Context Cartography: Toward Structured Governance of Contextual Space in Large Language Model Systems
arXiv:2603.20578v1 Announce Type: new Abstract: The prevailing approach to improving large language model (LLM) reasoning has centered on expanding context windows, implicitly assuming that more tokens yield better performance. However, empirical evidence - including the "lost in the middle" effect...
Knowledge Boundary Discovery for Large Language Models
arXiv:2603.21022v1 Announce Type: new Abstract: We propose Knowledge Boundary Discovery (KBD), a reinforcement learning based framework to explore the knowledge boundaries of the Large Language Models (LLMs). We define the knowledge boundary by automatically generating two types of questions: (i)...
Children's Intelligence Tests Pose Challenges for MLLMs? KidGym: A 2D Grid-Based Reasoning Benchmark for MLLMs
arXiv:2603.20209v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) combine the linguistic strengths of LLMs with the ability to process multimodal data, enbaling them to address a broader range of visual tasks. Because MLLMs aim at more general, human-like...
SciNav: A General Agent Framework for Scientific Coding Tasks
arXiv:2603.20256v1 Announce Type: new Abstract: Autonomous science agents built on large language models (LLMs) are increasingly used to generate hypotheses, design experiments, and produce reports. However, prior work mainly targets open-ended scientific problems with subjective outputs that are difficult to...
The production of meaning in the processing of natural language
arXiv:2603.20381v1 Announce Type: new Abstract: Understanding the fundamental mechanisms governing the production of meaning in the processing of natural language is critical for designing safe, thoughtful, engaging, and empowering human-agent interactions. Experiments in cognitive science and social psychology have demonstrated...
Coding Agents are Effective Long-Context Processors
arXiv:2603.20432v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable progress in scaling to access massive contexts. However, the access is via the latent and uninterpretable attention mechanisms, and LLMs fail to effective process long context, exhibiting significant...
JUBAKU: An Adversarial Benchmark for Exposing Culturally Grounded Stereotypes in Japanese LLMs
arXiv:2603.20581v1 Announce Type: new Abstract: Social biases reflected in language are inherently shaped by cultural norms, which vary significantly across regions and lead to diverse manifestations of stereotypes. Existing evaluations of social bias in large language models (LLMs) for non-English...
Hear Both Sides: Efficient Multi-Agent Debate via Diversity-Aware Message Retention
arXiv:2603.20640v1 Announce Type: new Abstract: Multi-Agent Debate has emerged as a promising framework for improving the reasoning quality of large language models through iterative inter-agent communication. However, broadcasting all agent messages at every round introduces noise and redundancy that can...
Weber's Law in Transformer Magnitude Representations: Efficient Coding, Representational Geometry, and Psychophysical Laws in Language Models
arXiv:2603.20642v1 Announce Type: new Abstract: How do transformer language models represent magnitude? Recent work disagrees: some find logarithmic spacing, others linear encoding, others per-digit circular representations. We apply the formal tools of psychophysics to resolve this. Using four converging paradigms...
Can I guess where you are from? Modeling dialectal morphosyntactic similarities in Brazilian Portuguese
arXiv:2603.20695v1 Announce Type: new Abstract: This paper investigates morphosyntactic covariation in Brazilian Portuguese (BP) to assess whether dialectal origin can be inferred from the combined behavior of linguistic variables. Focusing on four grammatical phenomena related to pronouns, correlation and clustering...
Reasoning Topology Matters: Network-of-Thought for Complex Reasoning Tasks
arXiv:2603.20730v1 Announce Type: new Abstract: Existing prompting paradigms structure LLM reasoning in limited topologies: Chain-of-Thought (CoT) produces linear traces, while Tree-of-Thought (ToT) performs branching search. Yet complex reasoning often requires merging intermediate results, revisiting hypotheses, and integrating evidence from multiple...
MzansiText and MzansiLM: An Open Corpus and Decoder-Only Language Model for South African Languages
arXiv:2603.20732v1 Announce Type: new Abstract: Decoder-only language models can be adapted to diverse tasks through instruction finetuning, but the extent to which this generalizes at small scale for low-resource languages remains unclear. We focus on the languages of South Africa,...
Code-MIE: A Code-style Model for Multimodal Information Extraction with Scene Graph and Entity Attribute Knowledge Enhancement
arXiv:2603.20781v1 Announce Type: new Abstract: With the rapid development of large language models (LLMs), more and more researchers have paid attention to information extraction based on LLMs. However, there are still some spaces to improve in the existing related methods....
The Anatomy of an Edit: Mechanism-Guided Activation Steering for Knowledge Editing
arXiv:2603.20795v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as knowledge bases, but keeping them up to date requires targeted knowledge editing (KE). However, it remains unclear how edits are implemented inside the model once applied. In...
RLVR Training of LLMs Does Not Improve Thinking Ability for General QA: Evaluation Method and a Simple Solution
arXiv:2603.20799v1 Announce Type: new Abstract: Reinforcement learning from verifiable rewards (RLVR) stimulates the thinking processes of large language models (LLMs), substantially enhancing their reasoning abilities on verifiable tasks. It is often assumed that similar gains should transfer to general question...
