Inference-Time

Follow this topic Ask about this topic

Recent momentum

-29%

15 papers in the last 28 days · 0.2% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-21

3 new papers

A weekly snapshot of new work published in Inference-Time.

Period ending 2026-09-14

5 new papers

A weekly snapshot of new work published in Inference-Time.

Period ending 2026-09-07

10 new papers

A weekly snapshot of new work published in Inference-Time.

197 papers

Latest in Inference-Time

Browse all topics →

Inference Time Optimization with Confidence Dynamics
May 24, 2026Yu Wang, Minghao Liu, Jiayun Wang +3Inference-Time Deepseek
Boosting Inference with Guided Reasoning: Stochastic Exploration for Recursive Models
May 24, 2026Andrew Corbett, Archit Sood, Anna Tzatzopoulou +2Reasoning Trajectory Recursion
Trust but Verify: Prover-Verifier Deliberation for Selective LLM Prediction
May 24, 2026João Sedoc, Baotong Zhang, Dean FosterLiar Theorem
Distilling Game Code World Model Generation into Lightweight Large Language Models
May 23, 2026Tyrone Serapio, Arjun Prakash, Haoyang Xu +2Code Generation Large Language Model Generation
Inference Time Context Sparsity: Illusion or Opportunity?
May 22, 2026Sahil Joshi, Prithvi Dixit, Agniva Chowdhury +5LLM Inference Efficiency Dynamic Sparse Attention
RAS: Reflection-Augmented Scaling with In-Context Learning for Executable Cypher Query Generation
May 21, 2026Minseok Jung, Abhas Ricky, Muhammad Rameez ChatniInference-Time Text2Cypher
Vector Policy Optimization: Training for Diversity Improves Test-Time Search
May 21, 2026Ryan Bahlous-Boldi, Isha Puri, Idan Shenfeld +6Multi-Objective Policy Optimization Large Language Model Post-Training
Can Transformers Learn to Verify During Backtracking Search?
May 21, 2026Yin Jun Phua, Tony Ribeiro, Tuan Nguyen +1Transformer Architectures Backward Induction
MLLMs Know When Before Speaking: Revealing and Recovering Temporal Grounding via Attention Cues
May 21, 2026Dazhao Du, Liao Duan, Jian Liu +5Video Temporal Grounding Temporal Grounding
CrossVLA: Cross-Paradigm Post-Training and Inference Optimization for Vision-Language-Action Models
May 21, 2026Zhi LiuPretrained Vision-Language-Action Vision-Language-Action Models
AVSD: Adaptive-View Self-Distillation by Balancing Consensus and Teacher-Specific Privileged Signals
May 20, 2026Duy Nguyen, Hanqi Xiao, Archiki Prasad +7Teacher Inference-Time
Neurosymbolic Learning for Inference-Time Argumentation
May 19, 2026Gabriel Freedman, Adam Dejl, Adam Gould +4Noisy Claim Verification Neuro-Symbolic Framework
GEM: GPU-Variability-Aware Expert to GPU Mapping for MoE Systems
May 19, 2026Sourish Wawdhane, Avinash Kumar, Poulami DasMixture-Of-Expert Inference Mixture-of-Experts Models
When Tabular Foundation Models Meet Strategic Tabular Data: A Prior Alignment Approach
May 19, 2026Xinpeng Lv, Yunxin Mao, Renzhe Xu +13Tabular Foundation Models Tabular Prior-Data Fitted Network
Inference-Time Scaling in Diffusion Models through Iterative Partial Refinement
May 19, 2026Taegu Kang, Jaesik Yoon, Sungjin AhnInference-Time Iterative Refinement
Beyond Inference-Time Search: Reinforcement Learning Synthesizes Reusable Solvers
May 18, 2026Soheyl Massoudi, Gabriel Apaza, Milad Habibi +1Future Llm-Assisted Solver Development Llm-Based Optimization Modeling
Semantic Reranking at Inference Time for Hard Examples in Rhetorical Role Labeling
May 18, 2026Anas Belfathi, Nicolas Hernandez, Laura Monceaux +2Reranking Soft-Label
CounterFlow: A Two-Phase Inference-Time Sampling for Counterfactual Video Foley Generation
May 18, 2026Gyubin Lee, Junwon Lee, Juhan NamJoint Audio-Video Generation Audio Latent
Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path Measures
May 18, 2026Chenyang Wang, Weizhong Wang, Yinuo Ren +2Monte Carlo Inference-Time
Harnessing LLM Agents with Skill Programs
May 18, 2026Hongjun Liu, Yifei Ming, Shafiq Joty +1Large Language Model Agents Inference-Time
Adaptive Generate-Rank-Verify: Inference-Time Search with Costly Verification
May 17, 2026Shaddin Dughmi, Mahdi Haghifam, Yusuf Hakan KalayciInference-Time Verifier
Dual-Dimensional Consistency: Balancing Budget and Quality in Adaptive Inference-Time Scaling
May 14, 2026Rongman Xu, Yifei Li, Tianzhe Zhao +3LLM Inference Efficiency Large Language Model Reasoning
EnergyLens: Predictive Energy-Aware Exploration for Multi-GPU LLM Inference Optimization
May 14, 2026Zhiye Song, Kyungmi Lee, Eun Kyung Lee +3LLM Inference Efficiency Multi-Gpu Systems
Inference-Time Machine Unlearning via Gated Activation Redirection
May 12, 2026Vinícius Conte Turani, Otávio Parraga, João Vitor Boer Abitante +7Training-Free Inference Framework Inference-Time
Plan Before You Trade: Inference-Time Optimization for RL Trading Agents
May 12, 2026Eun Go, Rohan Deb, Arindam BanerjeePortfolio Optimization Inference-Time Control
OLIVIA: Online Learning via Inference-time Action Adaptation for Decision Making in LLM ReAct Agents
May 11, 2026Sheldon Yu, Junda Wu, Xintong Li +6Large Language Model Agents Personalized Large Language Model Agents
Quantifying Concentration Phenomena of Mean-Field Transformers in the Low-Temperature Regime
May 11, 2026Albert Alcalde, Leon Bungert, Konstantin Riedl +1Transformer Encoder Transformer Architectures
Improving Temporal Action Segmentation via Constraint-Aware Decoding
May 11, 2026Yeo Keat Ee, Debaditya Roy, Chen Li +2Temporal Action Segmentation Inference-Time
Guided Streaming Stochastic Interpolant Policy
