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
1,335 results for “keyword:"llm agents"” in ICLR 2027. 267 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]The Environment Knows Why: Bidirectional Self-Distillation from Augmented Tool Feedback for Agentic RL▲2623.67
[PDF]Interface-Induced Trajectory Censoring: When Tool-Call Interfaces Distort Evaluation and RL Experience▼5.3k1.33
[PDF]The Opponent Learns Too: Alternating Adversarial Training for Stronger Conversational Agents▼4.5k2.25
[PDF]Causal Experience Instantiation: Grounding Procedural Memory with Temporal Graphs for Tool-Use Agents▲5103.00
[PDF]ASCENT: Online Test-Time Training of Long-Horizon Agents via Self-Distillation of Verified Experience▼5.8k2.33
[PDF]Forecast-Dojo: Replayable Environments for Benchmarking and Training LLM Forecasting Agents▲3952.67
[PDF]Fragile Follow-Through: Uncovering How User Revisions Disrupt Long-Horizon Task Execution in LLM Agents▼4.3k2.00
[PDF]PerMIT: Securing Persistent Memory for LLM Agents via Machine-Checked Integrity Theorems and Scalable Community Trust▲8.9k2.75
Withdrawn or desk rejected (267)
[PDF]When Is a Policy Violation a Model Failure? Policy Observability and Failure Attribution in Agent-Safety EvaluationDesk rejected
[PDF]MIRAGE: Memory Revision and Path-Aware Retrieval for Conflict Resolution in LLM Agent MemoryDesk rejected
[PDF]Implicit Strategic Optimization: Prediction-Aware Long-Horizon Learning for LLM AgentsDesk rejected1.67