Artificial Intelligence

Papers filed under cs.AI on arXiv, each one already summarized by Paperlayer. Open any of them to read the summary beside the original PDF, with every point linked to the line, figure, or table it came from.

Search paper metadata (including unsummarized papers)

21,721 to 21,780 of 27,520

Reward-Guided Speculative Decoding for Efficient LLM Reasoning
Baohao Liao, Yuhui Xu, Hanze Dong +5
cs.CLcs.AIarXiv:2501.19324v32025
The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution
Chen Qian, Peng Wang, Dongrui Liu +10
cs.AIcs.CLarXiv:2601.15075v22026
LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs
Gianluca Barmina, Peter Schneider-Kamp, Lukas Galke Poech
cs.CLcs.AIarXiv:2606.06286v12026
Subliminal Learning: Language models transmit behavioral traits via hidden signals in data
Alex Cloud, Minh Le, James Chua +5
cs.LGcs.AIarXiv:2507.14805v12025
FilterNet: Harnessing Frequency Filters for Time Series Forecasting
Kun Yi, Jingru Fei, Qi Zhang +4
cs.LGcs.AIeess.SParXiv:2411.01623v22024
SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards
Hunar Batra, Haoqin Tu, Hardy Chen +3
cs.CVcs.AIcs.CLarXiv:2511.07403v22025
Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems
Jianing Zhu, Yeonju Ro, John Robertson +5
cs.AIcs.CLcs.MAarXiv:2605.26302v12026
Visual Framing for News Stance Detection via Image Generation
Dahyun Lee, Jiyoung Han, Kunwoo Park
cs.CLcs.AIcs.CVarXiv:2609.00685v12026
DefaultGNN: A Dual-Perspective GNN Framework for Predicting Corporate Default from Buyer-Seller Transaction Networks
Junghoon Kim, Hyunsung Kim, Seungyoon Choi +4
cs.LGcs.AIarXiv:2609.25542v12026
Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models
Siddharth Karamcheti, Suraj Nair, Ashwin Balakrishna +3
cs.CVcs.AIcs.CLarXiv:2402.07865v22024
Llemma: An Open Language Model For Mathematics
Zhangir Azerbayev, Hailey Schoelkopf, Keiran Paster +6
cs.CLcs.AIcs.LOarXiv:2310.10631v32023
A Time-Based Readout for Vector-Matrix Multiplication in Fully Analog Memristive SNNs
Elia Mateu-Barriendos, Álvaro Gómez-Pau, Josep Rius +3
cs.ETcs.AIcs.ARarXiv:2609.11713v12026
Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems
Yihang Chen, Yuxiang Chen, Yuxuan Huang +3
cs.AIarXiv:2609.02750v12026
A Tale of Tails: Model Collapse as a Change of Scaling Laws
Elvis Dohmatob, Yunzhen Feng, Pu Yang +2
cs.LGcs.AIcs.CLarXiv:2402.07043v22024
When Agents Disagree: Bayesian Backward Reasoning as a Label-Free Anchor for Multi-Agent Collective Decision-Making
Ken Chen, Wei Wang, Sachith Seneviratne +2
cs.AIcs.MAarXiv:2609.11709v12026
Abstraction Agent
Boning Li, Longbo Huang
cs.MAcs.AIcs.CLarXiv:2609.04303v12026
Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models
Guanting Dong, Keming Lu, Chengpeng Li +4
cs.CLcs.AIcs.LGarXiv:2406.13542v32024
InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models
Hao Li, Xiaogeng Liu
cs.CLcs.AIcs.CRarXiv:2410.22770v32024
SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
Haozhan Li, Yuxin Zuo, Jiale Yu +18
cs.ROcs.AIcs.CLarXiv:2509.09674v12025
StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing
Zhijie Zheng, Yu Li, Chen Qian +5