BenchBench: Benchmarking Automated Benchmark Generation
arXiv:2603.20807v1 Announce Type: new Abstract: Benchmarks are the de facto standard for tracking progress in large language models (LLMs), yet static test sets can rapidly saturate, become vulnerable to contamination, and are costly to refresh. Scalable evaluation of open-ended items...
Can ChatGPT Really Understand Modern Chinese Poetry?
arXiv:2603.20851v1 Announce Type: new Abstract: ChatGPT has demonstrated remarkable capabilities on both poetry generation and translation, yet its ability to truly understand poetry remains unexplored. Previous poetry-related work merely analyzed experimental outcomes without addressing fundamental issues of comprehension. This paper...
NoveltyAgent: Autonomous Novelty Reporting Agent with Point-wise Novelty Analysis and Self-Validation
arXiv:2603.20884v1 Announce Type: new Abstract: The exponential growth of academic publications has led to a surge in papers of varying quality, increasing the cost of paper screening. Current approaches either use novelty assessment within general AI Reviewers or repurpose DeepResearch,...
User Preference Modeling for Conversational LLM Agents: Weak Rewards from Retrieval-Augmented Interaction
arXiv:2603.20939v1 Announce Type: new Abstract: Large language models are increasingly used as personal assistants, yet most lack a persistent user model, forcing users to repeatedly restate preferences across sessions. We propose Vector-Adapted Retrieval Scoring (VARS), a pipeline-agnostic, frozen-backbone framework that...
Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models
arXiv:2603.20957v1 Announce Type: new Abstract: Frontier LLM companies have repeatedly assured courts and regulators that their models do not store copies of training data. They further rely on safety alignment strategies via RLHF, system prompts, and output filters to block...
DiscoUQ: Structured Disagreement Analysis for Uncertainty Quantification in LLM Agent Ensembles
arXiv:2603.20975v1 Announce Type: new Abstract: Multi-agent LLM systems, where multiple prompted instances of a language model independently answer questions, are increasingly used for complex reasoning tasks. However, existing methods for quantifying the uncertainty of their collective outputs rely on shallow...
Reading Between the Lines: How Electronic Nonverbal Cues shape Emotion Decoding
arXiv:2603.21038v1 Announce Type: new Abstract: As text-based computer-mediated communication (CMC) increasingly structures everyday interaction, a central question re-emerges with new urgency: How do users reconstruct nonverbal expression in environments where embodied cues are absent? This paper provides a systematic, theory-driven...
MARLIN: Multi-Agent Reinforcement Learning for Incremental DAG Discovery
arXiv:2603.20295v1 Announce Type: new Abstract: Uncovering causal structures from observational data is crucial for understanding complex systems and making informed decisions. While reinforcement learning (RL) has shown promise in identifying these structures in the form of a directed acyclic graph...
Collaborative Adaptive Curriculum for Progressive Knowledge Distillation
arXiv:2603.20296v1 Announce Type: new Abstract: Recent advances in collaborative knowledge distillation have demonstrated cutting-edge performance for resource-constrained distributed multimedia learning scenarios. However, achieving such competitiveness requires addressing a fundamental mismatch: high-dimensional teacher knowledge complexity versus heterogeneous client learning capacities, which...
Rolling-Origin Validation Reverses Model Rankings in Multi-Step PM10 Forecasting: XGBoost, SARIMA, and Persistence
arXiv:2603.20315v1 Announce Type: new Abstract: (a) Many air quality forecasting studies report gains from machine learning, but evaluations often use static chronological splits and omit persistence baselines, so the operational added value under routine updating is unclear. (b) Using 2,350...
Probing the Latent World: Emergent Discrete Symbols and Physical Structure in Latent Representations
arXiv:2603.20327v1 Announce Type: new Abstract: Video world models trained with Joint Embedding Predictive Architectures (JEPA) acquire rich spatiotemporal representations by predicting masked regions in latent space rather than reconstructing pixels. This removes the visual verification pathway of generative models, creating...
Bounded Coupled AI Learning Dynamics in Tri-Hierarchical Drone Swarms
arXiv:2603.20333v1 Announce Type: new Abstract: Modern autonomous multi-agent systems combine heterogeneous learning mechanisms operating at different timescales. An open question remains: can one formally guarantee that coupled dynamics of such mechanisms stay within the admissible operational regime? This paper studies...
Hybrid Autoencoder-Isolation Forest approach for time series anomaly detection in C70XP cyclotron operation data at ARRONAX
arXiv:2603.20335v1 Announce Type: new Abstract: The Interest Public Group ARRONAX's C70XP cyclotron, used for radioisotope production for medical and research applications, relies on complex and costly systems that are prone to failures, leading to operational disruptions. In this context, this...
Graph-Aware Text-Only Backdoor Poisoning for Text-Attributed Graphs
arXiv:2603.20339v1 Announce Type: new Abstract: Many learning systems now use graph data in which each node also contains text, such as papers with abstracts or users with posts. Because these texts often come from open platforms, an attacker may be...
Interpretable Multiple Myeloma Prognosis with Observational Medical Outcomes Partnership Data
arXiv:2603.20341v1 Announce Type: new Abstract: Machine learning (ML) promises better clinical decision-making, yet opaque model behavior limits the adoption in healthcare. We propose two novel regularization techniques for ensuring the interpretability of ML models trained on real-world data. In particular,...