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
98 results for “keyword:"tool using"” in ICLR 2027. 30 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]What Does a Failed Rollout Supervise? Separating Policy Failure from Recoverability in Tool Agents▼4.3k2.00
[PDF]AnyTool-Agent: API-Guided Tool Use for Data-Scarce Ecosystems via Execution-Grounded Policy Optimization▲5103.00
[PDF]Beyond Tool Responses: Effect Verification and Residual Recovery under Response–Effect Mismatch▼3.7k2.25
[PDF]Beyond Trust: Proof-Carrying Generation and Independent Release Assurance for Multi-Agent LLMs▼1.2k1.67
[PDF]From Knowledge to Decisions: Repairing Evidence Seeking after Full-Evidence Adaptation▼1.2k1.67
[PDF]After Denial, What Next? Recoverability-Aware Legal Continuation for Tool-Using Agents▼1.3k1.75
[PDF]MICO: VERIFIABLE MILESTONES FOR PROVABLY BOUNDED CREDIT ASSIGNMENT IN AGENTIC REINFORCEMENT LEARNING▲11.00
[PDF]Interactive Monitoring: Can Questioning Mitigate Misbehavior While Preserving Task Utility?▼1.2k3.00
[PDF]Autonomous Red Teaming for Utility-Preserving Indirect Prompt Injection via Fine-Grained Diagnosis▼1.2k1.67
[PDF]When Tools Silently Lie: Evaluating and Mitigating Blind Compliance in Tool-Augmented Data Agents▲6.1k2.00
[PDF]From Traces to Guarded Programs: Evidence-Gated Compilation of Recurrent Agent Workflows▼1351.33
[PDF]Success Is Not Completion: Goal-Closure Monitoring and Corroborated Contracts for Tool-Using Agents▼5.8k2.33
[PDF]Where Did the Agent Go Wrong? Localizing—and Fixing—Failure Steps in Multi-Step Video-Editing Agent Traces▼5.8k2.33
[PDF]CoER: Defending against Adaptive Indirect Prompt Injection via Adversarial Co-Evolution and Refinement▼4.5k2.67
Withdrawn or desk rejected (30)
[PDF]The Repair Is Not the Task: Execution Records and False Completion in Agent RecoveryWithdrawn1.33
[PDF]Jailbreak Context Lingers: Divergent Safety Routing and Its Cross-Task Predictability in Tool AgentsWithdrawn2.00
[PDF]SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt InjectionWithdrawn2.00
[PDF]Policy Improvement as Decision Revision: Preserving the Incumbent under Executable FeedbackWithdrawn1.33
[PDF]The Filter Outweighs the Channel: Decomposing Why Tool-Using Agents Corrupt Structured Records at ScaleDesk rejected
[PDF]-IF: A Multi-Variant Benchmark for Agentic Instruction Following in Executable EnvironmentsWithdrawn1.67
[PDF]The Simulator Says Yes: Language World Models Narrate the Executions Their Environment RefusedDesk rejected