arXiv AI

Improving LLM Interpretability with User-Centric Chain-of-Thought Reasoning

The paper proposes a user‑centric Chain‑of‑Thought (CoT) reasoning framework that structures LLM reasoning traces into self‑contained, verifiable steps using XML‑like tags. This design allows users to independently assess and correct the AI’s reasoning while preserving performance on mathematical reasoning tasks. User studies show that the approach improves perceived usefulness and ease of use compared to standard CoT.

arXiv AI
6d ago

From Atomic to Agentic: Towards Interpretable Evaluation of LLMs' Agentic Mathematical Capabilities

The paper introduces a new benchmark that evaluates large language models (LLMs) on their agentic mathematical reasoning rather than just final answers. It aligns problem‑solving behaviors with a taxonomy of reusable mathematical atomic capabilities and includes planning, action, and feedback tasks in both textual and multimodal settings. Experiments show that models with similar end‑to‑end accuracy can have very different agentic profiles, highlighting the importance of process‑level evaluation.

By Jiayi Kuang, Yinghui Li, Yunze Song, Keyu Chen, Zhifeng Shen, Yangning Li, Yidong Wang, Di Yin, Ruizhi Qiao, Xing Sun, Kai Jin, Ying Shen, Liang Lin, Philip S. Yu
arXiv Computation and Language
Aug 27

ReFIne: A Framework for Trustworthy Large Reasoning Models with Reliability, Faithfulness, and Interpretability

ReFIne is a training framework that augments large reasoning models with three trustworthiness properties: interpretability, faithfulness, and reliability. It combines supervised fine‑tuning with GRPO to produce structured, tag‑based reasoning traces, explicitly disclose decisive information, and provide self‑assessments of soundness and confidence. Applied to Qwen3 models, ReFIne improves interpretability by 44.0 %, faithfulness by 18.8 %, and reliability by 42.4 % on mathematical benchmarks.

By Chung-En Sun, Ge Yan, Akshay Kulkarni, Tsui-Wei Weng
arXiv AI
Jun 16

VeriGraph: Towards Verifiable Data-Analytic Agents

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.

By Jiajie Jin, Zhao Yang, Wenle Liao, Yuyang Hu, Guanting Dong, Xiaoxi Li, Yutao Zhu, Zhicheng Dou
arXiv AI
Aug 14

MARC v1: An Open-Source Multi-Agent Framework for Clinical AI Reasoning and Coordination

arXiv:2608. 13476v1 Announce Type: new Abstract: We present Multi-Agent Reasoning and Coordination (MARC), an open-source framework that replaces monolithic LLM prompting with deterministic multi-agent orchestration for clinical reasoning.

By Saisha Shetty, Satvik Tripathi, Austin Lin, Colin Zhao, Theodore Kim, Don Enwerem, Jacinta Arnold, Shahriar Faghani, Tessa S Cook
arXiv AI
Aug 24

Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning

The paper introduces a method to improve test-time scaling (TTS) for large language models by using multi-agent systems (MAS) to split long reasoning chains into manageable contexts. A new dataset, M500, containing 500 multi-agent collaborative reasoning traces, is used to fine‑tune open‑source models, enabling them to learn collaborative patterns and outperform their base versions. An adaptive scaling strategy with a "CEO" agent is proposed to dynamically guide reasoning depth, and experiments in the AgentVerse framework confirm the effectiveness of the approach.

By Can Jin, Hongwu Peng, Qixin Zhang, Yujin Tang, Dimitris N. Metaxas, Tong Che