Progressive Reasoning

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 22

All topics

Evidence-Inference Reconstruction: When The Evidence Is Recalled But The Reasoning Goes Wrong
Sep 27, 2026Megan Diehl, Ser-Nam LimMulti-Hop Reasoning Evidence-Grounded Questions
University of Central Florida
OPERA: A Unified Omnimodal Progressive Spatio-Temporal Reasoning Agent for Referring Video Segmentation
Sep 27, 2026Jingchen Ni, Yuji Wang, Shannan Yan +3Video Object Segmentation Multi-Modal Data
Tsinghua University · University of California San Diego · ETH Zurich
From Glance to Scrutiny: Progressive Distortion Reasoning for Fine-Grained Image Quality Assessment
Sep 8, 2026Aoting Zhang, Mingze Gao, Dongbao Yang +5Image Quality Assessment Multimodal Large Language Models
IIE, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Xiaohongshu Inc. +1
ThinkRetrieve: Retrieval-Augmented Reasoning Traces for Test-Time Scaling
Aug 11, 2026Vaibhav Singh, Soumya Suvra Ghosal, Sarvesh Gharat +3Test-Time Scaling Large Reasoning Models
IIT Bombay · University of Maryland, College Park · Adobe Research
Your Prompt Is Not the Only Prompt: How Much Do LLMs Weight Structured-Output Schema Descriptions?
Aug 8, 2026Sin-Ying LinSchema Prompt Engineering
Independent Researcher
Protoreasoning in Tiny Transformers
Aug 5, 2026Eduardo Valle, Fergal ReidProgressive Reasoning Small Large Language Models
Fin AI Research
On the Generalization of Steering Vectors for Chain-of-Thought Faithfulness
Jul 31, 2026Matthew Nguyen, Kyle Cox, Austin Meek +1Explanation Faithfulness Chain-of-Thought Reasoning
University of Virginia · Independent · University of Delaware +1
Deep Interaction: An Efficient Human-AI Interaction Method for Large Reasoning Models
Jul 15, 2026Hefeng Zhou, Jinxuan Zhang, Jiong Lou +4LLM Reasoning Strategies Large Reasoning Models
Shanghai Artificial Intelligence Laboratory · Shanghai Jiao Tong University
ThinkBLOX: 3D Indoor Scene Generation with Progressive Reasoning
Jul 15, 2026Yuan Xiao, Can Wang, Xiangyu Kong +13D Scene Generation 3D Scene Understanding
Department of Computer Science, City University of Hong Kong, Hong Kong · School of Computing and Data Science, University of Hong Kong · School of Computer Science, Beijing Information Science and Technology University
Progressive Reasoning with Primitive Correction for Compositional Zero-Shot Learning
Jul 7, 2026Ziyi Chen, Haoyan Shi, Sunhan Xu +1Compositional Generalization Progressive Reasoning
School of Computer Science and Technology, Beijing Jiaotong University · Key Laboratory of Big Data & Artificial Intelligence in Transportation (Ministry of Education)
GeoSearcher: Anchor-Guided Progressive Reasoning for Remote Sensing Visual Grounding with Process Supervision
Jul 1, 2026Dianyu Wang, Peirong Zhang, Xuyang Li +2Remote Sensing Multiple Vision Tasks
Aerospace Information Research Institute, the Key Laboratory of Network Information System Technology (NIST), and the Key Laboratory of Target Cognition and Application Technology (TCAT), Chinese Academy of Sciences, Beijing 100190, China · School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100190, China
PRISM: Progressive Reasoning through Iterative Slot Memory for Vision
May 29, 2026Ziyu Wang, Shuangpeng Han, Mengmi ZhangVisual Representations Frozen Backbone
Deep NeuroCognition Lab, Nanyang Technological University, Singapore
DRScaffold: Boosting Dense-Scene Reasoning in Lightweight Vision Language Models
May 25, 2026Xinrui Shi, Kai Liu, Ziqing Zhang +3Recent Vision-Language Models Scene Reasoning
1Shanghai Jiao Tong University
MixRea: Benchmarking Explicit-Implicit Reasoning in Large Language Models
May 19, 2026Yuanqing Cai, Ziyi Huang, Minhao Liu +3LLM Reasoning Strategies Progressive Reasoning
Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China
D $^2$ Evo: Dual Difficulty-Aware Self-Evolution for Data-Efficient Reinforcement Learning
May 16, 2026Ru Zhang, Renda Li, Ziyu Ma +4Progressive Reasoning
Alibaba Group · AMAP, Alibaba Group · BUPT
TRACES: Tagging Reasoning Steps for Adaptive Cost-Efficient Early-Stopping
Apr 22, 2026Yannis Belkhiter, Seshu Tirupathi, Giulio Zizzo +1Large Reasoning Models Progressive Reasoning
IBM Research Europe · Trinity College Dublin · Dublin, Ireland +1
Process Reward Models Meet Planning: Generating Precise and Scalable Datasets for Step-Level Rewards
Apr 20, 2026Raffaele Pisano, Roberto NavigliProcess Reward Model Table Reasoning Datasets
Babelscape · Sapienza University of Rome
StoryCoder: Narrative Reformulation for Structured Reasoning in LLM Code Generation
Apr 16, 2026Geonhui Jang, Dongyoon Han, YoungJoon YooCode Generation Narratives
Dept. of Artificial Intelligence, Chung-Ang University · NAVER AI Lab
Less Data Approximates More: Earning Faithful Confidence in High-Stakes Domains
Apr 9, 2026Haokai Ma, Lee Yan Zhen, Gang Yang +4Supervised Finetuning Faithfulness
National University of Singapore, Singapore · Singapore Management University, Singapore
Step-Level Sparse Autoencoder for Reasoning Process Interpretation
Mar 3, 2026Xuan Yang, Jiayu Liu, Yuhang Lai +3LLM Reasoning Strategies Improving Sparse Autoencoders
Department of Data Science, City University of Hong Kong · Hong Kong Institute of AI for Science, City University of Hong Kong · Li Auto Inc +1
ActionEngine: From Reactive to Programmatic Web Agents via State Machine Memory
Feb 24, 2026Hongbin Zhong, Fazle Faisal, Luis França +4Web Agents Reactive
Georgia Tech USA · Microsoft Research USA
Step-Tagging: Toward controlling the generation of Language Reasoning Models through step monitoring
Dec 16, 2025Yannis Belkhiter, Seshu Tirupathi, Giulio Zizzo +1Large Reasoning Models Progressive Reasoning
1IBM Research Europe, Dublin, Ireland · 2Trinity College Dublin, Ireland · 3ADAPT Research Centre, Dublin, Ireland

