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
43 results for “keyword:"multi hop reasoning"” in ICLR 2027. 2 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Bridges over Heavy Hitters: A Causal-HITS Theory and Counterfactual Benchmark for Attention-Graph KV-Cache Compression▲452.75
[PDF]Where Does Reasoning Fail? Attributing Distributed LLM Failures through Critical Evidence▼1.2k1.67
[PDF]Reinforcing Large Vision Language Models for Multi-Hop Reasoning in Lifelong Knowledge Editing▼5.8k2.33
[PDF]Confluence: WHEN DOES CONSERVED-FLOW ROUTING HELP? A COUPLING CONDITION FOR MIXTURE-OF-EXPERTS, WITH A LEGALITY GUARANTEE▼1361.33
[PDF]Language models use both proactive and retroactive mechanisms to make compositional inferences▼4.5k2.67
[PDF]Reasoning or Retrieval? Diagnosing LLM Failures on Temporal Knowledge Graphs with Ground-Truth Evidence▼5.8k2.33
[PDF]From Relevant Fragments to Sufficient Answers: Verifiable Evidence Chains in Long Dialogues▼1361.33
[PDF]Graph-Parameterized Capacity for Latent Multi-Hop Recall: Usage, Compression, and Composition▼13k2.00
[PDF]Adaptive Retrieval and Verification: A Shared Agentic Controller for Cybersecurity RAG and GraphRAG▼1361.33
[PDF]Multi-Token Prediction and Alternative Tokenization Improve Learning Latent Multi-Hop Graph Search at Scale▲153.33
[PDF]AutoScientist: An Autonomous Agent for Long-Horizon Scientific Discovery via Connectome Memory▼1.2k1.67
[PDF]mxSRBench: Towards Spatial Understanding and Diagrammatic Reasoning in mxGraph for Large Language Models▲3.0k2.33
[PDF]Anchoring the Bridge Across Hops: Unlocking Latent Multi-Hop Reasoning under Knowledge Injection▼5.9k2.50
[PDF]Not All Thinking is Created Equal: Latent Reasoning Discovers a Recurrent Search Algorithm for Depth Generalization▲6.1k2.00
[PDF]More Than Correct Answers: Testing, Tracing, and Predicting Multi-Hop Execution in Transformers▲6.1k2.00
[PDF]EvoLinkBench: A Benchmark and Framework for Knowledge Graph Self-Evolution in Memory-Augmented Agents▼1611.50
[PDF]Knowledge Interaction in Hypernetwork-based Continual Learning: Conflict and Composition▲6.1k2.00
[PDF]Retrieving by Frequency, Not Position: Frequency-Division Multiplexed Memory for Structured Retrieval in Language Models▼1361.33
[PDF]DocTrek: Tree-Guided Agentic Reinforcement Learning via Dense Rewards for Document Understanding▼4.3k2.00
[PDF]Does Probe Conditioning Isolate Composition? An Information-Control Audit of Multi-Hop Evaluation▼1361.33
[PDF]The Precision Cliff: An Information-Theoretic Lower Bound on Quantization for Iterative Compositional Retrieval▲11.00