LLM Reasoning

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

68 papers in the last four weeks, up 143% on the four weeks before. 0.7% of all new papers.

Jul 13Week of Sep 28

Latest papers 650

All topics

Learning from Teacher Continuations at Student States
Sep 28, 2026Haojin Wang, Dylan Zhang, Huaibo Chen +8Language Model Distillation On-Policy Distillation
University of Illinois at Urbana-Champaign · Massachusetts Institute of Technology · University of Pennsylvania +2
When Confidence Rises Too Early: Detecting Shortcut Reasoning via Premature Answer Commitment
Sep 28, 2026Zhaohan Zhang, Junjie Liu, Chengzhengxu Li +6Faithfulness of Language Model Explanations Confidence Estimation in Language Models
Queen Mary University of London · Tongyi Lab, Alibaba Group · Xi’an Jiaotong University
Teach to Learn: Hint Annealing for Self-improving LLM Reasoning
Sep 28, 2026Zile Wang, Zijian Li, Haodong Wang +5Reinforcement Learning Self-Training for Language Models
The Hong Kong University of Science and Technology · Yuanbao Team, Tencent
Rewarding Novel Deductions: Solver-guided Process Supervision for Logical Reasoning
Sep 28, 2026Muhammad Asif Ali, Wenqing Wang, Huan Wang +1RL for Language Model Reasoning Process Supervision
FORTE Lab, Faculty of Science, Information Technology University, Lahore, Pakistan · College of Informatics, Huazhong Agricultural University, Wuhan, China · Qatar Computing Research Institute, Hamad Bin Khalifa University, Doha, Qatar
Knowing When Thinking Is Not Enough: Teaching Small Reasoning Models to Reason Beyond Their Parametric Knowledge
Sep 28, 2026Chanuk Lee, Minki Kang, Sangwoo Park +3Cost-Aware Inference Efficient Language Model Reasoning
KAIST
Direct Self-Evolving Optimization: Evolving LLMs without Challenger Training
Sep 28, 2026Yuyang Deng, Yu Wang, Jiayun WangSelf-Training for Language Models Large Language Model-Guided Optimization
Accenture, Center for Advanced AI · Georgia Institute of Technology
Investigating Human--AI Discrepancies via Multiple-Solution Problems
Sep 28, 2026Zihao Wang, Francesco Insulla, Andrea MontanariGenerative AI Evaluation LLM Reasoning
Department of Mathematics, Stanford University · Institute of Computational and Mathematical Engineering, Stanford University · Department of Statistics and Department of Mathematics, Stanford University
How code helps different tasks? A decompositional lens on LLM post-training
Sep 27, 2026Zheng Yu, Yiwei Li, Yishen Chen +4LLM Fine-Tuning Instruction-Tuning Data Selection
Sun Yat-sen University · Shenzhen Loop Area Institute · The Chinese University of Hong Kong, Shenzhen +1
Selecting Diverse SFT Traces Improves Post-RL Generalization
Sep 27, 2026Dylan Zhang, Mingyuan Wu, Jinning LiReasoning Diversity RL for Language Model Reasoning
University of Illinois Urbana-Champaign, work done at Google · Google
Rethinking Token Reweighting for SFT: Suppress, Reverse, and Extrapolate Learned Features
Sep 27, 2026Cunchun Li, Haonan He, Yifan Gao +4Supervised Fine-Tuning Adaptive Loss Weighting
Shanghai AI Laboratory · University of Science and Technology of China · Fudan University +2
EnigmaForge: The Question Is Hidden in the Story
Sep 24, 2026Daniel EisnerQuestion Answering Synthetic Benchmark Generation
No More Free Lunch: Corpus Task Complexity Matters as Corpora Grow
Sep 24, 2026Prasann Singhal, Amanda Bertsch, Jacob Steinhardt +1Long-Context Language Model Evaluation LLM Reasoning
UC Berkeley · Carnegie Mellon University · Allen Institute for AI
ELF-REG: Scaling Continuous Diffusion Language Models to Reasoning Tasks
Sep 24, 2026Zeyu Michael Li, William Xingxu Chen, Bingshuo Qian +2Code Generation Diffusion Language Models
Duke University · Tsinghua University
Can LLMs Reason About Runtime Behavior? A Repository-Level Dynamic Benchmark
Sep 23, 2026Hamed Taherkhani, Mohammad Abdollahi, Melika Sepidband +3LLM Evaluation Software Engineering Benchmarks
York University Toronto, Canada · The University of Texas at Dallas Texas, USA
Planned Test-Time Scaling with Coordinated Reasoning Paths
Sep 23, 2026Xueqing Wu, Langxing Bai, Hritik Bansal +5RL for Language Model Reasoning Test-Time Scaling
University of California, Los Angeles · Amazon
LOCKR: A Hidden-State Trajectory-Guided Planner for Detecting and Repairing Stable-but-Wrong Lock-In in Diffusion Language Models
Sep 23, 2026Guoshenghui Zhao, Tan Yu, Weijie ZhaoDiffusion Language Model Inference Diffusion Language Models
Rochester Institute of Technology · NVIDIA Corporation
Beyond Repeated Sampling: Learning Search Policies for LLM Reasoning
Sep 22, 2026Ismail Labiad, Matthieu Kowalski, Marc Schoenauer +2RL for Language Model Reasoning LLM Reasoning
Meta FAIR · Université Paris-Saclay, LISN, Inria, CNRS · NYU Courant Institute and CDS
Ladders of Thought: A Self-Evolving Curriculum of Progressively Simplified Reasoning Traces
Sep 22, 2026Minghui Liu, Thomas Magelinski, Dehao Yuan +2Numerical Reasoning in Language Models Curriculum Learning
University of Maryland, College Park · Capital One
Robust Failure, Conservative Repair: Textual Knowledge Distillation from Cross-Model Failures
Sep 21, 2026Andrew Ren, Haokun Liu, Chenhao TanKnowledge Distillation LLM Reasoning
University of Chicago
Efficient Reasoning Exploration via State-Conditioned Latent Steering with Progress Guidance
Sep 21, 2026Hengyuan Zhang, Chenming Shang, Zunhai Su +10Best-of-N Sampling Inference-Time Guidance
The University of Hong Kong · University of California, Los Angeles · Arizona State University +3
What Does Privileged Information Add to On-Policy Self-Distillation?
Sep 17, 2026XiuYu Zhang, Wei Chow, Junfeng Fang +2On-Policy Self-Distillation Learning Using Privileged Information
National University of Singapore
Think Thrice Before Reranking: Multi-perspective Evidence and Reasoning Integration for Text Reranking
Sep 17, 2026Lijun Liu, Zhengzong Chen, Wenyan Li +2Learning to Rank RL for Language Model Reasoning
Honor Device Co., Ltd
LLM-as-an-Improver: Turning Verification into Better Candidates
Sep 17, 2026Akiyoshi Tomihari, Yuma IchikawaLLM Answer Verification LLM Reranking
Fujitsu Limited Department of Computer Science The University of Tokyo · Fujitsu Limited RIKEN center for AIP
Clueing up LLMs with Tool-Augmented Deductive Reasoning
Sep 16, 2026Rebecca Ansell, Autumn Toney-WailsMulti-Agent LLM Systems AI Agent Benchmarks
Georgetown University · Syntheos, Corp · UNU-MERIT
What Counts as Strategic Reasoning? A Systematic Mapping of Chess Research on Humans, Engines, and Language Models
Sep 16, 2026Paolo Ciancarini, Remo PareschiChess Human-AI Decision Making
Department of Computer Science and Engineering, University of Bologna, Bologna, Italy · Stake Lab, University of Molise, Campobasso, Italy
Bellman Policy Optimization
Sep 14, 2026Zhuoqing Song, Haotian Xu, Xikun Zhang +1Reinforcement Learning RL for Language Model Reasoning
1Apodex US, Inc. · 2Princeton University
Stellar Colosseum: A Many-Agent Harness for Long-Horizon Research in Mathematics and Theoretical Computer Science
Sep 14, 2026Honghao Lin, David P. Woodruff, Yuan Deng +3Inference-Time Search Automated Theorem Proving
1Google Research. · 2Carnegie Mellon University.
Discrete Beckmann Transport Models for One-Step Language Modeling and Reasoning
Sep 14, 2026Sophia Tang, Shiyi WangOne-Step Generative Modeling Flow-Based Generative Modeling
University of Pennsylvania · Harvard University · Kempner Institute +1
HISPO: Hierarchical Importance-Sampling Policy Optimization with Entropy-Derived Segments
Sep 14, 2026Quoc-Vinh Lai-Dang, Hyo-Sang ShinRL for Language Model Reasoning Credit Assignment in RL
Cho Chun Shik Graduate School of Mobility KAIST
CWM: Controllable White-Box Meta-Prompting for Adaptive Retrieval-Augmented Generation and Reasoning Ability
Sep 14, 2026Keuntae Kim, Eunhye Jeong, Yong Suk ChoiLLM Prompting Adaptive RAG
Department of Computer Science, Hanyang University, Seoul, Korea · Department of Artificial Intelligence, Hanyang University, Seoul, Korea

