Imitation

Follow this topic Ask about this topic

Recent momentum

-77%

3 papers in the last 28 days · 0.1% 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 2026-09-14

1 new paper

A weekly snapshot of new work published in Imitation.

Period ending 2026-09-07

2 new papers

A weekly snapshot of new work published in Imitation.

69 papers

Latest in Imitation

Open your feed →

Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails
Sep 8, 2026Zhou Yu, Bin Bi, Shiva Kumar Pentyala +8Agent Harness On-Policy
Mechanism Design for Alignment and Control
Sep 1, 2026Dirk Bergemann, Andrew Koh, Stephen MorrisArtificial Intelligence Alignment Artificial Intelligence Agents
Does Imitation Learning Preserve Temporal Robustness in Dexterous Manipulation? An Expert-Learner Comparison Across Task Execution Speeds
Sep 1, 2026Clinton Enwerem, John S. Baras, Calin BeltaImitation Learning Robotic Manipulation Policies
Intent Speaks Louder: Controllable User Simulation Beyond Response Imitation
Aug 10, 2026Bo Wang, Ruixing Zhang, Yunqi Liu +4Social Simulations Imitation
Imaginative Generative AI: Crossing the Entropy Wall into Worlds Beyond Imitation
Aug 10, 2026Farzan Farnia, Hossein Goli, Amin GohariImagination Imitation
SpeedTuning: Speeding Up Policy Execution with Lightweight Reinforcement Learning
Aug 10, 2026David D. Yuan, Tony Z. Zhao, Kaylee Burns +1Robotic Manipulation Policies Robotic Manipulation
VIDP: Variable Impedance Diffusion Policy for Compliant Robot Manipulation from Diverse Demonstrations
Aug 6, 2026Hisham Khalil, Neil Fernandes, Thomas M. Kwok +2Impedance Control Robotic Manipulation
Turing's First Imitation Game: Design Concepts and a Human-Approximates-Machine Reading
Aug 6, 2026Sharon Temtsin, Christoph BartneckCounter Turing Test Imitation
PRIMAL3: Pathfinding via Reinforcement and Imitation Multi-Agent Learning - Leveraging LaCAM3
Aug 5, 2026Chengyang He, Tanishq Duhan, Gadiel Sznaier Camps +6Multi-Agent Path Finding Multi-Agent Reinforcement Learning
ValueFormer: A Causal Transformer Value Function with Stage-Aware Labels for Semi-Autonomous Vision-Language-Action Policies
Aug 3, 2026Inkyu Sa, Konstantin Stulov, Rajat BhageriaVision-Language-Action Actor--Critic Training
TWINS: A Tactile Wearable Isomorphic Arm Networked System for Contact-Rich Manipulation Learning
Aug 3, 2026Takahide Kitamura, Masaki Murooka, Natsuki Yamanobe +1Tactile Sensing Contact-Rich Manipulation
Creative Transformation in Literary Texts: Modelling Change Across Representational Levels
Jul 30, 2026Ioana-Roxana Boriceanu, Liviu P. DinuCreativity Literature
LM-GRASP: Instance-Specific Language Models for Combinatorial Construction via Online Imitation Learning
Jul 30, 2026Mohand Mezmaz, Grégoire DanoyMetaheuristics Combinations
LeAct: Learning to Reason from Expert Actions
Jul 23, 2026Ziran Yang, Chengshuai Shi, Raj Ghugare +3Reinforcement Learning Base-To-Thinking Gap Full-Context Baselines
When Reasoning Narrows the Move: Diversity Collapse in LLM Game Play
Jul 21, 2026Junyi Sha, Renfei Tan, David Simchi-LeviSupervised Fine-Tuning Output and Model Diversity
Imitation of Arm Gestures by the Semi-Humanoid Robot NICO
Jul 20, 2026Anastasiya Ihnatovich, Igor FarkašHumanoid Robots Human-Robot Interaction
Distributionally Robust and Safe Imitation Learning
Jul 15, 2026Ahmed Aboudonia, Naira HovakimyanImitation Learning Distributional Reinforcement Learning
Agentic-DPO: From Imitation to Agentic Policy Optimization on Expert Trajectories
Jul 12, 2026Yixiong Chen, Alan YuilleAgentic Reinforcement Learning Imitation
Compete Then Collaborate: Frontier AI Teachers Build a Verifiable Curriculum to Improve a Coding Student Beyond Imitation
Jul 9, 2026Miseong Shawn KimCurriculum Multi-Teacher Distillation
Feedback Manipulation Regularization: Enabling Offline Agent Alignment for Imitation Learning
Jul 8, 2026Benjamin Poole, Minwoo LeeImitation Learning Reinforcement Learning From Human Feedback
Shift & Drift: A Zero-Shot Benchmark for Generalizable and Robust Autonomous Driving Motion Planning
Jul 8, 2026Alessandro Canevaro, Hang Yu, Julian Schmidt +5Autonomous Driving Simulation Distribution Shifts
Language-Critique Imitation Learning from Suboptimal Demonstrations
Jul 1, 2026Chih-Han Yang, Dai-Jie Wu, Yun-Ping Huang +3Imitation Learning Imitation
Active-GRPO: Adaptive Imitation and Self-Improving Reasoning for Molecular Optimization
Jul 1, 2026Xuefeng Liu, Mingxuan Cao, Qinan Huang +3Molecular Optimization Grokipedia
The Label Imitation Game: Turing Test Network for Zero-Shot Pseudo-Label Pruning
Jun 29, 2026Brent A. Griffin, Jason J. CorsoPseudo-Labeling Pre-Trained Vision-Language Models
Humanoid-DART: Humanoid Loco-Manipulation using Diffusion-guided Augmentation through Relabeling and Tracking
Jun 25, 2026Pranav Debbad, Kanish Thiagarajan, Victor Dhédin +2Humanoid Loco-Manipulation Goal-Conditioned Reinforcement Learning
Beyond Monotonic Progress: Retry-Supervised Value Learning for Robot Imitation
Jun 23, 2026Xinyao Qin, Junjie Lu, Kaixin Wang +7Robot Imitation Learning Imitation
Learning to See While Learning to Act: Diffusion Models for Active Perception in Robot Imitation
Jun 22, 2026Kuancheng Wang, Vaibhav Saxena, Shuo Cheng +2Imitation Action-Conditioned Prediction
Imitation from Heterogeneous Demonstrations using Grounded Latent-Action World Models
Jun 19, 2026Tianyou Wang, Anson Lei, Joe Watson +1Latent World Action Models Imitation Learning
