arXiv:2603.20034v1 Announce Type: cross Abstract: We wish to measure the information coverage of an ad hoc retrieval algorithm, that is, how much of the range of available relevant information is covered by the search results. Information coverage is a central aspect for retrieval, especially when the retrieval system is integrated with generative models in a […]
On the Ability of Transformers to Verify Plans
arXiv:2603.19954v1 Announce Type: new Abstract: Transformers have shown inconsistent success in AI planning tasks, and theoretical understanding of when generalization should be expected has been limited. We take important steps towards addressing this gap by analyzing the ability of decoder-only models to verify whether a given plan correctly solves a given planning instance. To analyse […]
POET: Power-Oriented Evolutionary Tuning for LLM-Based RTL PPA Optimization
arXiv:2603.19333v1 Announce Type: cross Abstract: Applying large language models (LLMs) to RTL code optimization for improved power, performance, and area (PPA) faces two key challenges: ensuring functional correctness of optimized designs despite LLM hallucination, and systematically prioritizing power reduction within the multi-objective PPA trade-off space. We propose POET (Power-Oriented Evolutionary Tuning), a framework that addresses […]
The $mathbfY$-Combinator for LLMs: Solving Long-Context Rot with $lambda$-Calculus
arXiv:2603.20105v1 Announce Type: cross Abstract: LLMs are increasingly used as general-purpose reasoners, but long inputs remain bottlenecked by a fixed context window. Recursive Language Models (RLMs) address this by externalising the prompt and recursively solving subproblems. Yet existing RLMs depend on an open-ended read-eval-print loop (REPL) in which the model generates arbitrary control code, making […]
Diffusion-Guided Semantic Consistency for Multimodal Heterogeneity
arXiv:2603.19337v1 Announce Type: cross Abstract: Federated learning (FL) is severely challenged by non-independent and identically distributed (non-IID) client data, a problem that degrades global model performance, especially in multimodal perception settings. Conventional methods often fail to address the underlying semantic discrepancies between clients, leading to suboptimal performance for multimedia systems requiring robust perception. To overcome […]
Experience is the Best Teacher: Motivating Effective Exploration in Reinforcement Learning for LLMs
arXiv:2603.20046v1 Announce Type: new Abstract: Reinforcement Learning (RL) with rubric-based rewards has recently shown remarkable progress in enhancing general reasoning capabilities of Large Language Models (LLMs), yet still suffers from ineffective exploration confined to curent policy distribution. In fact, RL optimization can be viewed as steering the policy toward an ideal distribution that maximizes the […]
Beyond Weighted Summation: Learnable Nonlinear Aggregation Functions for Robust Artificial Neurons
arXiv:2603.19344v1 Announce Type: cross Abstract: Weighted summation has remained the default input aggregation mechanism in artificial neurons since the earliest neural network models. While computationally efficient, this design implicitly behaves like a mean-based estimator and is therefore sensitive to noisy or extreme inputs. This paper investigates whether replacing fixed linear aggregation with learnable nonlinear alternatives […]
Design-OS: A Specification-Driven Framework for Engineering System Design with a Control-Systems Design Case
arXiv:2603.20151v1 Announce Type: cross Abstract: Engineering system design — whether mechatronic, control, or embedded — often proceeds in an ad hoc manner, with requirements left implicit and traceability from intent to parameters largely absent. Existing specification-driven and systematic design methods mostly target software, and AI-assisted tools tend to enter the workflow at solution generation rather […]
DIAL-KG: Schema-Free Incremental Knowledge Graph Construction via Dynamic Schema Induction and Evolution-Intent Assessment
arXiv:2603.20059v1 Announce Type: new Abstract: Knowledge Graphs (KGs) are foundational to applications such as search, question answering, and recommendation. Conventional knowledge graph construction methods are predominantly static, rely ing on a single-step construction from a fixed corpus with a prede f ined schema. However, such methods are suboptimal for real-world sce narios where data arrives […]
The Autonomy Tax: Defense Training Breaks LLM Agents
arXiv:2603.19423v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks. Practitioners deploy defense-trained models to protect against prompt injection attacks that manipulate agent behavior through malicious observations or retrieved content. We reveal a fundamental textbfcapability-alignment paradox: defense training […]
LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation
arXiv:2603.20192v1 Announce Type: cross Abstract: Recent advances in diffusion models have significantly improved text-to-video generation, enabling personalized content creation with fine-grained control over both foreground and background elements. However, precise face-attribute alignment across subjects remains challenging, as existing methods lack explicit mechanisms to ensure intra-group consistency. Addressing this gap requires both explicit modeling strategies and […]
Vocabulary shapes cross-lingual variation of word-order learnability in language models
arXiv:2603.19427v1 Announce Type: cross Abstract: Why do some languages like Czech permit free word order, while others like English do not? We address this question by pretraining transformer language models on a spectrum of synthetic word-order variants of natural languages. We observe that greater word-order irregularity consistently raises model surprisal, indicating reduced learnability. Sentence reversal, […]