The paper proposes a trust schema and verification framework to ensure that agent skills, which augment LLMs, are rigorously verified before deployment, thereby making human-in-the-loop oversight scal…

This paper investigates the prevalence and impact of relation chains in software review workflows using data from Gerrit, finding that they increase merge times and review effort propagation.

MEMENTO proposes a novel framework that treats the open web as a continuous learning signal, enabling agents to acquire task-specific expertise and reusable research strategies in low-data domains wit…

The paper proposes a two-stage filter-then-verify framework combining GNNs and ModernBERT to accurately detect complex social engineering attacks in email networks by analyzing both structural pattern…

The paper analyzes a fragment of Higher-Order Datalog, showing that restricting recursion to a linear form shifts its expressive power from time complexity to space complexity, specifically capturing…

The paper quantitatively confirms the Currier A/B language distinction in the Voynich Manuscript, demonstrating it is governed by a higher-dimensional, context-dependent boolean switch rather than a s…

GrepSeek introduces a novel direct corpus interaction (DCI) search agent that trains an LLM to find and compose evidence from large text corpora by issuing executable shell commands, achieving state-o…

The paper establishes bijections between tree records, girth of connected endofunctions, and genesis sequences, deriving generating functions for tree and forest record numbers using Cayley's tree fun…

The paper introduces STORYLENSWRITER, a novel framework that significantly improves personalized story rewriting by incorporating context-aware narrative enrichment, outperforming style-only adaptatio…

This paper unifies the fragmented field of Tree-of-Thoughts (ToT) reasoning by mapping LLM-based search processes onto a formal taxonomy derived from classical heuristic search theory.

The paper demonstrates that LLMs generate correlated, non-existent character ensembles (ghost couples) whose co-occurrence rates are highly predictable and model-specific, leading to the creation of f…

The paper proposes CheckRLM, a framework that improves the reliability of Reasoning Language Models by identifying and correcting factual errors using Retrieval-Augmented Generation.

This paper demonstrates that targeted adaptation of the small language model Phi Silica, using dataset curation and fine-tuning, significantly improves its performance in short-form text rewriting, na…

This paper proposes a framework for multi-hop retrieval as query-set compatibility scoring, improving retrieval performance and downstream QA task performance.

The paper proposes RIEQE, a two-stage training framework that synergistically co-evolves implicit and explicit reasoning capabilities in Large Reasoning Models (LRMs) to significantly improve fine-gra…

The paper argues that current search agents often verify existing knowledge rather than genuinely searching, and introduces LiveBrowseComp, a new benchmark to measure true evidence-driven discovery.

The paper introduces MAVEN, a lightweight symbolic reasoning scaffold that significantly improves the generalization and end-to-end success rate of large language models in complex, multi-step tool-ca…