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
2,518 results for “area:"datasets and benchmarks"” in ICLR 2027. 617 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]No Single Point Suffices: Reporting Regularization Landscapes in Frozen-Representation Evaluation▲11.00
[PDF]SMH-Bench: Benchmarking LLM Agents for Environment-Grounded Reasoning and Action in Smart Homes▲3922.67
[PDF]From Trajectories to Grounded Preferences: Process Preference Synthesis via Interaction Element Graphs for Web PRMs▲3.0k2.33
[PDF]MS-Eval: Benchmarking Sub-Agent Delegation and Orchestration in MCP-Intensive Working Scenarios▼4.3k2.00
[PDF]PaperEvaluation: Benchmarking Agent-Generated Scientific Papers with Execution Evidence▼4.3k2.00
[PDF]Does the World Wait While Agents Think? A Temporal Fidelity Audit of Interactive-Agent Benchmarks▲9.2k2.67
[PDF]Correct Scores, Unsupported Conclusions: Benchmarking Evaluation under Incomplete Semantic Reference▼4.3k2.00
[PDF]Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development▲9.2k2.67
[PDF]WebMix-Collapse: A Rewrite Benchmark for Sizing the Length Confound in Short-Form Synthetic-Text Detection▲11k2.00
[PDF]Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks▼1.3k1.75
[PDF]MuseFACET: Benchmarking Trustworthy and Controllable Image-to-Text Generation for Musuem Collection Interpretation▲5.4k3.00
[PDF]Can LLMs Think Like Consumers? Benchmarking Crowd-Level Reaction Reconstruction with ConsumerSimBench▲6.1k2.00
[PDF]RHContrast: A Matched-Control Benchmark for Evaluating Reward-Hacking Risks in Long-Form LLM Responses▲3.0k2.33
[PDF]SkillEval: Learning Interpretable Ability Profiles of LLMs via Cognitive Diagnosis Models▼1.2k1.67
[PDF]Finding Answers in Thought Matters: Revisiting Evaluation on Large Language Models with Reasoning▼1.2k1.67
[PDF]LoHoSearch: Benchmarking Long-Horizon Search Agents Beyond the Human Difficulty Ceiling▲5103.00
[PDF]Lost in Sequence, Found in Text: Retrieving Functionally Related Proteins Under Joint Sequence and Structure Similarity Controls▲5.4k3.00
[PDF]Selection Is Not Validation: Auditing Proxy-to-Behavior Reversals in Language-Model Data Curation▲11.00
[PDF]DeepVisualMath: Comprehensive Evaluation of Visual Mathematical Reasoning in Large Multimodal Models▲6.1k2.00
[PDF]From Detection to Intervention: Counterfactual Decontamination for Language-Model Evaluation▼1361.33
[PDF]MIRAGE: Benchmarking Intent Identifiability under Partial Observation through Counterfactual Multi-Agent Reasoning▼1.2k1.67
[PDF]MemGround: Evaluating Memory Behavior of Large Language Models in Long-Horizon Gamified Scenarios▲3922.67
Withdrawn or desk rejected (617)
[PDF]NEAR-Bench: Benchmarking Predictive Performance and EEG Input Dependence in EEG-to-Text DecodingWithdrawn2.00
[PDF]When Is a Policy Violation a Model Failure? Policy Observability and Failure Attribution in Agent-Safety EvaluationDesk rejected
[PDF]Matched Counterfactual Attribution: A Controlled Evaluation of Data Selection for Video Instruction TuningDesk rejected2.00
[PDF]Less Data, Faster Convergence: Goal-Driven Data Optimization for Multimodal Instruction TuningDesk rejected1.67
[PDF]-Bench: Benchmarking Proactive Speech Interaction with Full-Duplex Conversational AIDesk rejected