Context Shapes LLMs Retrieval-Augmented Fact-Checking Effectiveness
arXiv:2602.14044v1 Announce Type: new Abstract: Large language models (LLMs) show strong reasoning abilities across diverse tasks, yet their performance on extended contexts remains inconsistent. While prior research has emphasized mid-context degradation in question answering, this study examines the impact of...
Mind the (DH) Gap! A Contrast in Risky Choices Between Reasoning and Conversational LLMs
arXiv:2602.15173v1 Announce Type: new Abstract: The use of large language models either as decision support systems, or in agentic workflows, is rapidly transforming the digital ecosystem. However, the understanding of LLM decision-making under uncertainty remains limited. We initiate a comparative...
IRPAPERS: A Visual Document Benchmark for Scientific Retrieval and Question Answering
arXiv:2602.17687v1 Announce Type: cross Abstract: AI systems have achieved remarkable success in processing text and relational data, yet visual document processing remains relatively underexplored. Whereas traditional systems require OCR transcriptions to convert these visual documents into text and metadata, recent...
A Case Study of Selected PTQ Baselines for Reasoning LLMs on Ascend NPU
arXiv:2602.17693v1 Announce Type: cross Abstract: Post-Training Quantization (PTQ) is crucial for efficient model deployment, yet its effectiveness on Ascend NPU remains under-explored compared to GPU architectures. This paper presents a case study of representative PTQ baselines applied to reasoning-oriented models...
Can LLM Safety Be Ensured by Constraining Parameter Regions?
arXiv:2602.17696v1 Announce Type: cross Abstract: Large language models (LLMs) are often assumed to contain ``safety regions'' -- parameter subsets whose modification directly influences safety behaviors. We conduct a systematic evaluation of four safety region identification methods spanning different parameter granularities,...
TPRU: Advancing Temporal and Procedural Understanding in Large Multimodal Models
arXiv:2602.18884v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs), particularly smaller, deployable variants, exhibit a critical deficiency in understanding temporal and procedural visual data, a bottleneck hindering their application in real-world embodied AI. This gap is largely caused by...
How Far Can We Go with Pixels Alone? A Pilot Study on Screen-Only Navigation in Commercial 3D ARPGs
arXiv:2602.18981v1 Announce Type: new Abstract: Modern 3D game levels rely heavily on visual guidance, yet the navigability of level layouts remains difficult to quantify. Prior work either simulates play in simplified environments or analyzes static screenshots for visual affordances, but...
Robust Exploration in Directed Controller Synthesis via Reinforcement Learning with Soft Mixture-of-Experts
arXiv:2602.19244v1 Announce Type: new Abstract: On-the-fly Directed Controller Synthesis (OTF-DCS) mitigates state-space explosion by incrementally exploring the system and relies critically on an exploration policy to guide search efficiently. Recent reinforcement learning (RL) approaches learn such policies and achieve promising...
Time Series, Vision, and Language: Exploring the Limits of Alignment in Contrastive Representation Spaces
arXiv:2602.19367v1 Announce Type: new Abstract: The Platonic Representation Hypothesis posits that learned representations from models trained on different modalities converge to a shared latent structure of the world. However, this hypothesis has largely been examined in vision and language, and...
The Million-Label NER: Breaking Scale Barriers with GLiNER bi-encoder
arXiv:2602.18487v1 Announce Type: new Abstract: This paper introduces GLiNER-bi-Encoder, a novel architecture for Named Entity Recognition (NER) that harmonizes zero-shot flexibility with industrial-scale efficiency. While the original GLiNER framework offers strong generalization, its joint-encoding approach suffers from quadratic complexity as...
Causal Identification from Counterfactual Data: Completeness and Bounding Results
arXiv:2602.23541v1 Announce Type: new Abstract: Previous work establishing completeness results for $\textit{counterfactual identification}$ has been circumscribed to the setting where the input data belongs to observational or interventional distributions (Layers 1 and 2 of Pearl's Causal Hierarchy), since it was...
SleepLM: Natural-Language Intelligence for Human Sleep
arXiv:2602.23605v1 Announce Type: new Abstract: We present SleepLM, a family of sleep-language foundation models that enable human sleep alignment, interpretation, and interaction with natural language. Despite the critical role of sleep, learning-based sleep analysis systems operate in closed label spaces...
Pessimistic Auxiliary Policy for Offline Reinforcement Learning
arXiv:2602.23974v1 Announce Type: new Abstract: Offline reinforcement learning aims to learn an agent from pre-collected datasets, avoiding unsafe and inefficient real-time interaction. However, inevitable access to out-ofdistribution actions during the learning process introduces approximation errors, causing the error accumulation and...