Sep 28, 2026, cs.CLJ/K move · Enter open · S save

Learning from Teacher Continuations at Student States

Haojin Wang, Dylan Zhang, Huaibo Chen, Suhao Yu+7

University of Illinois at Urbana-Champaign · Massachusetts Institute of Technology · University of Pennsylvania+2

Language Model Distillation On-Policy Distillation Knowledge Distillation LLM Reasoning

Open paper AskPDF arXiv

We present OLIVE (OnLine InterVEntion). At each iteration, the evolving student policy generates a new prefix, the teacher continues it autoregressively, and the student is updated using cross-entropy computed on the teacher-generated tokens. Each design choice targets a corresponding limitation of existing distillation methods: (1) sequential covariate shift in offline supervised fine-tuning (SFT) on fixed teacher trajectories, (2) fragmented supervision under prefix failure in token-level on-policy distillation (OPD), and (3) the need for access to teacher token probabilities in distribution-matching distillation. OLIVE achieves higher reasoning performance than OPD (with a top-16 KL approximation) at comparable GPU-hour cost. Our asynchronous implementation further reduces OLIVE's total training time by 23.8%. We evaluate OLIVE on both hard reasoning tasks and agentic tasks which reflects modern post-training scenarios, and it consistently outperforms existing distillation methods under the same training budget. By regenerating prefixes from the evolving student, OLIVE continues improving after offline distillation plateaus while better preserving the general capabilities and plasticity of the student. Using only text from GPT-5.4-mini, continuously training with OLIVE outperforms offline SFT from the same teacher by 13% on ScienceWorld. These results support OLIVE as an effective and efficient approach to online language-model distillation.

Momentum

Related topics

Latest papers 650