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
95 results for “keyword:"tasks"” in ICLR 2027. 21 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]DMAIC-Bench: From Self-Reflection to Self-Restraint for Agents in Multi-Stage Analytical Tasks▼5.8k2.40
[PDF]InEx: Intrinsic and Extrinsic Evidence for Trustworthy Evaluation of Latently Verifiable Tasks▲452.75
[PDF]RLVR landscapes for iterated multiplications can be benign: Insights from spin-glass theory▼4.3k2.00
[PDF]Consensus-Breaking Re-rollout: Recovering Missing Action Contrasts for Long-Horizon Agent Reinforcement Learning▼4.3k2.00
[PDF]Long-horizon-terminal-bench 2.0: Testing the limits of agents on long-horizon terminal tasks with dense reward-based grading▼4.3k2.00
[PDF]COPE: Recovering Long-Horizon Coding Tasks through Compression of Pull-Request Evolution▲3972.67
[PDF]Mobile Skills Bench: Benchmarking Long-Horizon Interactive Mobile Agents with Multimodal Skills under Hybrid Execution▲5103.00
[PDF]Learning from All-Failed Groups via First-Visit Coverage in Long-Horizon Agentic Tasks▼5.8k2.33
[PDF]Agentic-OPD: Recovering Forgotten Agent Capabilities via On-Policy Distillation for Long-Horizon Tasks▲6.1k2.00
[PDF]SimuWoB: Simulating Real-World Mobile Apps for Fast and Faithful GUI Agent Benchmarking▼5.8k2.33
[PDF]RGDT-Bench: Benchmarking LLM Reasoning for Rule-Governed Decisions and Their Justifications▲6.1k2.00
[PDF]Conjunctive Amplification of Reward-Scale Miscalibration in Cooperative Multi-Event Reinforcement Learning▼5.8k2.33
[PDF]Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic Tasks in Real-World Professional Fields▼5.8k2.33
[PDF]ViCoR: Reliable Molecular Structure Extraction via Spatially Aligned Verification and Executable Revision▲3.0k2.50
Withdrawn or desk rejected (21)
[PDF]EarthArena: Benchmarking Agents on Real-world, Long-Horizon Scientific Tasks in Earth ObservationWithdrawn1.67
[PDF]CommerceAgentBench: Benchmarking Long-Horizon Agents in High-Fidelity, Stateful, and Reproducible Replicas of Real Online ServicesDesk rejected2.00