The paper introduces TRACE, a novel metric that evaluates the logical structure of LLM reasoning (CoT) by integrating Toulmin's argumentation theory, demonstrating that sound reasoning structure corre…

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 survey provides a comprehensive analysis of Reasoning Language Model (RLM) adoption across 28 scientific disciplines, revealing significant disparities in RLM maturity across different scientific…

This paper synthesizes over 150 scattered studies and reports to provide the first comprehensive primer on post-training reasoning data, organizing the field around data objects, utility, construction…

This paper introduces MIRA-Ev, a clinical argument mining benchmark in Spanish, English, and Basque with a three-tier task hierarchy for evidence sentence retrieval, argumentative component extraction…

The paper introduces Entropy-Cut Metropolis-Hastings, an efficient sampling method that uses next-token entropy to identify and resample from critical decision points in a reasoning trace, significant…

This paper introduces cost-aware Retrieval-Augmented Generation (RAG), demonstrating that fixed evidence selection is brittle and that adaptive, agentic controllers are necessary for effective knowled…

HypoAgent is an agentic framework that enables interactive, multi-turn abductive hypothesis generation over knowledge graphs, achieving state-of-the-art performance by integrating specialized agents f…

The paper evaluates LLM reasoning on Boolean satisfiability (SAT) problems, concluding that conventional metrics are misleading and proposing a paired-formula protocol with Accurate Differentiation Ra…

This paper introduces a novel framework, the Reasoning Safety Monitor, to detect and prevent logical inconsistencies and adversarial manipulations within the internal reasoning steps of large language…

The paper introduces ForeSci, a novel benchmark that evaluates LLM agents' ability to make forward-looking research judgments using only historical evidence, finding that explicit evidence organizatio…

The paper introduces Contrastive Reflection (CORE), a novel non-parametric method that rapidly improves language model reasoning by distilling contrasts between successful and unsuccessful problem att…

This paper introduces a fuzzy-logic-based qualitative extension of Answer Set Programming (ASP) to integrate numerical information and qualitative reasoning.

AEGIS is a novel multi-agent framework that grounds vulnerability reasoning by reconstructing per-variable dependency chains over a Code Property Graph, achieving state-of-the-art performance on the P…

This paper introduces DynaKRAG, a method for multi-hop retrieval-augmented generation that learns a shared policy for evidence operations, achieving state-of-the-art results on three benchmarks.

The paper introduces LFTutor, an intelligent tutoring system leveraging LLMs and Socratic questioning to teach laypeople about logical fallacies, demonstrating its effectiveness in fostering critical…

DenseSteer is a training-free inference-time framework that improves the math reasoning capabilities of small language models by steering their internal representations toward a 'Dense Reasoning' patt…

The paper introduces HRBench, a unified and comprehensive evaluation framework for systematically benchmarking and comparing various thinking-mode switching strategies in hybrid-reasoning LLMs.