Demonstrations, CoT, and Prompting: A Theoretical Analysis of ICL
arXiv:2603.19611v1 Announce Type: new Abstract: In-Context Learning (ICL) enables pretrained LLMs to adapt to downstream tasks by conditioning on a small set of input-output demonstrations, without any parameter updates. Although there have been many theoretical efforts to explain how ICL...
Continual Learning for Food Category Classification Dataset: Enhancing Model Adaptability and Performance
arXiv:2603.19624v1 Announce Type: new Abstract: Conventional machine learning pipelines often struggle to recognize categories absent from the original trainingset. This gap typically reduces accuracy, as fixed datasets rarely capture the full diversity of a domain. To address this, we propose...
GoAgent: Group-of-Agents Communication Topology Generation for LLM-based Multi-Agent Systems
arXiv:2603.19677v1 Announce Type: new Abstract: Large language model (LLM)-based multi-agent systems (MAS) have demonstrated exceptional capabilities in solving complex tasks, yet their effectiveness depends heavily on the underlying communication topology that coordinates agent interactions. Within these systems, successful problem-solving often...
Elon Musk unveils chip manufacturing plans for SpaceX and Tesla
Elon Musk recently outlined ambitious plans for a chip-building collaboration Tesla and SpaceX — but he has a history of overpromising.
LGESynthNet: Controlled Scar Synthesis for Improved Scar Segmentation in Cardiac LGE-MRI Imaging
arXiv:2603.18356v1 Announce Type: new Abstract: Segmentation of enhancement in LGE cardiac MRI is critical for diagnosing various ischemic and non-ischemic cardiomyopathies. However, creating pixel-level annotations for these images is challenging and labor-intensive, leading to limited availability of annotated data. Generative...
An Onto-Relational-Sophic Framework for Governing Synthetic Minds
arXiv:2603.18633v1 Announce Type: new Abstract: The rapid evolution of artificial intelligence, from task-specific systems to foundation models exhibiting broad, flexible competence across reasoning, creative synthesis, and social interaction, has outpaced the conceptual and governance frameworks designed to manage it. Current...
Thinking with Constructions: A Benchmark and Policy Optimization for Visual-Text Interleaved Geometric Reasoning
arXiv:2603.18662v1 Announce Type: new Abstract: Geometric reasoning inherently requires "thinking with constructions" -- the dynamic manipulation of visual aids to bridge the gap between problem conditions and solutions. However, existing Multimodal Large Language Models (MLLMs) are largely confined to passive...
Correlation-Weighted Multi-Reward Optimization for Compositional Generation
arXiv:2603.18528v1 Announce Type: new Abstract: Text-to-image models produce images that align well with natural language prompts, but compositional generation has long been a central challenge. Models often struggle to satisfy multiple concepts within a single prompt, frequently omitting some concepts...
Expert Personas Improve LLM Alignment but Damage Accuracy: Bootstrapping Intent-Based Persona Routing with PRISM
arXiv:2603.18507v1 Announce Type: new Abstract: Persona prompting can steer LLM generation towards a domain-specific tone and pattern. This behavior enables use cases in multi-agent systems where diverse interactions are crucial and human-centered tasks require high-level human alignment. Prior works provide...
Do Large Language Models Possess a Theory of Mind? A Comparative Evaluation Using the Strange Stories Paradigm
arXiv:2603.18007v1 Announce Type: new Abstract: The study explores whether current Large Language Models (LLMs) exhibit Theory of Mind (ToM) capabilities -- specifically, the ability to infer others' beliefs, intentions, and emotions from text. Given that LLMs are trained on language...
How Confident Is the First Token? An Uncertainty-Calibrated Prompt Optimization Framework for Large Language Model Classification and Understanding
arXiv:2603.18009v1 Announce Type: new Abstract: With the widespread adoption of large language models (LLMs) in natural language processing, prompt engineering and retrieval-augmented generation (RAG) have become mainstream to enhance LLMs' performance on complex tasks. However, LLMs generate outputs autoregressively, leading...
D-Mem: A Dual-Process Memory System for LLM Agents
arXiv:2603.18631v1 Announce Type: new Abstract: Driven by the development of persistent, self-adapting autonomous agents, equipping these systems with high-fidelity memory access for long-horizon reasoning has emerged as a critical requirement. However, prevalent retrieval-based memory frameworks often follow an incremental processing...
TARo: Token-level Adaptive Routing for LLM Test-time Alignment
arXiv:2603.18411v1 Announce Type: new Abstract: Large language models (LLMs) exhibit strong reasoning capabilities but typically require expensive post-training to reach high performance. Recent test-time alignment methods offer a lightweight alternative, but have been explored mainly for preference alignment rather than...
Multimodal Task Interference: A Benchmark and Analysis of History-Target Mismatch in Multimodal LLMs
arXiv:2603.18425v1 Announce Type: new Abstract: Task interference, the performance degradation caused by task switches within a single conversation, has been studied exclusively in text-only settings despite the growing prevalence of multimodal dialogue systems. We introduce a benchmark for evaluating this...
UT-ACA: Uncertainty-Triggered Adaptive Context Allocation for Long-Context Inference
arXiv:2603.18446v1 Announce Type: new Abstract: Long-context inference remains challenging for large language models due to attention dilution and out-of-distribution degradation. Context selection mitigates this limitation by attending to a subset of key-value cache entries, yet most methods allocate a fixed...
