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120 results for “keyword:"agent safety"” in ICLR 2027. 26 withdrawn or desk rejected listed apart.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]Do Detailed Guard Denials Help Bypass Guardrails? Evaluating Runtime Feedback in DeepSeek Harness▼4.3k2.00
[PDF]The Vocabulary Bottleneck as an Estimator: Rate, Bias, and Hidden Transfer Between Language Models▼1.2k1.67
[PDF]Admission Control for Multi-Agent LLM Systems: Enforcing Safety Invariants on the Connection Graph▲6.1k2.00
[PDF]HarmonyGuard: A Multi-Agent Guardrail for Web Agents via Dual-Timescale Policy Grounding▲5.4k3.00
[PDF]Beyond Prompt Filtering: What Runtime Safety Mechanisms for LLM Agents Observe, Decide, and Control▼1361.33
[PDF]Same Answer, Different Reasons: Disentangling Coordination from Consensus in Multi-Agent Debate▲3952.67
[PDF]CrossAnchor: Image-Anchored Text Optimization Exposes Blind Spots in Multi-line Defenses of Agentic Systems▼4.3k2.00
[PDF]ControlBench: Did the Approval Actually Happen? Process-Grounded Auditing of Human Control over LLM Agents▼4.3k2.00
[PDF]CROSS: Coupled Recurrence of Latent-Symbolic Security-State for Runtime Safety Monitoring of AI Agents▼5.8k2.33
[PDF]AEGIS: Evidence-Grounded Agent Safety Verification with Diffusion Scoring and Ising-Structured Risk Inference▼4.3k2.00
[PDF]PACT: Provenance-Aware Contract Testing — What Do LLM-Agent Task-Contract Checkers Actually Certify?▼1361.33
[PDF]Do Agents Do What Users Ask? Measuring Intent-State Consistency in Tool-Using Language Agents▼5.8k2.33
[PDF]Counterfactual Stress Testing of Behavioral Invariants in LLM Agents: A Study of Dynamic Authorization▼5.8k2.33
[PDF]MedicalPressureBench: Evaluating Care Pathway Integrity of Medical Agents Under Workplace Pressure▼4.3k2.00
[PDF]Stop Stealing, Stop Attacking: Countering Benchmark Hacking with Kernel-Enforced Contracts Outside the Agent's Reach▼4.3k2.00
[PDF]AURA-Eval: Evaluation Framework for Acting Under Risk Awareness in LLM Agent Trajectories▼5.9k2.50
[PDF]Are Your Agents Ready to Evolve? Assessing Evolution-Readiness in Agents Through Paired Safety and Utility Scoring▲3.0k2.33
Withdrawn or desk rejected (26)
[PDF]Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent SystemsWithdrawn1.33