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
5,245 results for “keyword:"agent"” in ICLR 2027. 1,221 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]SOCAL: Step-Specific Over-Search Calibration for Search Agents via Self-Distilled Hindsight▲3.0k2.33
[PDF]CivWorldBench: Evaluating Language World Models in Structured Multi-Agent Sandbox Worlds▲133.33
[PDF]SVP: State-Verified Planning for System-Level External Knowledge Integration in Agentic Reasoning▼4.3k2.00
[PDF]Valid Actions, Wrong Targets: Visual Attacks and Evidence-Based Defense for Web Agents▲9.2k2.67
[PDF]WitRepair: Certifiable Minimum Repair of Persistent Agent Memory via Retrieval Equivalence▼1361.33
[PDF]ONTOS: Candidate-First Knowledge Graph Question Answering with Ontology-Constrained Program Synthesis▲3892.67
[PDF]The Agent Loop Is a Routing Decision: Measuring the Switching Tax in Multi-Turn LLM Routing▼1.2k1.67
[PDF]When Fine-Grained Credit Assignment Helps and Hurts: Multimodal Agentic Reinforcement Learning through Video Editing▲3.0k2.33
[PDF]INCUMBENT: THE MODEL PROPOSES, THE STORE DISPOSES — STRUCTURAL TRUTH MAINTENANCE FOR AGENT MEMORY▼4.3k2.00
[PDF]FAROS: Characterizing Coding-Agent Search for Executable Time-Series Anomaly Detectors▼1.3k1.75
[PDF]Only What Was Asked: Overcoming Effect Blindness of LLM Agents in Stateful Environments▼4.5k2.25
[PDF]TRACE: Task-conditioned Retrieval and Aggregation with Token-Budgeted Compilation for Executable Skill Programs in LLM Agents▼71.25
[PDF]Translating Research to Slides: Audience-Grounded Presentation Generation via Verifiable Transduction Graphs▲5.4k3.00
[PDF]SeekOrStop: Benchmarking Tool-Mediated Blue-Team Investigation under Matched Evidence Access▼4.3k2.00
[PDF]HorizonKV: Future-Aware KVCache Reuse via Lightweight Relevance Estimation for Interleaved Agent Contexts▼1.2k1.67
[PDF]TRACE: FROM VERIFIED OUTCOMES TO REUSABLE PROBING STRATEGIES FOR MEMORY-EXPOSURE ASSESSMENT IN CLINICAL LLM AGENTS▼1361.33
[PDF]FDE-Bench: Evaluating End-to-End Delivery from Underspecified Real-World Business Requests▼1.2k3.00
[PDF]ConScribe: Repairing Learned Skills with Residual Updates for Changing Web Environments▲6.1k2.00
Withdrawn or desk rejected (1,221)
[PDF]When Is a Policy Violation a Model Failure? Policy Observability and Failure Attribution in Agent-Safety EvaluationDesk rejected
[PDF]Population Contracts for Scalable Language-Guided Multi-Robot Planning and ControlDesk rejected
[PDF]When to Act, Not What to Act: Prospective Authorization for Tool-Using Language ModelsWithdrawn1.33
[PDF]FairWatch: Interaction Topology as a First-Order Variable Shaping Safety and Fairness in Multi-Agent DeliberationDesk rejected2.00