cs.AIcs.CRarXiv:2608.24777v12026
Follow the Winners: Conservative Policy Improvement with the Cross-Entropy Method for Critic-Free RFT
Joery Ariën de Vries, Neil David Lawrence, Zhenwen Dai
cs.LGcs.AIarXiv:2610.03361v12026
HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding
Haowei Zhang, Shudong Yang, Jinlan Fu +2
cs.CVcs.AIcs.CLarXiv:2601.14724v42026
IONet: Learning to Cure the Curse of Drift in Inertial Odometry
Changhao Chen, Xiaoxuan Lu, Andrew Markham +1
cs.ROcs.AIcs.CVarXiv:1802.02209v12018
Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs
Andries Smit, Paul Duckworth, Nathan Grinsztajn +2
cs.CLcs.AIarXiv:2311.17371v32023
Commonsense Knowledge Base Completion with Structural and Semantic Context
Chaitanya Malaviya, Chandra Bhagavatula, Antoine Bosselut +1
cs.CLcs.AIarXiv:1910.02915v22019
West-WRF AI 2-km: High-Resolution Prediction of Integrated Vapor Transport and Precipitation
Nazak Rouzegari, Vesta Afzali Gorooh, Agniv Sengupta +6
physics.ao-phcs.AIarXiv:2609.25512v12026
Exploring the Roles of Large Language Models in Reshaping Transportation Systems: A Survey, Framework, and Roadmap
Tong Nie, Jian Sun, Wei Ma
cs.AIarXiv:2503.21411v22025
Diffusion Model Alignment Using Direct Preference Optimization
Bram Wallace, Meihua Dang, Rafael Rafailov +7
cs.CVcs.AIcs.GRarXiv:2311.12908v12023
Decision Theory with Prospect Interference and Entanglement
V. I. Yukalov, D. Sornette
math-phcs.AIphysics.soc-pharXiv:1102.2738v12011
X-RACE: XAI-assisted Recurrent neural network Attribution for Channel Estimation
Abdul Karim Gizzini, Yahia Medjahdi
eess.SPcs.AIarXiv:2609.11211v12026
MMErroR: A Benchmark for Erroneous Reasoning in Vision-Language Models
Yang Shi, Yifeng Xie, Minzhe Guo +6
cs.CVcs.AIcs.LGarXiv:2601.03331v22026
Swift4D:Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstruction of dynamic scene
Jiahao Wu, Rui Peng, Zhiyan Wang +5
cs.CVcs.AIarXiv:2503.12307v12025
Cordial Learning: Distributed Training with Correlated Data
Sarah Shitrit, Ilai Bistritz
cs.LGcs.AIarXiv:2610.03330v12026
Evidence Blindness in Direct Corpus Interaction: Persistent Navigation with AtlasNav
Hongyu Guo, Zhiyu Zheng, Zhao Cao
cs.AIarXiv:2608.24764v12026
Driven by Compression Progress: A Simple Principle Explains Essential Aspects of Subjective Beauty, Novelty, Surprise, Interestingness, Attention, Curiosity, Creativity, Art, Science, Music, Jokes
Juergen Schmidhuber
cs.AIcs.NEarXiv:0812.4360v22008
AutoWorldModel-Bench: A State-Centric Benchmark for Automated World-Model Research
Marjan Moodi, Xuankang Zhu, Fernando De Mesentier Silva +2
cs.AIarXiv:2608.11216v12026
From Pixel to Coding: Evaluating the Figure Reproduction Capabilities of MLLMs
Zijian Chen, Zhengyu Chen, Bohan Liang +7
cs.CVcs.AIarXiv:2610.10066v12026
DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos
Wenbo Hu, Xiangjun Gao, Xiaoyu Li +5
cs.CVcs.AIcs.GRarXiv:2409.02095v22024
Rapid Locomotion via Reinforcement Learning
Gabriel B Margolis, Ge Yang, Kartik Paigwar +2
cs.ROcs.AIcs.LGarXiv:2205.02824v12022
SPaRC: A Spatial Pathfinding Reasoning Challenge
Lars Benedikt Kaesberg, Jan Philip Wahle, Terry Ruas +1
