present a Bayesian adversarial multi-agent...
Density-Guided Response Optimization: Community-Grounded Alignment via Implicit Acceptance Signals
arXiv:2603.03242v1 Announce Type: new Abstract: Language models deployed in online communities must adapt to norms that vary across social, cultural, and domain-specific contexts. Prior alignment approaches rely on explicit preference supervision or predefined principles, which are effective for well-resourced settings...
Detecting AI-Generated Essays in Writing Assessment: Responsible Use and Generalizability Across LLMs
arXiv:2603.02353v1 Announce Type: new Abstract: Writing is a foundational literacy skill that underpins effective communication, fosters critical thinking, facilitates learning across disciplines, and enables individuals to organize and articulate complex ideas. Consequently, writing assessment plays a vital role in evaluating...
RO-N3WS: Enhancing Generalization in Low-Resource ASR with Diverse Romanian Speech Benchmarks
arXiv:2603.02368v1 Announce Type: new Abstract: We introduce RO-N3WS, a benchmark Romanian speech dataset designed to improve generalization in automatic speech recognition (ASR), particularly in low-resource and out-of-distribution (OOD) conditions. RO-N3WS comprises over 126 hours of transcribed audio collected from broadcast...
CoDAR: Continuous Diffusion Language Models are More Powerful Than You Think
arXiv:2603.02547v1 Announce Type: new Abstract: We study why continuous diffusion language models (DLMs) have lagged behind discrete diffusion approaches despite their appealing continuous generative dynamics. Under a controlled token--recovery study, we identify token rounding, the final projection from denoised embeddings...
How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities
arXiv:2603.02578v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in socially sensitive domains, yet their unpredictable behaviors, ranging from misaligned intent to inconsistent personality, pose significant risks. We introduce SteerEval, a hierarchical benchmark for evaluating LLM controllability...
Think, But Don't Overthink: Reproducing Recursive Language Models
arXiv:2603.02615v1 Announce Type: new Abstract: This project reproduces and extends the recently proposed ``Recursive Language Models'' (RLMs) framework by Zhang et al. (2026). This framework enables Large Language Models (LLMs) to process near-infinite contexts by offloading the prompt into an...
Real-Time Generation of Game Video Commentary with Multimodal LLMs: Pause-Aware Decoding Approaches
arXiv:2603.02655v1 Announce Type: new Abstract: Real-time video commentary generation provides textual descriptions of ongoing events in videos. It supports accessibility and engagement in domains such as sports, esports, and livestreaming. Commentary generation involves two essential decisions: what to say and...
MAGE: Meta-Reinforcement Learning for Language Agents toward Strategic Exploration and Exploitation
arXiv:2603.03680v1 Announce Type: new Abstract: Large Language Model (LLM) agents have demonstrated remarkable proficiency in learned tasks, yet they often struggle to adapt to non-stationary environments with feedback. While In-Context Learning and external memory offer some flexibility, they fail to...
A Rubric-Supervised Critic from Sparse Real-World Outcomes
arXiv:2603.03800v1 Announce Type: new Abstract: Academic benchmarks for coding agents tend to reward autonomous task completion, measured by verifiable rewards such as unit-test success. In contrast, real-world coding agents operate with humans in the loop, where success signals are typically...
In-Context Environments Induce Evaluation-Awareness in Language Models
arXiv:2603.03824v1 Announce Type: new Abstract: Humans often become more self-aware under threat, yet can lose self-awareness when absorbed in a task; we hypothesize that language models exhibit environment-dependent \textit{evaluation awareness}. This raises concerns that models could strategically underperform, or \textit{sandbag},...
Phi-4-reasoning-vision-15B Technical Report
arXiv:2603.03975v1 Announce Type: new Abstract: We present Phi-4-reasoning-vision-15B, a compact open-weight multimodal reasoning model, and share the motivations, design choices, experiments, and learnings that informed its development. Our goal is to contribute practical insight to the research community on building...
BeamPERL: Parameter-Efficient RL with Verifiable Rewards Specializes Compact LLMs for Structured Beam Mechanics Reasoning
arXiv:2603.04124v1 Announce Type: new Abstract: Can reinforcement learning with hard, verifiable rewards teach a compact language model to reason about physics, or does it primarily learn to pattern-match toward correct answers? We study this question by training a 1.5B-parameter reasoning...
Towards Realistic Personalization: Evaluating Long-Horizon Preference Following in Personalized User-LLM Interactions
arXiv:2603.04191v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly serving as personal assistants, where users share complex and diverse preferences over extended interactions. However, assessing how well LLMs can follow these preferences in realistic, long-term situations remains underexplored....
$\tau$-Knowledge: Evaluating Conversational Agents over Unstructured Knowledge
arXiv:2603.04370v1 Announce Type: new Abstract: Conversational agents are increasingly deployed in knowledge-intensive settings, where correct behavior depends on retrieving and applying domain-specific knowledge from large, proprietary, and unstructured corpora during live interactions with users. Yet most existing benchmarks evaluate retrieval...
Capability Thresholds and Manufacturing Topology: How Embodied Intelligence Triggers Phase Transitions in Economic Geography
arXiv:2603.04457v1 Announce Type: new Abstract: The fundamental topology of manufacturing has not undergone a paradigm-level transformation since Henry Ford's moving assembly line in 1913. Every major innovation of the past century, from the Toyota Production System to Industry 4.0, has...
Progressive Refinement Regulation for Accelerating Diffusion Language Model Decoding
arXiv:2603.04514v1 Announce Type: new Abstract: Diffusion language models generate text through iterative denoising under a uniform refinement rule applied to all tokens. However, tokens stabilize at different rates in practice, leading to substantial redundant refinement and motivating refinement control over...
Adaptive Memory Admission Control for LLM Agents
arXiv:2603.04549v1 Announce Type: new Abstract: LLM-based agents increasingly rely on long-term memory to support multi-session reasoning and interaction, yet current systems provide little control over what information is retained. In practice, agents either accumulate large volumes of conversational content, including...
Self-Attribution Bias: When AI Monitors Go Easy on Themselves
arXiv:2603.04582v1 Announce Type: new Abstract: Agentic systems increasingly rely on language models to monitor their own behavior. For example, coding agents may self critique generated code for pull request approval or assess the safety of tool-use actions. We show that...
When Agents Persuade: Propaganda Generation and Mitigation in LLMs
arXiv:2603.04636v1 Announce Type: new Abstract: Despite their wide-ranging benefits, LLM-based agents deployed in open environments can be exploited to produce manipulative material. In this study, we task LLMs with propaganda objectives and analyze their outputs using two domain-specific models: one...
Memory as Ontology: A Constitutional Memory Architecture for Persistent Digital Citizens
arXiv:2603.04740v1 Announce Type: new Abstract: Current research and product development in AI agent memory systems almost universally treat memory as a functional module -- a technical problem of "how to store" and "how to retrieve." This paper poses a fundamental...
Breaking Contextual Inertia: Reinforcement Learning with Single-Turn Anchors for Stable Multi-Turn Interaction
arXiv:2603.04783v1 Announce Type: new Abstract: While LLMs demonstrate strong reasoning capabilities when provided with full information in a single turn, they exhibit substantial vulnerability in multi-turn interactions. Specifically, when information is revealed incrementally or requires updates, models frequently fail to...
Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling
arXiv:2603.04791v1 Announce Type: new Abstract: We introduce Timer-S1, a strong Mixture-of-Experts (MoE) time series foundation model with 8.3B total parameters, 0.75B activated parameters for each token, and a context length of 11.5K. To overcome the scalability bottleneck in existing pre-trained...