The paper proposes a layered verification approach for argument graphs generated by large language models (LLMs). It suggests starting with deterministic checks, then using solver-based methods, followed by LLM reviews, and resorting to debate only when uncertainty remains, reserving human judgment for cases no other instrument can resolve. A study on human-annotated graphs with injected defects shows that while LLM reviewers can detect structural issues with high recall, they also produce false positives, exhibit inconsistent verdicts, and are slower than exact checks, underscoring the need for deterministic verification gates.
arXiv:2606. 16603v1 Announce Type: cross Abstract: LLM-based agents have demonstrated strong capabilities in data-intensive analytical tasks, yet their outputs are rarely verifiable: a reliance on linear text trajectories makes their reasoning difficult to audit.
The paper introduces a typed reasoning graph framework to compare human and large language model (LLM) reasoning paths in scientific fact‑checking. By modeling explanations as graphs linking false claims to study context, findings, premises, and fallacy labels, the authors enable one‑to‑one alignment of human and LLM reasoning at the sub‑graph level. Using 84 false claims from MISSCIPLUS, they evaluate GPT‑5, Claude Opus 4.7, and Qwen3‑32B, finding distinct performance patterns: Qwen3‑32B has the lowest verdict failure rate, GPT‑5 shows the highest human alignment, and Claude Opus 4.7, while weak at verdict prediction, often produces valid reasoning in successful cases.
The paper introduces RuVerBench, a benchmark with 2,458 instances for evaluating the reliability of Large Language Models acting as judges (LaaJ) in verifying rubric compliance within agentic scenarios such as deep research and agentic coding. It systematically meta‑evaluates frontier LLMs, revealing that even the most advanced models perform well yet still produce substantial noise. The study also examines how prompt design, batching, and majority voting affect verification accuracy, noting that weaker models are more prompt‑sensitive, batched verification trades accuracy for efficiency, and majority voting offers diminishing returns.
The paper introduces Reasoning DAG Probing, a method that treats premises, intermediate conclusions, and final answers as nodes in a directed acyclic graph (DAG). By training lightweight probes on LLM hidden states, the authors show that DAG structure is encoded in the models, peaking in intermediate layers and becoming stronger with larger models. During autoregressive generation, the latent DAG structure emerges progressively, anticipating answer correctness and enabling correction of some incorrect outputs by steering activations toward the ground‑truth DAG.
The paper introduces a two-stage diagnostic evaluation to assess the structural reliability of reasoning graphs used in large language models for tasks like multi-hop question answering. Stage 1 examines how graph reliability depends on topology, prompt design, and model family, while Stage 2 evaluates the impact of graph errors on uncertainty estimation. Findings show that graph-based computation is vulnerable to upstream errors, offers limited benefit as prompt context alone, but improves confidence-based answer discrimination and enables node-level diagnostics.
The paper presents a unified dataset of 350 Lean tasks to evaluate specification generation (SpecGen) for verifiable code, combining metrics of formal validity, reference similarity, equivalence, and behavioural adequacy. It highlights that restricting similarity measures to a subset of tasks can shift rankings, and shows that a perfect postcondition score can still miss critical input coverage, underscoring the need for separate feedback on input and output constraints.
arXiv:2609.13808v1 Announce Type: new Abstract: Structured knowledge fact checking aims to determine the truthfulness of natural language claims by reasoning over structured evidence. Recent program-...
arXiv:2607. 17917v1 Announce Type: new Abstract: Scientific Reasoning Graph Extraction (SRGE) aims to recover explicit links among observations, evidence, intermediate claims, and paper-level conclusions.
GraphCert introduces a method to bootstrap graph reasoning agents by generating graph‑grounded question‑answer pairs and certifying the supporting evidence. The approach uses a Bootstrapped Graph Quizzer to produce QA pairs, then executes and semantically curates the evidence into certified rubrics that guide reward‑based training of a Graph Solver. Experiments on five GRBENCH domains show GraphCert outperforms larger LLM agents and demonstrates robust policy transfer across heterogeneous graphs.
arXiv:2610.15107v1 Announce Type: new Abstract: Chain-of-thought prompting enables reasoning in large language models but produces explanations that are difficult to verify, expensive to generate, an...
arXiv:2610.18606v1 Announce Type: new Abstract: Large language models increasingly tackle tasks that require multi-step reasoning, where errors in intermediate claims can affect the final answer. Sel...
As autonomous AI agents take on every stage of scientific inquiry, research output is expanding far beyond human review capacity. Yet scientific communication still relies on natural-language prose: a...