Sep 27, 2026, cs.AIJ/K move · Enter open · S save

Evidence-Inference Reconstruction: When The Evidence Is Recalled But The Reasoning Goes Wrong

Megan Diehl, Ser-Nam Lim

University of Central Florida

Multi-Hop Reasoning Evidence-Grounded Questions Progressive Reasoning Large Language Model Agents

Open paper AskPDF arXiv

Modern multi-hop LLM agents are equipped with built-in mechanisms to detect errors in intermediate reasoning steps. Such errors trigger corrective actions from these agents, which mostly follow the paradigm of retrying the steps or the reasoning trajectories. Not only are these retries expensive, we present in this paper that they are also potentially unnecessary. To this end, we introduce Evidence-Inference Reconstruction (EIR), which uses structured state to guide one retrieval trajectory, accumulating source evidence in the process. We show that as long as the relevant evidence has been collected, EIR is capable of generating the correct answer in a single final model call even if erroneous evidence has been mixed in due to incorrect intermediate reasoning steps. In one evaluation, using Haiku 4.5 and GPT-4.1 Mini, we evaluate EIR on matched 1,000-question subsets of HotpotQA, 2WikiMultiHopQA, and MuSiQue, showing that EIR improves Answer F1, the overlap between the model's and the correct answer, over the baseline by 8.3--32.8 points, Agentic SSR by 10.6--29.1 points, and Reflexion by 1.1--15.9 points. Additionally, we show that EIR averages 4.85 total model calls per question, compared with 35.29 for Agentic SSR and 12.41 for Reflexion. Together, these results corroborate EIR's central premise: separating evidence retrieval from the final answer model call can improve answer accuracy while utilizing substantially less computation.

Momentum

Related topics

Latest papers 22