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
120 results for “keyword:"agent safety"” in ICLR 2027. 26 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]MobileGrail: Learning Compact Guardrails for On-Device deployable Mobile GUI Agent Safety▲3.0k2.33
[PDF]MedGauge: Evidence-Grounded Commit Protocols for Reliable Tool-Using LLM Agents in Medical Measurement▲5103.00
[PDF]Aligned Alone, Misaligned Together: Forecasting Adversarial Capture in LLM Agent Populations▲3952.67
[PDF]Risk Exposure Does Not Mean Unsafe Action: Evidence-Dynamics Alignment for Agent Safety▼1361.33
[PDF]From One Monitor to One Joint: Tractable Probabilistic Inference for Agent Safety with Tensor Networks▼5.8k2.33
[PDF]Check, Don't Trust: Evidence Contracts for Small Language Agents in GPU-Cluster Operations▼1.2k1.67
[PDF]Cooperative Words, Adversarial Actions: Action-Level Ambiguity in Embodied Multi-Agent Systems▼13k2.00
[PDF]Risk Lies in the Relations: Relation-Aware Collaboration Graph Defense for LLM Multi-Agent Systems▲3952.67
[PDF]After Denial, What Next? Recoverability-Aware Legal Continuation for Tool-Using Agents▼1.3k1.75
[PDF]Interactive Monitoring: Can Questioning Mitigate Misbehavior While Preserving Task Utility?▼1.2k3.00
[PDF]From Prompt Injection to Persistent Control: Defending Agentic Workspaces Against Trojan Backdoors▼1.2k1.67
[PDF]Compositional Safety Failures in Harness Evolution: Identification and Runtime Monitoring▲3.0k2.33
Withdrawn or desk rejected (26)
[PDF]Policy-Verified Self-Training: Learning Agent Compliance from Verifiable Policy RewardsWithdrawn1.67
[PDF]BLINDSPOT: A Benchmark for Safety and Refusal Calibration in Long-Horizon Tool-Using AgentsDesk rejected