GAIN: A Benchmark for Goal-Aligned Decision-Making of Large Language Models under Imperfect Norms
arXiv:2603.18469v1 Announce Type: new Abstract: We introduce GAIN (Goal-Aligned Decision-Making under Imperfect Norms), a benchmark designed to evaluate how large language models (LLMs) balance adherence to norms against business goals. Existing benchmarks typically focus on abstract scenarios rather than real-world...
EntropyCache: Decoded Token Entropy Guided KV Caching for Diffusion Language Models
arXiv:2603.18489v1 Announce Type: new Abstract: Diffusion-based large language models (dLLMs) rely on bidirectional attention, which prevents lossless KV caching and requires a full forward pass at every denoising step. Existing approximate KV caching methods reduce this cost by selectively updating...
Cross-Lingual LLM-Judge Transfer via Evaluation Decomposition
arXiv:2603.18557v1 Announce Type: new Abstract: As large language models are increasingly deployed across diverse real-world applications, extending automated evaluation beyond English has become a critical challenge. Existing evaluation approaches are predominantly English-focused, and adapting them to other languages is hindered...
Cross-Modal Rationale Transfer for Explainable Humanitarian Classification on Social Media
arXiv:2603.18611v1 Announce Type: new Abstract: Advances in social media data dissemination enable the provision of real-time information during a crisis. The information comes from different classes, such as infrastructure damages, persons missing or stranded in the affected zone, etc. Existing...
Why Better Cross-Lingual Alignment Fails for Better Cross-Lingual Transfer: Case of Encoders
arXiv:2603.18863v1 Announce Type: new Abstract: Better cross-lingual alignment is often assumed to yield better cross-lingual transfer. However, explicit alignment techniques -- despite increasing embedding similarity -- frequently fail to improve token-level downstream performance. In this work, we show that this...
Evaluating LLM-Generated Lessons from the Language Learning Students' Perspective: A Short Case Study on Duolingo
arXiv:2603.18873v1 Announce Type: new Abstract: Popular language learning applications such as Duolingo use large language models (LLMs) to generate lessons for its users. Most lessons focus on general real-world scenarios such as greetings, ordering food, or asking directions, with limited...
Towards Differentiating Between Failures and Domain Shifts in Industrial Data Streams
arXiv:2603.18032v1 Announce Type: new Abstract: Anomaly and failure detection methods are crucial in identifying deviations from normal system operational conditions, which allows for actions to be taken in advance, usually preventing more serious damages. Long-lasting deviations indicate failures, while sudden,...
Adapting Methods for Domain-Specific Japanese Small LMs: Scale, Architecture, and Quantization
arXiv:2603.18037v1 Announce Type: new Abstract: This paper presents a systematic methodology for building domain-specific Japanese small language models using QLoRA fine-tuning. We address three core questions: optimal training scale, base-model selection, and architecture-aware quantization. Stage 1 (Training scale): Scale-learning experiments...
Enhancing Reinforcement Learning Fine-Tuning with an Online Refiner
arXiv:2603.18088v1 Announce Type: new Abstract: Constraints are essential for stabilizing reinforcement learning fine-tuning (RFT) and preventing degenerate outputs, yet they inherently conflict with the optimization objective because stronger constraints limit the ability of a fine-tuned model to discover better solutions....
AGRI-Fidelity: Evaluating the Reliability of Listenable Explanations for Poultry Disease Detection
arXiv:2603.18247v1 Announce Type: new Abstract: Existing XAI metrics measure faithfulness for a single model, ignoring model multiplicity where near-optimal classifiers rely on different or spurious acoustic cues. In noisy farm environments, stationary artifacts such as ventilation noise can produce explanations...
Learning to Reason with Curriculum I: Provable Benefits of Autocurriculum
arXiv:2603.18325v1 Announce Type: new Abstract: Chain-of-thought reasoning, where language models expend additional computation by producing thinking tokens prior to final responses, has driven significant advances in model capabilities. However, training these reasoning models is extremely costly in terms of both...
Escaping Offline Pessimism: Vector-Field Reward Shaping for Safe Frontier Exploration
arXiv:2603.18326v1 Announce Type: new Abstract: While offline reinforcement learning provides reliable policies for real-world deployment, its inherent pessimism severely restricts an agent's ability to explore and collect novel data online. Drawing inspiration from safe reinforcement learning, exploring near the boundary...
Multi-Agent Reinforcement Learning for Dynamic Pricing: Balancing Profitability,Stability and Fairness
arXiv:2603.16888v1 Announce Type: new Abstract: Dynamic pricing in competitive retail markets requires strategies that adapt to fluctuating demand and competitor behavior. In this work, we present a systematic empirical evaluation of multi-agent reinforcement learning (MARL) approaches-specifically MAPPO and MADDPG-for dynamic...
MHPO: Modulated Hazard-aware Policy Optimization for Stable Reinforcement Learning
arXiv:2603.16929v1 Announce Type: new Abstract: Regulating the importance ratio is critical for the training stability of Group Relative Policy Optimization (GRPO) based frameworks. However, prevailing ratio control methods, such as hard clipping, suffer from non-differentiable boundaries and vanishing gradient regions,...