Recycling Failures: Salvaging Exploration in RLVR via Fine-Grained Off-Policy Guidance
arXiv:2602.24110v1 Announce Type: new Abstract: Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a powerful paradigm for enhancing the complex reasoning capabilities of Large Reasoning Models. However, standard outcome-based supervision suffers from a critical limitation that penalizes trajectories that...
Long Range Frequency Tuning for QML
arXiv:2602.23409v1 Announce Type: cross Abstract: Quantum machine learning models using angle encoding naturally represent truncated Fourier series, providing universal function approximation capabilities with sufficient circuit depth. For unary fixed-frequency encodings, circuit depth scales as O(omega_max * (omega_max + epsilon^{-2})) with...
Human Supervision as an Information Bottleneck: A Unified Theory of Error Floors in Human-Guided Learning
arXiv:2602.23446v1 Announce Type: cross Abstract: Large language models are trained primarily on human-generated data and feedback, yet they exhibit persistent errors arising from annotation noise, subjective preferences, and the limited expressive bandwidth of natural language. We argue that these limitations...
AI Runtime Infrastructure
arXiv:2603.00495v1 Announce Type: new Abstract: We introduce AI Runtime Infrastructure, a distinct execution-time layer that operates above the model and below the application, actively observing, reasoning over, and intervening in agent behavior to optimize task success, latency, token efficiency, reliability,...
Fair in Mind, Fair in Action? A Synchronous Benchmark for Understanding and Generation in UMLLMs
arXiv:2603.00590v1 Announce Type: new Abstract: As artificial intelligence (AI) is increasingly deployed across domains, ensuring fairness has become a core challenge. However, the field faces a "Tower of Babel'' dilemma: fairness metrics abound, yet their underlying philosophical assumptions often conflict,...
Embracing Anisotropy: Turning Massive Activations into Interpretable Control Knobs for Large Language Models
arXiv:2603.00029v1 Announce Type: new Abstract: Large Language Models (LLMs) exhibit highly anisotropic internal representations, often characterized by massive activations, a phenomenon where a small subset of feature dimensions possesses magnitudes significantly larger than the rest. While prior works view these...
SimpleTool: Parallel Decoding for Real-Time LLM Function Calling
arXiv:2603.00030v1 Announce Type: new Abstract: LLM-based function calling enables intelligent agents to interact with external tools and environments, yet autoregressive decoding imposes a fundamental latency bottleneck that limits real-time applications such as embodied intelligence, game AI, and interactive avatars (e.g.,...
Engineering Reasoning and Instruction (ERI) Benchmark: A Large Taxonomy-driven Dataset for Foundation Models and Agents
arXiv:2603.02239v1 Announce Type: new Abstract: The Engineering Reasoning and Instruction (ERI) benchmark is a taxonomy-driven instruction dataset designed to train and evaluate engineering-capable large language models (LLMs) and agents. This dataset spans nine engineering fields (namely: civil, mechanical, electrical, chemical,...
SUN: Shared Use of Next-token Prediction for Efficient Multi-LLM Disaggregated Serving
arXiv:2603.02599v1 Announce Type: new Abstract: In multi-model LLM serving, decode execution remains inefficient due to model-specific resource partitioning: since cross-model batching is not possible, memory-bound decoding often suffers from severe GPU underutilization, especially under skewed workloads. We propose Shared Use...
LLMs for High-Frequency Decision-Making: Normalized Action Reward-Guided Consistency Policy Optimization
arXiv:2603.02680v1 Announce Type: new Abstract: While Large Language Models (LLMs) form the cornerstone of sequential decision-making agent development, they have inherent limitations in high-frequency decision tasks. Existing research mainly focuses on discrete embodied decision scenarios with low-frequency and significant semantic...
Characterizing Memorization in Diffusion Language Models: Generalized Extraction and Sampling Effects
arXiv:2603.02333v1 Announce Type: new Abstract: Autoregressive language models (ARMs) have been shown to memorize and occasionally reproduce training data verbatim, raising concerns about privacy and copyright liability. Diffusion language models (DLMs) have recently emerged as a competitive alternative, yet their...
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...
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},...
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...
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...
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...
SalamahBench: Toward Standardized Safety Evaluation for Arabic Language Models
arXiv:2603.04410v1 Announce Type: new Abstract: Safety alignment in Language Models (LMs) is fundamental for trustworthy AI. However, while different stakeholders are trying to leverage Arabic Language Models (ALMs), systematic safety evaluation of ALMs remains largely underexplored, limiting their mainstream uptake....