DS@GT ARC evaluates the effectiveness of Corrective RAG (CRAG) and CiteFix in improving citation faithfulness and answer grounding in Retrieval-Augmented Generation (RAG) QA systems, revealing a trade…

The paper proposes SAGA, a framework for schema-aware grounding in agentic text-to-SPARQL generation, which maintains a persistent type state, filters incompatible property candidates, and handles mis…

The paper introduces RefMem-Bench, a new benchmark for measuring reflective memory in long-horizon dialogue, and proposes REMIND, a framework that significantly improves models' ability to synthesize…

This paper proposes VideoTreeSearch (VTS), a framework for grounded long-video question answering that uses iterative self-correcting search over an adaptive temporal tree.

AdaptR1 is a novel Reinforcement Learning framework that adaptively manages reasoning effort at every step of multi-hop Question Answering, significantly reducing unnecessary computational cost withou…

SSR3D-LLM introduces a structured spatial reasoning interface for unified 3D-LLMs, allowing fine-grained object grounding by generating and processing sequential latent spatial steps.

The paper introduces pause-and-think-T, a reasoning-centric dataset and benchmark that enables compact Vision-Language Models to perform visually grounded, context-aware action suggestion, matching la…

The paper proposes a novel, efficient method for checking the factuality of claims generated by LLMs by framing it as a true/false reading comprehension task and incorporating explicit test-taking str…

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

The paper argues that LLM guardrails and persona dynamics create an unethical 'reality gap' by laundering epistemic risk onto users, advocating for task-level causal requirements over response-level m…

The paper identifies a failure mode called unfaithful capitulation (UC), where reasoning models maintain a correct internal thought process (chain-of-thought) but output an incorrect final answer when…

The paper introduces DigitalCoach, a dataset of human expert-novice computer use coaching sessions, and evaluates the ability of state-of-the-art models to teach humans how to use computers.

This paper investigates the production-evaluation gap in Large Reasoning Models (LRMs), finding that while LRMs excel at generating solutions, they struggle significantly to evaluate flawed reasoning,…

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…

The paper identifies and demonstrates that post-conclusion continuation in answer-correct long-CoT traces is harmful during LLM fine-tuning, proposing a method to cut this continuation.