Papers with suboptimal reasoning
Test-Time Strategies for More Efficient and Accurate Agentic RAG (2026.acl-srw)
Copied to clipboard
Abhinav Sharma, Brian Zhang, Deepti Guntur, Zhiyang Zuo, Shreyas Chaudhari, Wenlong Zhao, Franck Dernoncourt, Puneet Mathur, Ryan A. Rossi, Nedim Lipka
| Challenge: | Retrieval-Augmented Generation (RAG) systems face challenges with complex, multi-hop questions. |
| Approach: | They propose to integrate contextualization module and de-duplication module to improve the accuracy of retrieved documents and to reduce the number of turns by 10.5%. |
| Outcome: | The proposed approach achieves a 5.6% increase in EM score and reduces the average number of turns by 10.5% compared to the baseline. |
RAVR: Reference-Answer-guided Variational Reasoning for Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Experiments show that reinforcement learning (RL) can refine the reasoning abilities of large language models (LLMs) but requires a key prerequisite: the model must already be able to generate high-utility reasoning paths with non-negligible probability. |
| Approach: | They propose a framework that uses answer-conditioned reasoning as a variational surrogate for question-only reasoning. |
| Outcome: | Experiments on 11 benchmarks and 3 models show that RAVR reduces hesitation, strengthens conclusion consolidation, and promotes problem-specific strategies in reasoning. |
MAKI: Multi-layer Aligned Knowledge Injection for Structure-aware Knowledge Graph Completion with Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing knowledge graph completion methods struggle to capture structural information in knowledge graphs (KGs) Existing approaches for KGC focus on learning representations of entities and relations through observed structural patterns. |
| Approach: | They propose a multi-layer Aligned Knowledge Injection model that tightly integrates structured KG information into LLMs through multi-layered alignment. |
| Outcome: | The proposed method outperforms state-of-the-art methods on benchmark datasets. |