cs.AIcs.CLarXiv:2505.16686v22025
WorldTree: A Corpus of Explanation Graphs for Elementary Science Questions supporting Multi-Hop Inference
Peter A. Jansen, Elizabeth Wainwright, Steven Marmorstein +1
cs.CLcs.AIcs.IRarXiv:1802.03052v12018
Class-RAG: Real-Time Content Moderation with Retrieval Augmented Generation
Jianfa Chen, Emily Shen, Trupti Bavalatti +10
cs.AIcs.CLarXiv:2410.14881v22024
ProtAgents: Protein discovery via large language model multi-agent collaborations combining physics and machine learning
A. Ghafarollahi, M. J. Buehler
cond-mat.softcs.AIcs.CLarXiv:2402.04268v12024
Flow caching for autoregressive video generation
Yuexiao Ma, Xuzhe Zheng, Jing Xu +9
cs.CVcs.AIarXiv:2602.10825v12026
Synthesizing Post-Training Data for LLMs through Multi-Agent Simulation
Shuo Tang, Xianghe Pang, Zexi Liu +6
cs.AIcs.CLarXiv:2410.14251v22024
ReToken: One Token to Improve Vision-Language Models for Visual Retrieval
Yao Xiao, Reuben Tan, Zhen Zhu +3
cs.CVcs.AIcs.LGarXiv:2607.28627v12026
MixLLM: Dynamic Routing in Mixed Large Language Models
Xinyuan Wang, Yanchi Liu, Wei Cheng +5
cs.CLcs.AIcs.DBarXiv:2502.18482v12025
ValueGraph: Value-Signal Guided Graph Pre-training for Contextualized User Representation
Yitong Han, Wei Gao, Yi Zhao +3
cs.CLcs.AIcs.LGarXiv:2609.00057v12026
IQ-Learn: Inverse soft-Q Learning for Imitation
Divyansh Garg, Shuvam Chakraborty, Chris Cundy +3
cs.LGcs.AIarXiv:2106.12142v42021
Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design
Chenyu Wang, Masatoshi Uehara, Yichun He +7
cs.LGcs.AIarXiv:2410.13643v22024
UpgradeBench: A Decision-Centric Benchmark for Upgrading Fine-Tuned LLM Specialists
Ye Chen, Weining Zhang
cs.AIarXiv:2608.20918v12026
MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning
Ehud Karpas, Omri Abend, Yonatan Belinkov +14
cs.CLcs.AIarXiv:2205.00445v12022
SDPAD: A Fully Spike-Driven Pipeline for End-to-End Autonomous Driving
Chengjun Zhang, Yuhao Zhang, Jie Yang +1
cs.ROcs.AIarXiv:2610.11583v12026
130k Lines of Formal Topology in Two Weeks: Simple and Cheap Autoformalization for Everyone?
Josef Urban
cs.LOcs.AIcs.SCarXiv:2601.03298v12026
Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements
Jingyu Zhang, Ahmed Elgohary, Ahmed Magooda +2
cs.CLcs.AIarXiv:2410.08968v22024
PrivateHub: Contrastive Diffusion Model for Private Sensor-Intensive Environment Data Generation
Jiechao Gao, Yuandong Pan, Jie Wang +2
cs.CRcs.AIarXiv:2609.02958v12026
KV$^2$: A Self-Refining KV Cache
Johannes Wesch, Danni Liu, Jan Niehues
cs.AIcs.CLarXiv:2610.03198v12026
Beacon: Single-Turn Diagnosis and Mitigation of Latent Sycophancy in Large Language Models
Sanskar Pandey, Ruhaan Chopra, Angkul Puniya +1
cs.CLcs.AIarXiv:2510.16727v22025
Tracing Stereotypes from Representation to Output in Multilingual LLMs
Ariun-Erdene Tumurchuluun, Yusser Al Ghussin, Pinzhen Chen +2
cs.CLcs.AIarXiv:2609.08322v12026
Buyer Artificial Intelligence-Enabled Environmental Governance and Supplier Environmental Controversies: An Organizational Information Processing and Signaling
Yongchao Martin Ma, Xinya Guan
cs.CYcs.AIstat.AParXiv:2609.11391v12026

