arXiv:2601.08057v1 Announce Type: new Abstract: The Hanano Puzzle is a one-player game with irreversible gravity, where the goal is to make colored blocks make contact with flowers of the corresponding color. The game Jelly no Puzzle shares similar mechanics. In general, determining if a given level of each of the two games is solvable is PSPACE-complete. There are also known restrictions under which determining if a level of Jelly no Puzzle is solvable is NP-complete. We find that […]

Ver mais

arXiv:2602.00879v1 Announce Type: new Abstract: Among parallel decoding paradigms, diffusion large language models (dLLMs) have emerged as a promising candidate that balances generation quality and throughput. However, their integration with Mixture-of-Experts (MoE) architectures is constrained by an expert explosion: as the number of tokens generated in parallel increases, the number of distinct experts activated grows nearly linearly. This results in substantial memory traffic that pushes inference into a memory-bound regime, negating the efficiency gains of both MoE and […]

Ver mais

TIL: Using LLM in the shebang line of a script Kim_Bruning on Hacker News: But seriously, you can put a shebang on an english text file now (if you’re sufficiently brave) […] This inspired me to look at patterns for doing exactly that with LLM. Here’s the simplest, which takes advantage of LLM fragments: #!/usr/bin/env -S llm -f Generate an SVG of a pelican riding a bicycle But you can also incorporate tool calls using the -T name_of_tool […]

Ver mais

arXiv:2601.08986v1 Announce Type: new Abstract: We study the pointwise maximal leakage (PML) envelope of the Gaussian mechanism, which characterizes the smallest information leakage bound that holds with high probability under arbitrary post-processing. For the Gaussian mechanism with a Gaussian secret, we derive a closed-form expression for the deterministic PML envelope for sufficiently small failure probabilities. We then extend this result to general unbounded secrets by identifying a sufficient condition under which the envelope coincides with the Gaussian case. […]

Ver mais

arXiv:2601.10942v1 Announce Type: new Abstract: Software is in constant evolution, with developers frequently submitting pull requests (PRs) to introduce new features or fix bugs. Testing PRs is critical to maintaining software quality. Yet, even in projects with extensive test suites, some PR-modified lines remain untested, leaving a “last-mile” regression test gap. Existing test generators typically aim to improve overall coverage, but do not specifically target the uncovered lines in PRs. We present Change And Cover (ChaCo), an LLM-based […]

Ver mais

arXiv:2601.16312v1 Announce Type: new Abstract: Research in AI4Science has shown promise in many science applications, including polymer design. However, current LLMs prove ineffective on this problem space because: (i) most models lack polymer-specific knowledge (ii) existing aligned models lack coverage of knowledge and capabilities relevant to polymer design. Addressing this, we introduce PolyBench, a large scale training and test benchmark dataset of more than 125K polymer design related tasks, leveraging a knowledge base of 13M+ data points obtained […]

Ver mais

arXiv:2603.02029v2 Announce Type: replace-cross Abstract: Moving beyond evaluations that collapse performance across heterogeneous prompts toward fine-grained evaluation at the prompt level, or within relatively homogeneous subsets, is necessary to diagnose generative models’ strengths and weaknesses. Such fine-grained evaluations, however, suffer from a data bottleneck: human gold-standard labels are too costly at this scale, while automated ratings are often misaligned with human judgment. To resolve this challenge, we propose a novel statistical model based on tensor factorization that merges […]

Ver mais

arXiv:2603.00618v1 Announce Type: new Abstract: Multi-domain graph pre-training integrates knowledge from diverse domains to enhance performance in the target domains, which is crucial for building graph foundation models. Despite initial success, existing solutions often fall short of answering a fundamental question: how is knowledge integrated or transferred across domains? This theoretical limitation motivates us to rethink the consistency and transferability between model pre-training and domain adaptation. In this paper, we propose a fresh Riemannian geometry perspective, whose core […]

Ver mais

arXiv:2602.07086v1 Announce Type: new Abstract: Enterprise systems increasingly require natural language interfaces that can translate user requests into structured operations such as SQL queries and REST API calls. While large language models (LLMs) show promise for code generation [Chen et al., 2021; Huynh and Lin, 2025], their effectiveness in domain-specific enterprise contexts remains underexplored, particularly when both retrieval and modification tasks must be handled jointly. This paper presents a comprehensive evaluation of three retrieval-augmented generation (RAG) variants [Lewis […]

Ver mais