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
225 results for “keyword:"language model agent"” in ICLR 2027. 35 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Embodied Skill Bench: Benchmarking How Well Agents with Embodied Skills Perform on Physical Tasks▲14k3.00
[PDF]Consensus-Breaking Re-rollout: Recovering Missing Action Contrasts for Long-Horizon Agent Reinforcement Learning▼4.3k2.00
[PDF]SkillScaffold: Scaffolding Agentic Reinforcement Learning with Policy-Adaptive Skill Credit Assignment and Selective Injection▼5.8k2.33
[PDF]Beyond Positive Reinforcement: A Hierarchical Multi-Perspective Memory Framework for Multi-Agent Systems▼4.3k2.00
[PDF]Rome Wasn’t Built in One Turn: Replay-Grounded Reward Signals for Long-Horizon Freeciv Agents▼4.3k2.00
[PDF]CERES: RECONCILING DURABLE EVIDENCE AND EVOLVING ACTIVE STATE FOR LONG-LIVED LLM AGENTS▼1.2k1.67
[PDF]Learning When Cellular Responses Transfer: A Factorized Memory-Guided Agent for Perturbation Prediction▼4.3k2.00
[PDF]Learning What Not to Learn: Target-Conditioned Update Eligibility for Self-Improving Agents▼5.8k2.33
[PDF]More Is Not Always Better: Overlapping Gains and Composition Failures in Agent Adaptation▼1361.33
[PDF]TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training▼5.8k2.33
[PDF]Socratic Skill Learning: Interleaving Teaching and Practice for Transferable Agent Skills▲3952.67
[PDF]What a Memory Can and Cannot Carry: Representation Shapes What an Experience Layer Can Hold▲3.8k2.50
[PDF]EnvSched: Environment-Aware Scheduling for Rollout-Efficient Agent Reinforcement Learning▲3952.67
[PDF]RISE: Reasoning-Induced Supervised Reinforcement Learning with Expert-Collaborative Training▼2443.33
[PDF]When Is Tool-Observation Compression Worth Pursuing? Replay Audits Across Agent Interfaces▼1.2k1.67
[PDF]NovelAudit: A Benchmark for Open-Ended Narrative Consistency Auditing in Full-Length Novels▼4.3k2.00
Withdrawn or desk rejected (35)
[PDF]CommerceAgentBench: Benchmarking Long-Horizon Agents in High-Fidelity, Stateful, and Reproducible Replicas of Real Online ServicesDesk rejected2.00
[PDF]Characterizing When Language Models Take Harmful Actions to Protect Their Assigned GoalsWithdrawn2.00