May 11, 2026Puming Jiang, Meiyi Wang, Kelvin Lin +2Inference-Time Control Robot Policies
TimeClaw: A Time-Series AI Agent with Exploratory Execution Learning
May 11, 2026Hangchen Liu, Dongyuan Li, Renhe Jiang +3Inference-Time Artificial Intelligence Agents
The two clocks and the innovation window: When and how generative models learn rules
May 11, 2026Binxu Wang, Emma Lucia Byrnes Finn, Bingbin LiuGenerative Models Clocks
PruneTIR: Inference-Time Tool Call Pruning for Effective yet Efficient Tool-Integrated Reasoning
May 11, 2026Luan Zhang, Dandan Song, Zhijing Wu +8Large Language Model Reasoning Fewer Tool-Call Errors
Enabling Structure-Only Initialization and Out-of-Distribution Generalization in GNN-based Molecular Dynamics Simulators
May 10, 2026S. A. Shteingolts, Salman N. Salman, Dan MendelsMolecular Dynamics Inverse Design
PMCTS: Principled Parallelized Inference Time Scaling with Particle Monte Carlo Tree Search
May 9, 2026Yaniv Oren, Viliam Vadocz, Joery A. de Vries +3Monte Carlo Tree Search Monte Carlo
Training with Harnesses: On-Policy Harness Self-Distillation for Complex Reasoning
May 9, 2026Zhengyang Zhao, Lu Ma, Wentao ZhangUnsupervised On-Policy Self-Distillation Inference-Time
Semantic Voting: Execution-Grounded Consensus for LLM Code Generation
May 9, 2026Shan Jiang, Zijian Yi, Chenguang ZhuCode Generation Large Language Model Generation
Sketch-and-Verify: Structured Inference-Time Scaling via Program Sketching
May 9, 2026Shan Jiang, Zijian Yi, Chenguang ZhuInference-Time Sketches
CA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget Allocation
May 8, 2026James Petullo, Nianwen XueText-To-Sql Sql
CLIPer: Tailoring Diverse User Preference via Classifier-Guided Inference-Time Personalization
May 8, 2026Jinyan Su, Jinpeng Zhou, Claire Cardie +1Personalization Inference-Time
Inference-Time Refinement Closes the Synthetic-Real Gap in Tabular Diffusion
May 7, 2026Eugenio Lomurno, Filippo Balzarini, Francesco Benelle +2Synthetic Tabular Data Synthetic-To-Real Domain Gap
Power Distribution Bridges Sampling, Self-Reward RL, and Self-Distillation
May 6, 2026Akiyoshi Tomihari, Issei SatoUnsupervised On-Policy Self-Distillation Large Language Model Performance
Safety and accuracy follow different scaling laws in clinical large language models
May 5, 2026Sebastian Wind, Tri-Thien Nguyen, Jeta Sopa +9Large Language Model Safety Inference-Time
Visual Latents Know More Than They Say: Unsilencing Latent Reasoning in MLLMs
May 4, 2026Xin Zhang, Qiqi Tao, Jiawei Du +2Latent Visual Reasoning Efficient Latent Reasoning
The Model Knows, the Decoder Finds: Future Value Guided Particle Power Sampling
May 4, 2026Tu Nguyen, Matthieu Zimmer, Rasul Tutunov +2Inference-Time Power Method
Mitigating Multimodal LLMs Hallucinations via Relevance Propagation at Inference Time
May 3, 2026Itai Allouche, Joseph KeshetLarge Language Model Hallucination Multi-Modal Large Language Models
To Use AI as Dice of Possibilities with Timing Computation
May 1, 2026Jia Li, Vipin Kumar, Rui ZhangCausal Inferences Counterfactual Reasoning
CellxPert: Inference-Time MCMC Steering of a Multi-Omics Single-Cell Foundation Model for In-Silico Perturbation
Apr 30, 2026Andac Demir, Erik W. Anderson, Jeremy L. Jenkins +1Single-Cell Perturbation Prediction Multi-Omic Framework
Toward a Science of Intent: Closure Gaps and Delegation Envelopes for Open-World AI Agents
Apr 27, 2026Maximiliano Armesto, Christophe KolbArtificial Intelligence Agents Intelligence
PhysNote: Self-Knowledge Notes for Evolvable Physical Reasoning in Vision-Language Model
Apr 27, 2026Sinin Zhang, Yunfei Xie, Yuxuan Cheng +2Large Vision Language Models Visual Reasoning
AdapTime: Enabling Adaptive Temporal Reasoning in Large Language Models
Apr 27, 2026Yimin Deng, Yejing Wang, Zhenxi Lin +8Large Language Model Reasoning Temporal Knowledge Graphs
Pref-CTRL: Preference Driven LLM Alignment using Representation Editing
Apr 26, 2026Imranul Ashrafi, Inigo Jauregi Unanue, Massimo PiccardiLarge Language Model Alignment Novel Modular Learning Framework
Process Supervision via Verbal Critique Improves Reasoning in Large Language Models
Apr 23, 2026Hao-Yuan ChenLarge Language Model Reasoning Inference-Time
Adaptive Test-Time Compute Allocation with Evolving In-Context Demonstrations
Apr 22, 2026Bowen Zuo, Dongruo Zhou, Yinglun ZhuTest Time Inference-Time
Unsupervised Confidence Calibration for Reasoning LLMs from a Single Generation
Apr 21, 2026Thomas Zollo, Jimmy Wang, Richard ZemelConfidence Estimation Large Language Model Reasoning
TEMPO: Scaling Test-time Training for Large Reasoning Models
Apr 21, 2026Qingyang Zhang, Xinke Kong, Haitao Wu +7Inference-Time Large Reasoning Models
Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery
Apr 21, 2026Abhinav AgarwalVulnerability Detection & Repair Defect
Hive: A Multi-Agent Infrastructure for Algorithm- and Task-Level Scaling
Apr 19, 2026Zizhang Luo, Yuhao Luo, Youwei Xiao +3Rate Scaling Task-Level
RosettaSearch: Multi-Objective Inference-Time Search for Protein Sequence Design
Apr 19, 2026Meghana Kshirsagar, Allen Nie, Ching-An Cheng +5Protein Design Sequence Modeling
Inference-Time Temporal Probability Smoothing for Stable Video Segmentation with SAM2 under Weak Prompts
Apr 18, 2026Dawar Jyoti DekaVideo Object Segmentation Pixel-Level Prediction
The Cognitive Penalty: Ablating System 1 and System 2 Reasoning in Edge-Native SLMs for Decentralized Consensus
Apr 18, 2026Syed Muhammad Aqdas RizviConsensus-Based Protocol Decentralization

