arXiv:2604. 01993v2 Announce Type: replace-cross Abstract: Multi-hop QA benchmarks often reward Large Language Models (LLMs) for spurious correctness, where models reach correct answers through invalid intermediate reasoning.
PRO-Step introduces a step‑level process reward optimization framework for Retrieval‑Augmented Generation (RAG) that evaluates both logical validity and evidential grounding at each reasoning step. By training a generative Preference‑Based Reward Model (PRM) and using PRM‑guided value tree search to create preference pairs, the method optimizes the policy through step‑level Direct Preference Optimization. Experiments on single and multi‑hop QA benchmarks show that PRO‑STEP achieves the best average EM and F1 scores across five datasets.
arXiv:2608.22753v1 Announce Type: new Abstract: Large language models (LLMs) excel at text understanding and generation, yet still struggle to reliably understand and apply externally provided proced...
arXiv:2607. 23019v1 Announce Type: new Abstract: Chain-of-thought (CoT) prompting enables large language models (LLMs) to tackle multi-step reasoning tasks, yet the generated intermediate steps are not guaranteed to be logically sound.
arXiv:2607. 10562v1 Announce Type: new Abstract: Evaluating the multi-hop reasoning capabilities of large language models remains a significant challenge.
arXiv:2606. 05402v1 Announce Type: cross Abstract: Large reasoning models (LRMs) produce reasoning traces with non-linear structures, such as backtracking and self-correction, that complicate the evaluation and monitoring of the reasoning process.
arXiv:2608. 07838v1 Announce Type: new Abstract: Large language models (LLMs) have increasingly supported response generation grounded in user-provided knowledge spanning heterogeneous structures.
arXiv:2504. 07385v3 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) become increasingly used for question-answering (QA), relying on static, pre-annotated references for evaluation poses significant challenges in cost, scalability, and completeness.
arXiv:2606. 10460v1 Announce Type: cross Abstract: Recent large language models (LLMs) have shown rapid progress in reading-based question answering (QA), where evidence is explicitly provided or can be trivially retrieved.
arXiv:2607. 05992v1 Announce Type: cross Abstract: Mathematical reasoning has become a central task for evaluating and tuning reasoning Large Language Models (LLMs), yet existing benchmarks remain heavily biased toward high-resource languages, with English and Chinese dominating both pre-training corpora and evaluation suites.
arXiv:2608. 12282v1 Announce Type: new Abstract: Agents deployed in enterprise settings must reason across structured APIs and document collections, yet existing benchmarks evaluate these capabilities in isolation.
arXiv:2605. 19228v2 Announce Type: replace-cross Abstract: Large Language Models have achieved strong performance on reasoning tasks with objective answers by generating step-by-step solutions, but diagnosing where a multi-step reasoning trace might fail remains difficult.