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
129 results for “keyword:"ai agents"” in ICLR 2027. 31 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]CareLoop: Measuring the Gap Between Knowing Medicine and Practicing It in the Context of Patients' Lives▼4.3k2.00
[PDF]FDE-Bench: Evaluating End-to-End Delivery from Underspecified Real-World Business Requests▼1.2k3.00
[PDF]DEBATE, NOT VOTING: AGENTIC ARBITRATION OVER WEAK OPTICAL CHEMICAL STRUCTURE RECOGNITION MODELS▼1.3k1.80
[PDF]How Do AI Agents Spend Your Money? Analyzing and Predicting Token Consumption in Agentic Coding Tasks▼5.8k2.33
[PDF]ScrambleToolBench: Agents Search Exhaustively Even When Their Own Map Points to the Next Step▼5.8k2.33
[PDF]ChameleonBench: Evaluating the Cross-Environment Robustness Across Heterogeneous Systems▼1.2k1.67
[PDF]AlphaIdeaBench: Benchmarking Automated Research Idea Generation under Feasibility Constraints with Peer Review Alignment▲3952.67
[PDF]Self-Evolution Should Be Stable, Not Frozen: Lyapunov-Gated Recursive Self-Improvement▼4.3k2.00
[PDF]What Makes Agents Effective for Scientific Design? A Controlled Evaluation with Scientific Foundation Model Tools▼5.8k2.33
[PDF]When Success Is a Lossy Record: Matched-Success Continuation Evaluation for Persistent Agents▼4.3k2.00
[PDF]Spec2Twin-Chain: Orchestrating Bi-Level Optimization with LLMs for Blockchain Digital Twin Construction▼1.2k1.67
[PDF]CVE-Bench Hard: Rigorous Evaluation of AI Agents for Identifying and Exploiting Complex Web Application Vulnerabilities▼4.5k2.67
[PDF]A Claim Is Not a Measurement: Compliance Claims Change What LLM Evaluators Verify and Accept▲3.0k2.33
[PDF]EvoCare: Towards Efficient and Robust Clinical Diagnosis with Proactive and Interactive Self-Evolving AI Agents▼3.7k2.25
[PDF]AnesTRACE: Benchmarking Intraoperative Anesthesia from Multimodal Perception to Multi-step Decision-Making▼1.2k1.67
[PDF]CovMOLAgent: Execution-Grounded Policy Learning for Multi-Objective Covalent Molecule Optimization▼1.2k1.67
[PDF]Melo: A Cognitive Science–Inspired Closed-Loop Long-Term Memory Framework for AI Agents▼1.2k1.67
[PDF]Do AI Agents Have Research Taste? SENSE-Bench for Anomaly-Driven Scientific Exploration▼1.2k1.67
[PDF]RS-Gen: A Multi-Stage Agentic Framework for Reasoning and Search-Augmented Image Generation▼4.3k2.00
Withdrawn or desk rejected (31)
[PDF]SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt InjectionWithdrawn2.00