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
193 results for “keyword:"multi turn"” in ICLR 2027. 28 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Measure Once, Steer with Many: Context Contamination and Composite Control for Persona Drift in LLMs▼5.8k2.33
[PDF]Early Context Starvation in Conversational LLMs: Causal Evidence from Attention Interventions▼1.2k1.67
[PDF]Train Less, Learn More: Adaptive Efficient Rollout Optimization for Group-Based Reinforcement Learning▼1.2k1.67
[PDF]The Emperor's New Scaffold: Semantically Equivalent Harnesses Reshuffle the Leaderboard▼4.3k2.00
[PDF]The Right Source Is Not Enough: Understanding History Interference in Speech-LLM Memory▼1.2k1.67
[PDF]EHRTemp: Learning Dynamic Clinical Decision Making from Longitudinal Electronic Health Records▼4.3k2.00
[PDF]Same Conversation, Different Actions: Phase-Conditioned Causal Steering for Multi-Turn LLM Safety▲1.7k3.33
[PDF]Do Multi-Turn Conversational Capabilities Carry Over from Text to Speech? A Parallel Multilingual Benchmark▼1.2k1.67
[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]StateWise: Teaching Language Models to Track and Obey Evolving Constraints in Multi-Turn Dialogue▼1.2k1.67
[PDF]Same Conversation, Different Tokens: Characterizing and Mitigating Token Drift for Efficient Multi-Turn LLM Serving▼4.5k2.67
[PDF]CAGPO: Critic-Anchored Group Policy Optimization for Multi-Turn LLM Agent Reinforcement Learning▼4.3k2.00
[PDF]MIRA: Mined Interaction Replay for Agent-Evaluation–Measuring Policy Adherence Beyond the End State▼4.3k2.00
[PDF]CURE: Constructing User-Specific Rubrics to Evaluate Multi-Turn Role-Playing Dialogue with Agent Judges▼1.2k1.67
[PDF]Multi-turn RL with Structural and Performance Aware Rewards for CUDA Kernel Generation▼1.2k1.67
[PDF]When Conversation is the Attack: Mining Transferable Contexts for Harmful Compliance and Over-Refusal▲3.0k2.33
[PDF]Crescendo-Live: Multi-Turn Jailbreaks of Full-Duplex Speech Models in Live Calls and Their Defense with Daimonion▲3.0k2.50
[PDF]Agentic Myopia: Probing the Temporal Awareness of Agents in Simulated Multi-Turn Coding Sessions▼4.3k2.00
[PDF]SG-LegalClarify: a Large-scale Benchmark for Legal Reasoning and Ambiguity Recognition in Singapore Law▼4.3k2.00
[PDF]Groundworks: Agents Can Complete Tasks Yet Fail Under Plausible Perturbations In Multi-Turn Interactions▼4.3k2.00
[PDF]OmicsBench: a long-horizon multi-turn benchmark of AI agents on research study-scale bioinformatics▼5.8k2.33
[PDF]Beyond Jailbreak Rates: Harm Centric Evaluation of Multi Turn Jailbreak Attacks and Defenses▼4.3k2.00
Withdrawn or desk rejected (28)
[PDF]When to Act, Not What to Act: Prospective Authorization for Tool-Using Language ModelsWithdrawn1.33
[PDF]Machine Love: Emergent Bonding Behavior in Large Language Models and Its Implications for AI SafetyDesk rejected
[PDF]Interact, Remember, and Act: Preference and Progress-Driven Reinforcement Learning for LLM AgentsWithdrawn1.67
[PDF]When Evidence Changes, Does Reasoning Follow? Revising Language Model Conclusions Under Changing EvidenceWithdrawn1.33
[PDF]MASCSBench: A Benchmark for Evaluating Emergent Content Safety Risks in Multi-Agent Conversational SystemsDesk rejected1.67