VFILC: Accurate Frequency Extrapolations in Imitation Learning via Sampling Frequency ILC
Jun 18, 2026Nozomu Masuya, Toshiaki Tsuji, Sho SakainoImitation Learning Imitation
CADET: Physics-Grounded Causal Auditing and Training-Free Deconfounding of End-to-End Driving Planners
Jun 12, 2026Zikun GuoAutonomous Driving Causal Intervention
From Imitation to Alignment: Human-Preference Flow Policies for Long-Horizon Sidewalk Navigation
Jun 10, 2026Honglin He, Zhizheng Liu, Yukai Ma +1Imitation Learning Perception-Action Loop
Ambient Diffusion Policy: Imitation Learning from Suboptimal Data in Robotics
Jun 10, 2026Adam Wei, Nicholas Pfaff, Thomas Cohn +4Diffusion Policies Imitation
Fourier Features Let Agents Learn High Precision Policies with Imitation Learning
Jun 10, 2026Balázs Gyenes, Emiliyan Gospodinov, Jan Frieling +5Point Clouds Imitation Learning
VOID: Defeating Unauthorized Mimicry in Latent Diffusion Models
Jun 10, 2026Chunlin Qiu, Ang Li, Tianxiao Huang +7Latent Diffusion Model Fréchet Inception Distance
Speculative Rollback Correction for Quality-Diverse Web Agent Imitation
Jun 10, 2026Longkun Hao, Hongyu Lin, Hao Li +10Imitation Learning Self-Improving Agents
Beyond Absolute Imitation: Anchored Residual Guidance for Privileged On-Policy Distillation
Jun 9, 2026Wenhao ZhangOn-Policy Distillation Teacher
Difference-Aware Retrieval Policies for Imitation Learning
Jun 8, 2026Quinn Pfeifer, Ethan Pronovost, Paarth Shah +3Imitation Learning Behavior Cloning
DexPIE: Stable Dexterous Policy Improvement from Real-World Experience
Jun 8, 2026Ruizhe Liao, Wenrui Chen, Liangji Zeng +4Robotic Manipulation Policies Real-World Mobile Manipulation Tasks
When Offline Selectors Cannot Beat the Best Single Model: A Diagnostic Study on edX Dropout Prediction
Jun 2, 2026Tyler Crosse, Alan Nadelsticher Ruvalcaba, Dustin Khang LeDuc +3Predictors Dropout
Training-Free Imitation Learning with Closed-Form Diffusion Policies
May 31, 2026Raghav Mishra, Ian R. ManchesterDiffusion Policies Imitation Learning
Beyond Independent Manipulation: Individual Fairness-aware Strategic Classification with Peer Imitation
May 30, 2026Xinpeng Lv, Chunyuan Zheng, Yunxin Mao +9Fairness-Aware Learning Emotional Manipulation
Infeasible optimization problems and the hierarchical augmented Lagrangian method in imitation learning
May 30, 2026Roland Andrews, Justin Carpentier, Ajay SathyaImitation Learning Robot Policies
HOIST: Humanoid Optimization with Imitation and Sample-efficient Tuning for Manipulating Suspended Loads
May 29, 2026Songyang Liu, Shunyu Yao, Dingyuan Huang +1Whole-Body Controllers Imitation Learning
SWIM: Single-Instance Whole-Body Imitation for swiMming
May 29, 2026Binglun Wang, Edmond S. L. Ho, He WangSwimming Robot Imitation Learning
What Frozen VLAs Already Know About Success: A Probing Study of Value-Like Structure in Foundation Robot Policies
May 27, 2026Jiachen Zhang, Junnan Nie, Junyi Lao +4Vision-Language-Action Policies Frozen Vision-Language Models
Teacher-Student Representational Alignment for Reinforcement Learning-Driven Imitation Learning
May 27, 2026Meraj Mammadov, Pedro Zuidberg Dos Martires, Johannes Andreas StorkImitation Learning Imitation
ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains
May 27, 2026Ziqi Zhao, Xinyu Ma, Liu Yang +6Unsupervised On-Policy Self-Distillation LLM Reasoning Methods
Beyond the Target: From Imitation to Collaboration in Speculative Decoding
May 24, 2026Jinze Li, Yixing Xu, Guanchen Li +7Speculative Decoding Collaboration
From Patches to Trajectories: Privileged Process Supervision for Software-Engineering Agents
May 21, 2026Murong Ma, Tianyu Chen, Yun Lin +7Software Engineering Swe-Bench Verified
Beyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives
May 19, 2026Junli Wang, Zhihua Hua, Xueyi Liu +7Autonomous Driving Imitation Learning
From Imitation to Interaction: Mastering Game of Schnapsen with Shallow Reinforcement Learning
May 16, 2026Ján Klačan, Sizhong ZhangSafe Reinforcement Learning Imitation
Imitation learning for clinical decision support in pediatric ECMO
May 15, 2026Fateme Golivand, Michael Skinner, Saurabh Mathur +5Imitation Learning Imitation
SkiP: When to Skip and When to Refine for Efficient Robot Manipulation
May 15, 2026Mingtong Dai, Guanqi Peng, Yongjie Bai +5Robotic Manipulation Real-Robot Experiments
NavOL: Navigation Policy with Online Imitation Learning
May 12, 2026Xiaofei Wei, Chun Gu, Li ZhangImitation Learning Navigation
RePO-VLA: Recovery-Driven Policy Optimization for Vision-Language-Action Models
May 10, 2026Weijia Liufu, Xiaoyu Guo, Ruiyi Chen +16Relative Policy Optimization Policy Optimization
Zero-shot Imitation Learning by Latent Topology Mapping
May 8, 2026Maxwell J. Jacobson, Yexiang XueImitation Learning Imitation
On Distinguishing Capability Elicitation from Capability Creation in Post-Training: A Free-Energy Perspective
May 8, 2026Yuhao Li, Shengchao LiuPost-Training Large Language Model Post-Training
Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level
May 7, 2026Nan Jia, Haojin Yang, Xing Ma +6On-Policy Distillation Policy Gradient
Provable imitation learning for control of instability in partially-observed Vlasov--Poisson equations
May 6, 2026Xiaofan Xia, Qin Li, Wenlong MouRobust Control Plasma Shape Control
An Efficient Metric for Data Quality Measurement in Imitation Learning
May 2, 2026Noushad Sojib, Momotaz BegumImitation Learning Data Quality