Artificial Intelligence

Reward-Guided Speculative Decoding for Efficient LLM Reasoning

The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution

LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs

Subliminal Learning: Language models transmit behavioral traits via hidden signals in data

FilterNet: Harnessing Frequency Filters for Time Series Forecasting

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards

Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems

Visual Framing for News Stance Detection via Image Generation

DefaultGNN: A Dual-Perspective GNN Framework for Predicting Corporate Default from Buyer-Seller Transaction Networks

Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models

Llemma: An Open Language Model For Mathematics

A Time-Based Readout for Vector-Matrix Multiplication in Fully Analog Memristive SNNs

Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems

A Tale of Tails: Model Collapse as a Change of Scaling Laws

When Agents Disagree: Bayesian Backward Reasoning as a Label-Free Anchor for Multi-Agent Collective Decision-Making

Abstraction Agent

Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models

InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models

SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing

Follow the Winners: Conservative Policy Improvement with the Cross-Entropy Method for Critic-Free RFT

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding

IONet: Learning to Cure the Curse of Drift in Inertial Odometry

Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs

Commonsense Knowledge Base Completion with Structural and Semantic Context

West-WRF AI 2-km: High-Resolution Prediction of Integrated Vapor Transport and Precipitation

Exploring the Roles of Large Language Models in Reshaping Transportation Systems: A Survey, Framework, and Roadmap

Diffusion Model Alignment Using Direct Preference Optimization

Decision Theory with Prospect Interference and Entanglement

X-RACE: XAI-assisted Recurrent neural network Attribution for Channel Estimation

MMErroR: A Benchmark for Erroneous Reasoning in Vision-Language Models

Swift4D:Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstruction of dynamic scene

Cordial Learning: Distributed Training with Correlated Data

Evidence Blindness in Direct Corpus Interaction: Persistent Navigation with AtlasNav

Driven by Compression Progress: A Simple Principle Explains Essential Aspects of Subjective Beauty, Novelty, Surprise, Interestingness, Attention, Curiosity, Creativity, Art, Science, Music, Jokes

AutoWorldModel-Bench: A State-Centric Benchmark for Automated World-Model Research

From Pixel to Coding: Evaluating the Figure Reproduction Capabilities of MLLMs

DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos

Rapid Locomotion via Reinforcement Learning

SPaRC: A Spatial Pathfinding Reasoning Challenge

WorldTree: A Corpus of Explanation Graphs for Elementary Science Questions supporting Multi-Hop Inference

Class-RAG: Real-Time Content Moderation with Retrieval Augmented Generation

ProtAgents: Protein discovery via large language model multi-agent collaborations combining physics and machine learning

Flow caching for autoregressive video generation

Synthesizing Post-Training Data for LLMs through Multi-Agent Simulation

ReToken: One Token to Improve Vision-Language Models for Visual Retrieval

MixLLM: Dynamic Routing in Mixed Large Language Models

ValueGraph: Value-Signal Guided Graph Pre-training for Contextualized User Representation

IQ-Learn: Inverse soft-Q Learning for Imitation

Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design

UpgradeBench: A Decision-Centric Benchmark for Upgrading Fine-Tuned LLM Specialists

MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning

SDPAD: A Fully Spike-Driven Pipeline for End-to-End Autonomous Driving

130k Lines of Formal Topology in Two Weeks: Simple and Cheap Autoformalization for Everyone?

Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements

PrivateHub: Contrastive Diffusion Model for Private Sensor-Intensive Environment Data Generation

KV$^2$: A Self-Refining KV Cache

Beacon: Single-Turn Diagnosis and Mitigation of Latent Sycophancy in Large Language Models

Tracing Stereotypes from Representation to Output in Multilingual LLMs

Buyer Artificial Intelligence-Enabled Environmental Governance and Supplier Environmental Controversies: An Organizational Information Processing and Signaling