LLM-as-a-Judge models generate chain-of-thought (CoT) sequences intended to capture the step-bystep reasoning process that underlies the final evaluation of a response. However, due to the lack of human annotated CoTs for evaluation, the required components and structure of effective reasoning traces remain understudied. Consequently, previous approaches often (1) constrain reasoning traces to hand-designed components, such as a list of criteria, reference answers, or verification questions and (2) structure them such that planning is intertwined with the reasoning for evaluation. In this work, we propose EvalPlanner, a preference optimization algorithm for Thinking-LLM-as-a-Judge that first generates an unconstrained evaluation plan, followed by its execution, and then the final judgment. In a self-training loop, EvalPlanner iteratively optimizes over synthetically constructed evaluation plans and executions, leading to better final verdicts. Our method achieves a new state-of-the-art performance for generative reward models on RewardBench (with a score of 93.9), despite being trained on fewer amount of, and synthetically generated, preference pairs. Additional experiments on other benchmarks like RM-Bench, JudgeBench, and FollowBenchEval further highlight the utility of both planning and reasoning for building robust LLM-as-a-Judge reasoning models.
SpatialChain: A Benchmark for Auditing Spatial Reasoning Faithfulness in VLMs
Universidade Federal de Mato Grosso (UFMT)(马托格罗索联邦大学);Universidade Federal de Goiás (UFG)(戈亚斯联邦大学);Advanced Knowledge Center for Immersive Technologies (AKCIT)(沉浸式技术高级知识中心)
PRIME: Planning and Retrieval-Integrated Memory for Enhanced Reasoning
Center for Healthcare Organization and Implementation Research, VA Bedford Health Care(VA Bedford Health Care 医疗组织与实施研究中心);Manning College of Information and Computer Sciences, University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校信息与计算机科学学院);Miner School of Computer and Information Sciences, University of Massachusetts Lowell(马萨诸塞大学洛厄尔分校 Miner 信息与计算机科学学院)
ELLIS Alicante at CQs-Gen 2025: Winning the critical thinking questions shared task: LLM-based question generation and selection
ELLIS Alicante(ELLIS阿利坎特);Universidad Alfonso X el Sabio(阿尔fonso X el Sabio大学);Universitat d’Alacant(阿利坎特大学);École Polytechnique Fédérale de Lausanne(洛桑联邦理工学院)
Don't Wait to Reply: Towards Responsive yet Thoughtful Dialogue through Proactive Thinking
Dept. of Comp. Sci. & Tech., Institute for AI, Tsinghua University(清华大学计算机科学与技术系、人工智能研究院);Institute for AI Industry Research (AIR), Tsinghua University(清华大学人工智能产业研究院);Tencent(腾讯)
ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning
Shanghai Jiao Tong University(上海交通大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);University of British Columbia(不列颠哥伦比亚大学);University College London(伦敦大学学院)
GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning
Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学高瓴人工智能学院);Beijing Academy of Artificial Intelligence(北京人工智能研究院);Tsinghua University(清华大学);The Hong Kong Polytechnic University(香港理工大学)
PoTable: Towards Systematic Thinking via Plan-then-Execute Stage Reasoning on Tables
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China(中国科学技术大学认知智能国家重点实验室);Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院)
The Thinking Therapist: Training Large Language Models to Deliver Acceptance and Commitment Therapy using Supervised Fine-Tuning and Odds Ratio Policy Optimization
Department of Psychiatry University of Toronto(精神病学系多伦多大学)
Tree-of-Mixed-Thought: Combining Fast and Slow Thinking for Multi-hop Visual Reasoning
University of Science and Technology of China(中国科学技术大学);cmss.chinamobile.com(中移(苏州)软件技术有限公司);Lin Gang Laboratory(林冈实验室);ShanghaiTech University(上海科技大学)
Thinking Like a Botanist: Challenging Multimodal Language Models with Intent-Driven Chain-of-Inquiry
Department of Robotics and Mechatronics Engineering, University of Dhaka(达卡大学机器人与机电工程系);Department of Computer Science and Engineering, University of Dhaka(达卡大学计算机科学与工程系);Department of Agronomy, Gazipur Agricultural University(加兹ipur农业大学作物学系);Department of Botany, University of Dhaka(达卡大学植物学系)
JudgeRLVR: Judge First, Generate Second for Efficient Reasoning
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University(多媒体信息处理国家重点实验室,计算机学院,北京大学);CFCS, School of Computer Science, Peking University(计算机学院,北京大学);LLM-Core Xiaomi(小智LLM核心)
Thinking Ahead: Foresight Intelligence in MLLMs and World Model
College of Software, Nankai University, China(南开大学软件学院);The University of Hong Kong, China(香港大学);NKIARI, Shenzhen Futian, China(NKIARI,深圳福田,中国);AAIS & VCIP, Nankai University, China(AAIS与VCIP,南开大学,中国);A*STAR Institute of Advanced Intelligence and Computing, Singapore(新加坡A*STAR先进智能与计算研究所)