When Do Hallucinations Arise? A Graph Perspective on the Evolution of Path Reuse and Path Compression
arXiv:2604.03557v1 Announce Type: new Abstract: Reasoning hallucinations in large language models (LLMs) often appear as fluent yet unsupported conclusions that violate either the given context or underlying factual knowledge. Although such failures are widely observed, the mechanisms by which decoder-only...
ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation
arXiv:2604.03922v1 Announce Type: new Abstract: Selecting LLM-generated code candidates using LLM-generated tests is challenging because the tests themselves may be incorrect. Existing methods either treat all tests equally or rely on ad-hoc heuristics to filter unreliable tests. Yet determining test...
AI Appeals Processor: A Deep Learning Approach to Automated Classification of Citizen Appeals in Government Services
arXiv:2604.03672v1 Announce Type: new Abstract: Government agencies worldwide face growing volumes of citizen appeals, with electronic submissions increasing significantly over recent years. Traditional manual processing averages 20 minutes per appeal with only 67% classification accuracy, creating significant bottlenecks in public...
Comparative reversal learning reveals rigid adaptation in LLMs under non-stationary uncertainty
arXiv:2604.04182v1 Announce Type: new Abstract: Non-stationary environments require agents to revise previously learned action values when contingencies change. We treat large language models (LLMs) as sequential decision policies in a two-option probabilistic reversal-learning task with three latent states and switch...
PRAISE: Prefix-Based Rollout Reuse in Agentic Search Training
arXiv:2604.03675v1 Announce Type: new Abstract: In agentic search, large language models (LLMs) are trained to perform multi-turn retrieval and reasoning for complex tasks such as multi-hop question answering (QA). However, current search-based Reinforcement Learning (RL) methods suffer from two core...
Predict, Don't React: Value-Based Safety Forecasting for LLM Streaming
arXiv:2604.03962v1 Announce Type: new Abstract: In many practical LLM deployments, a single guardrail is used for both prompt and response moderation. Prompt moderation operates on fully observed text, whereas streaming response moderation requires safety decisions to be made over partial...
I-CALM: Incentivizing Confidence-Aware Abstention for LLM Hallucination Mitigation
arXiv:2604.03904v1 Announce Type: new Abstract: Large language models (LLMs) frequently produce confident but incorrect answers, partly because common binary scoring conventions reward answering over honestly expressing uncertainty. We study whether prompt-only interventions -- explicitly announcing reward schemes for answer-versus-abstain decisions...
Structured Multi-Criteria Evaluation of Large Language Models with Fuzzy Analytic Hierarchy Process and DualJudge
arXiv:2604.03742v1 Announce Type: new Abstract: Effective evaluation of large language models (LLMs) remains a critical bottleneck, as conventional direct scoring often yields inconsistent and opaque judgments. In this work, we adapt the Analytic Hierarchy Process (AHP) to LLM-based evaluation and,...
Single-agent vs. Multi-agents for Automated Video Analysis of On-Screen Collaborative Learning Behaviors
arXiv:2604.03631v1 Announce Type: new Abstract: On-screen learning behavior provides valuable insights into how students seek, use, and create information during learning. Analyzing on-screen behavioral engagement is essential for capturing students' cognitive and collaborative processes. The recent development of Vision Language...
From Plausible to Causal: Counterfactual Semantics for Policy Evaluation in Simulated Online Communities
arXiv:2604.03920v1 Announce Type: new Abstract: LLM-based social simulations can generate believable community interactions, enabling ``policy wind tunnels'' where governance interventions are tested before deployment. But believability is not causality. Claims like ``intervention $A$ reduces escalation'' require causal semantics that current...
Self-Execution Simulation Improves Coding Models
arXiv:2604.03253v1 Announce Type: new Abstract: A promising research direction in enabling LLMs to generate consistently correct code involves addressing their inability to properly estimate program execution, particularly for code they generate. In this work, we demonstrate that Code LLMs can...
CAWN: Continuous Acoustic Wave Networks for Autoregressive Language Modeling
arXiv:2604.04250v1 Announce Type: new Abstract: Modern Large Language Models (LLMs) rely on Transformer self-attention, which scales quadratically with sequence length. Recent linear-time alternatives, like State Space Models (SSMs), often suffer from signal degradation over extended contexts. We introduce the Continuous...
Scaling DPPs for RAG: Density Meets Diversity
arXiv:2604.03240v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by grounding generation in external knowledge, yielding relevance responses that are aligned with factual evidence and evolving corpora. Standard RAG pipelines construct context through relevance ranking, performing...
Adaptive Threshold-Driven Continuous Greedy Method for Scalable Submodular Optimization
arXiv:2604.03419v1 Announce Type: new Abstract: Submodular maximization under matroid constraints is a fundamental problem in combinatorial optimization with applications in sensing, data summarization, active learning, and resource allocation. While the Sequential Greedy (SG) algorithm achieves only a $\frac{1}{2}$-approximation due to...
LLM-Agent-based Social Simulation for Attitude Diffusion
arXiv:2604.03898v1 Announce Type: new Abstract: This paper introduces discourse_simulator, an open-source framework that combines LLMs with agent-based modelling. It offers a new way to simulate how public attitudes toward immigration change over time in response to salient events like protests,...
