Shortcuts

Follow this topic Ask about this topic

Recent momentum

+57%

11 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 Shortcuts.

Period ending 2026-09-14

3 new papers

A weekly snapshot of new work published in Shortcuts.

Period ending 2026-09-07

4 new papers

A weekly snapshot of new work published in Shortcuts.

58 papers

Latest in Shortcuts

Open your feed →

Bad Genius: Counterfactual-Guided Harness Evolution Beyond Task-Specific Shortcuts
Sep 16, 2026Guojun Zhu, Xunheng Huang, Peng Yin +3Agentic Evaluations Adversarial Evaluation
Spurious Tool Use: When RL Agents Learn the Wrong Reason to Act
Sep 14, 2026Yiwei Yang, Haoxiang Zhang, Bingbing Wen +6Fewer Tool-Call Errors Large Language Model Agents
Breaking the Vision-Action Shortcut: Latent Interface Training for Generalizable Robotics Foundation Models
Sep 14, 2026Jianman Lin, Shailesh Shailesh, Zhongyi Luo +1Vision-Language-Action Models End-Effector Pose
Are You Learning Biological Signal or Shortcuts? Auditing and Mitigating Bias in Protein-Protein Interaction Datasets
Sep 9, 2026Judith Bernett, Anton Spannagl, Joel Ås +2Protein Data Bank Shortcuts
Prevalence calibration as shortcut mitigation
Sep 7, 2026Mohamed Amine Kina, Eike PetersenShortcuts Area Under The Receiver Operating Characteristic Curve
Mitigating Shortcut Learning: Texture-Penalized Prototype Networks
Sep 7, 2026Akshay Anilkumar Girija, Elena Hoemann, Frank Köster +1Convolutional Neural Networks Shortcuts
MedQA-MM: Shortcuts Behind Medical Visual Reasoning
Sep 3, 2026Benlu Wang, Yifan Zhang, Jiaqing Yu +7Medical Visual Question Answering Multimodal Clinical Data
HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolution
Sep 1, 2026Wen Jiang, Mingmin Chu, Yimeng Tian +6Self-Evolution Agent Harness
BAITBENCH: Measuring Agent Reward Hacking with Optional Shortcuts Planted in ML Tasks
Aug 31, 2026Pradyumna Shyama Prasad, Meiri Anto, Leon Eshuijs +3Agentic Benchmarks Large Language Model Agents
GUIDE: Guiding Internal Evidence with Language Instructions
Aug 31, 2026Soyeon Caren Han, Hyunsuk Chung, Jinwoo Kim +2Relation-Conditioned Evidence Encoder Unified Evaluation
ICON Decomposition: Auditing deep neural networks for shortcuts by decomposing layer-wise representations using concepts
Aug 26, 2026Roshan Prakash Rane, Marco Simnacher, Manuel Pfeuffer +7Explainability Shortcuts
Look What the Probes Dragged In! Real-World Chest X-ray Shortcuts in MedCLIP
Aug 12, 2026Nikolette Pedersen, Regitze Sydendal, Veronika Cheplygina +1Chest X-Ray Chest Radiography
UNMASK: Discovering and Causally Verifying Spurious Shortcuts in Text Classifiers
Aug 10, 2026Chidaksh Ravuru, Shashank SrivastavaSpurious Correlations Unlabeled Data
UNSPECIFIC: General Constraint Synthesis for Breaking Copy-and-Paste Shortcut in LLM Instruction Following
Aug 10, 2026Jeet Sharma, Balpreet Kaur, Jeremiah Hong +2Instruction-Tuned Models Instruction
Invisible Shortcuts: Why Vision Encoders Know Your Camera
Aug 5, 2026Vladan Stojnić, Ryan Ramos, Giorgos Kordopatis-Zilos +2Vision Encoders Vision Foundation Models
When Refusal Looks Safe: The Refusal-Cue Shortcut in Safety Guard Models
Aug 4, 2026Yu Feng, Chunting Zang, Chen Shen +4Refusals Guard
Right Answer, Wrong Method: Shortcut Hacking Misleads the Evaluation of LLM Reasoning on Frontier Science Benchmarks
Aug 3, 2026Xuan Ren, Weiqi Zhai, Tianle Pu +4Reasoning Benchmark Hacking
Analysis of the Shortcut Learning and Clever Hans Effect in CNN based ECG Image Classification
Jul 27, 2026Abhay Kumar Pathak, Mrityunjay Chaubey, Manjari Gupta +1Electrocardiogram Classification Atrial Fibrillation
Alleviating Regional Shortcuts for Few-Shot Class-Incremental Learning
Jul 24, 2026Haichen Zhou, Yazhe Lyu, Yixiong Zou +2Domain Incremental Learning Few-Shot Learning
Style over Substance: A Shortcut Audit of Emotion-Description Preference Evaluation
Jul 20, 2026Jiabing Yang, Yixiang Chen, Yuan Xu +6Emotion Recognition Multimodal Evaluation
Controlling Implicit Shortcut Reliance in L2 Spoken English Auto-markers
Jul 17, 2026Shilin Gao, Mark J. F. Gales, Kate M. KnillLinguistics English
Genre Bias or Aesthetic Perception? Identifying and Mitigating Shortcut Learning in Music Evaluation
Jul 15, 2026Yizhou Zhang, Wangjin Zhou, Yi Zhao +3Aesthetics Mean Opinion Scores
A Shortcut to Statistically Steady-State Turbulence with Flow Matching
Jul 14, 2026Gianluca Galletti, Gerald Gutenbrunner, William Hornsby +5Turbulence Shallow Water Equations
Artificial Foveated Perception for Mitigating Shortcut Learning in Robotic Foundation Models
Jul 12, 2026Xiatao Sun, Yuan Zhuang, Mateo Sanchez Lopez Negrete +9Robotic Perception Perceptual Understanding
Association Restoration Test: Revealing Restorable Shortcuts after Unlearning
Jul 7, 2026Amy Lu, Changxiu JiShortcuts Unlearning Aims
Shortcut Learning in Legal Judgment Prediction: Empirical Evidence from the UK Employment Tribunal
Jul 5, 2026Joe Watson, Joana Ribeiro de Faria, Marcus Tomalin +6Predictive Law Clinical Prediction
An Intervention-Based Framework for Shortcut Diagnosis in Spoofing Countermeasures
Jul 3, 2026Santiago Rubio, Pilar Bello, Dayana Ribas +3Spoofed Speech Deepfake Detection
The Moving Eye: Enhancing VLA Spatial Generalization via Hybrid Dynamic Data Collection
