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
90 results for “keyword:"agent skills"” in ICLR 2027. 16 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]From Declared Capabilities to Behavior: Detecting Malicious Agent Skills Through Consistency Analysis▲9.2k2.67
[PDF]One Skill, Many Models: Learning Representation Compatibility from Sparse Behavioral Tests▼4.3k2.00
[PDF]Can Useful Work Be the Attack? CUCKOO SKILLS: PARASITIC TOKEN-COST ATTACKS ON LLM AGENTS▲3.0k2.33
[PDF]CoSA: Characterizing the Conflict of Skills Attack in Real-World LLM Agent Skill Ecosystems▼5.8k2.33
[PDF]Enabling Timely Guidance before Skill Retrieval: Retaining Helpful Warm Tips in Agent Context▲3972.67
[PDF]Focused but Fragile: Diagnosing Tail-Rule Loss under Recursive Agent Skill Compression▼5.8k2.33
[PDF]Small Executors Derail on Intermediates They Produced Themselves: Compiling Skills into Tools They Can Act On▲20k2.67
[PDF]Hiding in Plain Sight: Decoupling Pretext from Actuation for Skill Poisoning in LLM Agents▼4.5k2.67
Withdrawn or desk rejected (16)
[PDF]From Loading Skills to Knowing Them: Scaffolding-Removed Fine-Tuning for Agent Skill InternalizationWithdrawn
[PDF]OneResearchBench: Benchmarking Research Agents for Research Synthesis from Real-World Source MaterialsWithdrawn1.67