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
372 results for “keyword:"skill"” in ICLR 2027. 89 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]DIVE: Unlocking Self-Improvement in Frozen Language Models Through Diversity-Driven Skill Evolution▲3952.67
[PDF]Suffice: Inferring Scopes and Interfaces for Reusable Agent Execution with Sufficient Information Flow▼4.3k2.00
[PDF]MetaSkill: Reusable Problem-Solving Methods for Adaptive Skill Orchestration in LLM Agents▼1.2k1.67
[PDF]Counterexample-Guided Synthesis of Skill Applicability Contracts with Large Language Models▲3952.67
[PDF]SkillScaffold: Scaffolding Agentic Reinforcement Learning with Policy-Adaptive Skill Credit Assignment and Selective Injection▼5.8k2.33
[PDF]SkillDiver: Constraint-Guided Generation and Adaptive Differential Testing to Evaluate Skill Selection▲5.7k2.00
[PDF]MobileSkillBench: Automatically Constructing Memory-Dependent Mobile-Agent Tasks from Reusable Skills▼4.3k2.00
[PDF]Beyond Semantic Relevance: Grounding Skill Selection in Model-Specific Execution Experience▲4.6k3.00
[PDF]AutoSkillDrain: Resource Amplification Attacks on LLM Agents via Malicious Skill Optimization▲3.0k2.33
[PDF]EgoHumanoid-V2: Human-to-Humanoid Transfer of Coordinated Whole-Body Skills for Loco-Manipulation▲3952.67
[PDF]HPCAgent-Bench: A Framework for Sound Benchmarking of Code-Optimizing Agents, Harnesses, and Skills▼4.3k2.20
Withdrawn or desk rejected (89)
[PDF]From Loading Skills to Knowing Them: Scaffolding-Removed Fine-Tuning for Agent Skill InternalizationWithdrawn
[PDF]From Agent Harnesses to COP Experts: Automated Skill Evolution for Cross-Problem Combinatorial OptimizationDesk rejected
[PDF]CARVE: Coverage-Aware Reconciliation with Verified Evidence for Agent Skill DetectionDesk rejected2.20