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
4,865 results for “keyword:"lm"” in ICLR 2027. 936 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]BeaconAgent: Learning Capability-Aware Help-Seeking Policies for Small Language Model Agents▲3942.67
[PDF]Beyond Prompt Filtering: What Runtime Safety Mechanisms for LLM Agents Observe, Decide, and Control▼1361.33
[PDF]REIN: Residual Modulation of Time Series Forecasts via LLM-Refined News Regime Signals▼4.3k2.00
[PDF]Balancing Quality and Coverage in Diffusion Language Models with Adaptive Risk Portfolios▼4.3k2.00
[PDF]Same Answer, Different Reasons: Disentangling Coordination from Consensus in Multi-Agent Debate▲3942.67
[PDF]Policy-State Fragmentation in Multi-Agent LLM Systems: Analyzing Binding Continuity and Runtime Enforcement▼1.2k1.67
[PDF]Actionable Feedback: Improving Model Capabilities From User Edit Data on Clinical Documentation▲6.1k2.00
[PDF]Blackwell-Guided Logit Search (BLS): Optimizing Multi-Turn Jailbreaks with Subliminal Steering▼1.2k1.67
[PDF]Reading the Tea Leaves, Again: Can Large Language Models Predict Language Model Training Runs?▼4.5k2.25
[PDF]Learning Cyber Defense with Limited Interaction: An Empirical Study of Reflective Prompt Optimization▼1.2k1.67
[PDF]RELACE: RETROSPECTIVE LIKELIHOOD-BASED ACTION CREDIT ESTIMATION FOR LONG-HORIZON LANGUAGE AGENTS▼1.2k1.67
[PDF]Attainment Is Not Stationarity: Objective and Optimizer Sources of Behavioral Drift after Safety Alignment▼4.3k2.00
[PDF]Diagnosing & Mitigating Constraint Induced Response Collapse in Instruction-Tuned LLMs▼4.5k2.67
[PDF]Understanding the theoretical properties of projected Bellman equation, linear Q-learning, and approximate value iteration▲3942.67
Withdrawn or desk rejected (936)
[PDF]When Is a Policy Violation a Model Failure? Policy Observability and Failure Attribution in Agent-Safety EvaluationDesk rejected
[PDF]-Bench: Benchmarking Proactive Speech Interaction with Full-Duplex Conversational AIDesk rejected