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
25 results for “keyword:"tool use agent"” in ICLR 2027. 6 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Contextual Privacy in Agentic Workflows is a Systems Problem: A Benchmark, Auditor & Guard▼5.8k2.33
[PDF]The Protocol Is the Agent: Decomposing RL, SFT, and Scaffold Effects in Tool-Use Agents from 0.8B to 27B▼1.2k1.67
[PDF]AgentQoSBench: Evaluating Quality-of-Service Awareness in Agents under Complex Tool Dependencies▲5103.00
[PDF]Choosing, Not Generating: Option Selection, Learned Preconditions, and Temporal Consistency Checks for Smart-Home Agents▲6.1k2.00
[PDF]-Emotion-Bench: Exposing the Interaction Fragility of LLM Agents through Real-World User Emotions▲4002.67
[PDF]StateForge: Synthesizing Verifiable Long-Horizon Data for Tool-Using Agents via State-Change Supervision▲3.0k2.50
[PDF]OpenMobile-2: Building Versatile Mobile Agents with Scalable Environments and App-Native Tools▲5103.00
[PDF]Verifiable State Transitions as Unified Supervision for Training Stateful Tool-Use Agents▲3.0k2.33
[PDF]BranchWise: A Path Is Not a Policy — Unfolding Successful Trajectories into Model-Tailored Decision Boundaries▲9.2k2.67
[PDF]Deviation Is Not Failure: Decoupling Plan-Adherence from Task-Correctness in LLM Judges via Input-Isolated Single-Axis Fine-Tuning▲6.1k2.00
[PDF]Is This Agent Evaluable? Certifying Verdicts About LLM Agents Under Nondeterminism, Oracle and Coverage Obstructions▼1.2k1.67
Withdrawn or desk rejected (6)
[PDF]Policy-Verified Self-Training: Learning Agent Compliance from Verifiable Policy RewardsWithdrawn1.67
[PDF]RectifyFlow: Plan Upfront, Rectify Selectively for Cost-Efficient Edge–Cloud Tool-Using AgentsDesk rejected2.67