Product-Stability: Provable Convergence for Gradient Descent on the Edge of Stability
arXiv:2604.02653v1 Announce Type: new Abstract: Empirically, modern deep learning training often occurs at the Edge of Stability (EoS), where the sharpness of the loss exceeds the threshold below which classical convergence analysis applies. Despite recent progress, existing theoretical explanations of...
Detecting and Correcting Reference Hallucinations in Commercial LLMs and Deep Research Agents
arXiv:2604.03173v1 Announce Type: new Abstract: Large language models and deep research agents supply citation URLs to support their claims, yet the reliability of these citations has not been systematically measured. We address six research questions about citation URL validity using...
Multi-Turn Reinforcement Learning for Tool-Calling Agents with Iterative Reward Calibration
arXiv:2604.02869v1 Announce Type: new Abstract: Training tool-calling agents with reinforcement learning on multi-turn tasks remains challenging due to sparse outcome rewards and difficult credit assignment across conversation turns. We present the first application of MT-GRPO (Multi-Turn Group Relative Policy Optimization)...
Communication-Efficient Distributed Learning with Differential Privacy
arXiv:2604.02558v1 Announce Type: new Abstract: We address nonconvex learning problems over undirected networks. In particular, we focus on the challenge of designing an algorithm that is both communication-efficient and that guarantees the privacy of the agents' data. The first goal...
Reinforcement Learning-based Knowledge Distillation with LLM-as-a-Judge
arXiv:2604.02621v1 Announce Type: new Abstract: Reinforcement Learning (RL) has been shown to substantially improve the reasoning capability of small and large language models (LLMs), but existing approaches typically rely on verifiable rewards, hence ground truth labels. We propose an RL...
Single-Agent LLMs Outperform Multi-Agent Systems on Multi-Hop Reasoning Under Equal Thinking Token Budgets
arXiv:2604.02460v1 Announce Type: new Abstract: Recent work reports strong performance from multi-agent LLM systems (MAS), but these gains are often confounded by increased test-time computation. When computation is normalized, single-agent systems (SAS) can match or outperform MAS, yet the theoretical...
Pragmatics Meets Culture: Culturally-adapted Artwork Description Generation and Evaluation
arXiv:2604.02557v1 Announce Type: new Abstract: Language models are known to exhibit various forms of cultural bias in decision-making tasks, yet much less is known about their degree of cultural familiarity in open-ended text generation tasks. In this paper, we introduce...
Aligning Progress and Feasibility: A Neuro-Symbolic Dual Memory Framework for Long-Horizon LLM Agents
arXiv:2604.02734v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated strong potential in long-horizon decision-making tasks, such as embodied manipulation and web interaction. However, agents frequently struggle with endless trial-and-error loops or deviate from the main objective in complex...
An Initial Exploration of Contrastive Prompt Tuning to Generate Energy-Efficient Code
arXiv:2604.02352v1 Announce Type: cross Abstract: Although LLMs are capable of generating functionally correct code, they also tend to produce less energy-efficient code in comparison to human-written solutions. As these inefficiencies lead to higher computational overhead, they are in direct conflict...
Audio Spatially-Guided Fusion for Audio-Visual Navigation
arXiv:2604.02389v1 Announce Type: cross Abstract: Audio-visual Navigation refers to an agent utilizing visual and auditory information in complex 3D environments to accomplish target localization and path planning, thereby achieving autonomous navigation. The core challenge of this task lies in the...
Generalization Limits of Reinforcement Learning Alignment
arXiv:2604.02652v1 Announce Type: new Abstract: The safety of large language models (LLMs) relies on alignment techniques such as reinforcement learning from human feedback (RLHF). However, recent theoretical analyses suggest that reinforcement learning-based training does not acquire new capabilities but merely...
Compositional Neuro-Symbolic Reasoning
arXiv:2604.02434v1 Announce Type: new Abstract: We study structured abstraction-based reasoning for the Abstraction and Reasoning Corpus (ARC) and compare its generalization to test-time approaches. Purely neural architectures lack reliable combinatorial generalization, while strictly symbolic systems struggle with perceptual grounding. We...
Competency Questions as Executable Plans: a Controlled RAG Architecture for Cultural Heritage Storytelling
arXiv:2604.02545v1 Announce Type: new Abstract: The preservation of intangible cultural heritage is a critical challenge as collective memory fades over time. While Large Language Models (LLMs) offer a promising avenue for generating engaging narratives, their propensity for factual inaccuracies or...
Beyond Precision: Importance-Aware Recall for Factuality Evaluation in Long-Form LLM Generation
arXiv:2604.03141v1 Announce Type: new Abstract: Evaluating the factuality of long-form output generated by large language models (LLMs) remains challenging, particularly when responses are open-ended and contain many fine-grained factual statements. Existing evaluation methods primarily focus on precision: they decompose a...
Interpretable Deep Reinforcement Learning for Element-level Bridge Life-cycle Optimization
arXiv:2604.02528v1 Announce Type: new Abstract: The new Specifications for the National Bridge Inventory (SNBI), in effect from 2022, emphasize the use of element-level condition states (CS) for risk-based bridge management. Instead of a general component rating, element-level condition data use...