May 24, 2026 · cs.CLJ/K move · Enter open · S save

Inference Time Optimization with Confidence Dynamics

Yu Wang, Minghao Liu, Jiayun Wang, Jinrui Huang+2

Inference time optimization techniques, such as repeated sampling, have significantly advanced the reasoning capabilities of Large Language Models (LLMs). However, the critical role of model uncertainty remains largely underexplored in these optimization strategies. In this paper, we investigate the dynamics of confidence along reasoning trajectories and for first time reveal a surprising and unique pattern: correct answer traces tend to exhibit confidence improvement over time (positive confidence gain), while incorrect traces show attenuated or declining confidence as reasoning proceeds. Based on this observation, we propose Confidence Dynamic Gain (CDG) based voting, which incorporates how the confidence trajectory of the response evolves along the reasoning chain. Experiments across four open-source architectures (DeepSeek-R1, gpt-oss, Gemma-3, Qwen-QwQ) on the AIME24/25, HMMT25, and BRUMO25 benchmarks demonstrate that CDG yields a significant performance boost over baselines. These results demonstrate that our method provides a robust discriminative signal for improving answer selection in LLM reasoning. We also provide theoretical insights for this phenomenon. Code will be released at https://github.com/Accenture/CDG.git.

Inference-Time Deepseek

Open paper Ask about it PDF