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
128 results for “keyword:"evolving agents"” in ICLR 2027. 35 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]ARISE-RL: Agentic Rubric-Grounded Iterative Self-Evolution with Reinforcement Learning▲9.2k2.67
[PDF]Repeatable but Not Replicable: Evaluator State as a Hidden Facet in Self-Evolving Agents▼4.3k2.00
[PDF]Learn to Sell, Not What to Sell: Dualistic Self-Evolution (DSE) of LLM Sales Agents with Human Nature as Reward (HNR)▼4.3k2.00
[PDF]Beyond Skill Evolution: Self-Evolving Context Management Policies for Long-Horizon Agent Harnesses▼4.3k2.00
[PDF]Learning to Elicit: Co-Evolving Routing and Information Disclosure in Societies of Language Agents▼1351.33
[PDF]Know What You Don’t Know: Agentic Data Synthesis by Evolving Generation Space for Closed-Loop Learning▲4002.67
[PDF]PrivMeSA: Privacy-Aware Self-Evolving Multi-Agent System for Medicine via Local-Remote LLM Collaboration▼5.8k2.33
[PDF]RSI-Router: Cost-Efficient LLM Routing via Evolution of Subtask-Level Model Assignments with Execution Skills▼5.8k2.33
[PDF]KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill▼1.2k1.67
[PDF]FinEvolveBench: A Benchmark for Self-Evolving Agents under Challenging Experience Regimes▲6.1k2.00
[PDF]Are Your Agents Ready to Evolve? Assessing Evolution-Readiness in Agents Through Paired Safety and Utility Scoring▲3.0k2.33
[PDF]FinEvo-Bench: A Longitudinal Benchmark for Self-Evolving Agents in Professional Financial Workflows▼4.5k2.67
Withdrawn or desk rejected (35)
[PDF]Rethinking Self-Evolving Agents: Do We Still Need Prescribed Optimization Pipelines?Withdrawn1.67
[PDF]MemEff: Enhancing Self-Evolving Agents through Behavioral Efficacy-Guided Memory OptimizationDesk rejected2.33
[PDF]Why Do Self-Evolving LLM Agents Fail? A Study of Memory-Based Learning at Test TimeDesk rejected1.33
[PDF]MORE: Mode-Optimized Reasoning with Self-Adaptive Effort for Self-Evolving AgentsDesk rejected2.67
[PDF]From VLM Planners to Robotic Agents: Self-Evolving Harnesses for History-Dependent ManipulationWithdrawn1.50