Jul 2, 2026Jincheng Tang, Yilong Zhu, Zhengyuan Xie +2Vision-Language-Action Models Robotic Datasets
Dataset Biases and Shortcut Learning in Motion-Based AI-Generated Video Detection
Jul 1, 2026Joren Michels, Lode Jorissen, Nick MichielsAi-Generated Image Detection Implicit Bias
Modal CEGAR-tableaux with RECAR and resolution-based SAT-shortcuts
Jun 30, 2026Rajeev Goré, Cormac KikkertSatisfiability Theorem
SGD Provably Prioritizes a Shortcut Spurious Feature in the XOR Model
Jun 29, 2026Tyler LaBonte, Vidya MuthukumarFeature Learning Rectified Linear Unit Networks
To Reason or to Fabricate: Reasoning Without Shortcuts via Hint-Anchored Pairwise Aggregation
Jun 28, 2026Jiuheng Lin, Chen Zhang, Yansong FengProcess Reward Modeling Shortcuts
Dismantling Pathological Shortcuts: A Causal Framework for Faithful LVLM Decoding
Jun 25, 2026Liu Yu, Can Chen, Ping Kuang +3Large Vision Language Models Hallucinations
Cross-View Variance Correlation in Path-Traced Stereo:A Hidden Shortcut in Synthetic Training Data
Jun 24, 2026Po-Ting LinStereo Vision Cross-View
Breaking Shortcut Learning for Cross-Trial EEG-Guided Target Speech Extraction via Two-Stage Training
Jun 23, 2026Wonchul Shin, Inyong Choi, Kyogu LeeElectroencephalography Spatial Super-Resolution Model Training
The Watermark Shortcut: How Provenance Marking Sabotages Audio Deepfake Detection
Jun 22, 2026Nicolas M. Müller, Pascal DebusAudio Deepfake Detection Watermarking
When Does a Video-Language Model Stop Watching? Reward Strength Controls the Formation and Reversal of Visual Shortcuts in Multimodal RLVR
Jun 20, 2026Zekun XuReinforcement Learning With Verifiable Reward Video-Language Models
From Shortcuts to Reasoning: Robust Post-Training of Theory of Mind with Reinforcement Learning
Jun 8, 2026Jike Zhong, Yuxiang Lai, Ming Li +5Theory-Of-Mind Reasoning Reinforcement Fine-Tuning
DynaCF: Mitigating Shortcut Learning in Reward Models via Dynamic Counterfactual Sensitivity
Jun 8, 2026Fengyuan Liu, Yongliang Miao, Zirui He +3Process Reward Modeling Counterfactual Rollouts
Twelve quick tips for designing AI-driven HPC workflows
Jun 5, 2026Jamie J. AlnasirHigh-Performance Computing Scientific Workflows
Invariant Gradient Alignment for Robust Reasoning Distillation
Jun 3, 2026Zehua Cheng, Wei Dai, Jiahao SunShortcuts
Low-Frequency Shortcuts in Texture-Driven Visual Learning
Jun 2, 2026Utku Şirin, Cathy Hou, David Alvarez-Melis +1Low-Frequency Cues Feature Learning
Suppressing Forgery-Specific Shortcuts for Generalizable Deepfake Detection
Jun 1, 2026Yihui Wang, Yonghui Yang, Jilong Liu +3Explainable Deepfake Detection Deepfake Detection
Shortcut to Nowhere: Demystifying Deep Spurious Regression
Jun 1, 2026Guanrong Xu, Jessica Li, Hao Wang +1Spurious Correlations Latent Confounders
Shortcuts in the Tail: Debiasing via Post-Hoc Spectral Compression of Fine-Tuning Updates
May 29, 2026Edward Sun, Dmitrii TroitskiiShortcuts Top-K
The Confidence Shortcut: A Reasoning Failure Mode of Masked Diffusion Models
May 27, 2026Dueun Kim, Albert NoMasked Diffusion Language Models Training-Inference Mismatch
From paper to benchmark: agentic, framework-based reproduction of under-specified methods in machine health intelligence
May 27, 2026Raffael Theiler, Ludovico Comito, David Leko +3Reproducibility Mle-Bench Lite
Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning
May 22, 2026Jinghan Jia, Joe Benton, Eric EasleyExplanation Faithfulness Faithfulness
Learning Spatiotemporal Sensitivity in Video LLMs via Counterfactual Reinforcement Learning
May 21, 2026Dazhao Du, Jian Liu, Jialong Qin +7Video-Language Models Counterfactual Rollouts
Learning to Think in Physics: Breaking Shortcut Learning in Scientific Diffusion via Representation Alignment
May 20, 2026Haozhe Jia, Pengyu Yin, Wenshuo Chen +6Partial Differential Equation Benchmarks First-Principles Calculation
SpurAudio: A Benchmark for Studying Shortcut Learning in Few-Shot Audio Classification
May 13, 2026Giries Abu Ayoub, Morad Tukan, Loay MualemSpeech Separation Audio
Shortcut Solutions Learned by Transformers Impair Continual Compositional Reasoning
May 6, 2026William T. Redman, Erik C. Johnson, Brian RobinsonTransformer Architectures Efficient Continual Learning
Reproducing Complex Set-Compositional Information Retrieval
May 5, 2026Vincent Degenhart, Dewi Timman, Arjen P. de Vries +2Retrievers Shortcuts
Deciphering Shortcut Learning from an Evolutionary Game Theory Perspective
May 4, 2026Xiayang Li, Kuo Gai, Shihua ZhangStochastic Gradient Descent Shortcuts
Beyond Shortcuts: Mitigating Visual Illusions in Frozen VLMs via Qualitative Reasoning
Apr 29, 2026Hao Guo, Fei Wang, Junjie Chen +4Frozen Vision-Language Models Large Vision Language Models
Cross-Modal Attention Analysis and Optimization in Vision-Language Models: A Study on Visual Reliability
Apr 19, 2026Lijie ZhouCross-Modal Attention Cross-Modal Learning
Chain-of-Thought Degrades Visual Spatial Reasoning Capabilities of Multimodal LLMs
Apr 17, 2026Sai Srinivas Kancheti, Aditya Sanjiv Kanade, Vineeth N. Balasubramanian +1Spatial Reasoning Embodied Spatial Intelligence
Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition
Jan 22, 2026Geo Ahn, Inwoong Lee, Taeoh Kim +3Open-Vocabulary Action Recognition Shortcuts