Sep 8, 2026 · cs.AIJ/K move · Enter open · S save

Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails

Zhou Yu, Bin Bi, Shiva Kumar Pentyala, Shubham Mehrotra+7

Agent harnesses (the system prompt, tool set, execution hooks, and context-management scaffolding around a model) are a critical determinant of agentic task success. Automated harness evolution can enable smaller models to perform well on domain-specific tasks at a fraction of frontier-model cost. Since both the harness and model weights shape behavior, we ask how harness evolution and lightweight fine-tuning should be combined. Across seven enterprise agent tasks, we first evolve a harness with the weaker model, then find that a stronger expert often uses it more effectively, suggesting expert supervision could close the remaining gap. However, training the weaker model on the expert's complete trajectories under the evolved harness backfires: performance regresses on all seven tasks by 4 to 30 points across Qwen3-Coder and Gemma 4, even though the same procedure helps under the unevolved harness. Our analysis shows that imitation transfers knowledge and increases scaffold usage, but disrupts model-harness fit: the weaker model adopts the expert's planning strategy without the competence to execute it and no longer matches the harness evolved around its native planning style. We therefore develop an on-policy expert-correction pipeline, automated by a meta-level MLE agent, that localizes the failing turn in the weaker model's own rollout and asks the expert to rewrite only that turn. This preserves the model's planning style and combines the gains of harness evolution and model adaptation. Our results identify and resolve a source of contention between harness and weight updates, yielding a compatibility-preserving recipe for economical co-evolution on domain-specific enterprise tasks.

Agent Harness On-Policy Parameter-Efficient Adaptation Imitation Transferable Knowledge

Open paper Ask about it PDF