NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
153 results for “keyword:"interactive"” in ICLR 2027. 60 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]PraxiScene: Benchmarking Agent Social Agency in Generated Open-Goal Interactive Scenarios▲3.0k2.50
[PDF]mini-psych-agent: Evaluating Human-Like Behavior in LLM Agents through Interactive Psychological Environments▼5.8k2.33
[PDF]SAMLens: Canonical Quality Can Hide Negative-Point Reversal in Specialized Segment Anything Models▲9.2k2.67
[PDF]GDPO-Listener: Expressive Interactive Head Generation via Auto-Regressive Flow Matching and Group Reward-Decoupled Policy Optimization▼1.2k3.00
[PDF]Persistent Preference Inference for Query-Efficient Interactive Multi-Objective Optimization▲4002.67
[PDF]Gauge and Drift: Separating Commanded Change from Error Accumulation in Autoregressive Generation▼5.8k2.33
[PDF]FashionArena: A Large-Scale, Production-Grounded Environment for Training and Evaluating Fashion Shopping Agents▼4.5k2.67
[PDF]Does the World Wait While Agents Think? A Temporal Fidelity Audit of Interactive-Agent Benchmarks▲9.2k2.67
[PDF]MemGround: Evaluating Memory Behavior of Large Language Models in Long-Horizon Gamified Scenarios▲4002.67
[PDF]DESIGN THEFEEDBACK, NOTJUST THEREWARD: ENVIRONMENTS FOROPEN-ENDED REINFORCEMENT LEARNING▼4.3k2.00
[PDF]Wait or Take Over: Forecasting OOD Persistence and Recovery for Efficient Human-in-the-Loop Imitation Learning▲1.7k3.33
[PDF]CaptchaArena: A Large-Scale, Fine-Grained Dataset for Training Computer-Use Agents on Interactive CAPTCHAs▲5103.00
[PDF]IKBQA-R1: Reinforcing Large Language Models for Question Answering over Incomplete Knowledge Graphs▲3.0k2.33
[PDF]Benchmarking In-Context Experiential Learning across Heterogeneous Action and Feedback Channels▼4.5k2.25
[PDF]StoreBench: A Live-Commerce Environment for Evaluating and Training Autonomous Operator Agents▲3.0k2.33
[PDF]What to Learn and Who to Ask: Adaptive Curriculum and Expert Allocation for Interactive Imitation▲5103.00
[PDF]From Knowledge to Decisions: Repairing Evidence Seeking after Full-Evidence Adaptation▼1.2k1.67
[PDF]Thinking by Doing: Building Efficient World Model Reasoning in LLMs via Multi-turn Interaction▲8.9k2.75
[PDF]SWE-Clar: Can Coding Agents Clarify Incomplete Client Requirements and Deliver Greenfield Software?▲3.0k2.33
[PDF]Beyond Oracle Communication: Benchmarking Interactive Intent Alignment Under Miscommunication and Evolving User Intent▲4.6k3.00
[PDF]CausaLab: A Scalable Environment for Interactive Causal Discovery Toward AI Scientists▲1.7k3.33
[PDF]LiveAct: Towards Real-Time Multi-Agent World Models with Heterogeneous Action Interfaces▲5.4k3.00
[PDF]Faultless Misreading: Diagnosing Professional Agents Under Incomplete Spreadsheet Requests▲4.6k3.00
Withdrawn or desk rejected (60)
[PDF]ElicitDoctor: Robust Multi-Turn Evidence Elicitation in Psychiatric Dialogue under Low-Disclosure Patient ResponsesDesk rejected2.00
[PDF]No Corners Cut: State-Grounded Transitions for Mid-Stream Prompt Switches in Video GenerationWithdrawn2.25