Sep 16, 2026 · cs.AIJ/K move · Enter open · S save

Bad Genius: Counterfactual-Guided Harness Evolution Beyond Task-Specific Shortcuts

Guojun Zhu, Xunheng Huang, Peng Yin, Jiahui Xie+2

Reliable agent evaluation is complicated by automatic harness optimization, which repeatedly uses a released benchmark

B_{\mathrm{rel}}

to guide a Proposer that edits prompts, memory, retrieval, tools, and control code around a fixed target agent. Task holdout varies semantic tasks but leaves the benchmark protocol fixed, so a "bad genius" Proposer can produce a cheating harness whose released-benchmark gain depends on a benchmark-wide shortcut. We introduce Counterfactual Harness Search and Evolution (CHASE), which casts harness evolution as constraint generation over validity-preserving benchmark counterfactuals. After each Proposer update, a Challenger searches for an executable protocol transformation with large gain destruction. A validity firewall checks that task semantics are preserved, while a confirmation set determines whether the counterfactual enters a finite archive. We formalize an exact shortcut-neutralized benchmark

B_0

and establish statistical guarantees linking finite counterfactual archives to

B_0

and characterizing sequential Challenger search. We evaluate CHASE on a synthetic benchmark and on OfficeQA, where CHASE retains strong released-benchmark gains while substantially reducing gain destruction under valid protocol changes.

Agentic Evaluations Adversarial Evaluation Counterfactual Reasoning Evolution Shortcuts

Open paper Ask about it PDF