No article text was recorded for this version.
multi-hop reasoning decay
Version 2 of 2624 papers929 conceptsfrozen 2026-10-04
Papers in this version
- Blog: LooGLE v2: Are LLMs Ready for Real World Long Dependency Challenges?
- Blog: Reasoning Models Lose their Way with Long Deduction
- Blog: Exploring the Limitations of Large Language Models in Compositional Relation Reasoning
- Blog: Deceiving Semantic Shortcuts on Reasoning Chains: How Far Can Models Go without Hallucination?
- Blog: SPARTA: Scalable and Principled Benchmark of Tree-Structured Multi-hop QA over Text and Tables
- Blog: ACCORD: Closing the Commonsense Measurability Gap
- Blog: GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
- Blog: Towards Understanding Factual Knowledge of Large Language Models
- Blog: Evaluating Commonsense in Pre-trained Language Models
- Blog: ConvexBench: Can LLMs Recognize Convex Functions?
- Blog: PHYSICS: Benchmarking Foundation Models on University-Level Physics Problem Solving
- Blog: ConvexBench: Can LLMs Recognize Convex Functions?
- Blog: QLEVR: A Diagnostic Dataset for Quantificational Language and Elementary Visual Reasoning
- Blog: Reasoning-Driven Question-Answering for Natural Language Understanding
- Blog: Does Reasoning Emerge? Examining the Probabilities of Causation in Large Language Models
- Blog: Large Language Models Meet Symbolic Provers for Logical Reasoning Evaluation
- Blog: LegalAgentBench: Evaluating LLM Agents in Legal Domain
- Blog: Exploring and Evaluating Multimodal Knowledge Reasoning Consistency of Multimodal Large Language Models
- Blog: Exploring and Evaluating Multimodal Knowledge Reasoning Consistency of Multimodal Large Language Models
- Blog: We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning
- Blog: Liar, Liar, Logical Mire: A Benchmark for Suppositional Reasoning in Large Language Models
- Blog: Multi-Relational Question Answering from Narratives: Machine Reading and Reasoning in Simulated Worlds
- Blog: A Causal Lens for Evaluating Faithfulness Metrics
- Blog: DecompSR: A dataset for decomposed analyses of compositional multihop spatial reasoning
- Blog: Evaluating LLMs' Mathematical Reasoning in Financial Document Question Answering
- Blog: A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models
- Blog: Transformation Driven Visual Reasoning
- Blog: Empowering LLMs with Logical Reasoning: A Comprehensive Survey
- Blog: What Does My QA Model Know? Devising Controlled Probes using Expert Knowledge
- Blog: AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning
- Blog: DeduCE: Deductive Consistency as a Framework to Evaluate LLM Reasoning
- Blog: A Case Study on the Effectiveness of LLMs in Verification with Proof Assistants
- Blog: M3CoT: A Novel Benchmark for Multi-Domain Multi-step Multi-modal Chain-of-Thought
- Blog: FormulaQA: A Question Answering Dataset for Formula-Based Numerical Reasoning
- Blog: Does Reasoning Emerge? Examining the Probabilities of Causation in Large Language Models
- Blog: Examining the Emergence of Deductive Reasoning in Generative Language Models
- Blog: Logically Consistent Adversarial Attacks for Soft Theorem Provers
- Blog: GeoLaux: A Benchmark for Evaluating MLLMs' Geometry Performance on Long-Step Problems Requiring Auxiliary Lines
- Blog: AGQA 2.0: An Updated Benchmark for Compositional Spatio-Temporal Reasoning
- Blog: Lexical Recall or Logical Reasoning: Probing the Limits of Reasoning Abilities in Large Language Models
- Blog: MathHay: An Automated Benchmark for Long-Context Mathematical Reasoning in LLMs
- Blog: Determining Relative Argument Specificity and Stance for Complex Argumentative Structures
- Blog: Causal Parrots: Large Language Models May Talk Causality But Are Not Causal
- Blog: LogiConBench: Benchmarking Logical Consistencies of LLMs
- Blog: MDCR: A Dataset for Multi-Document Conditional Reasoning
- Blog: Meta-Thinking in LLMs via Multi-Agent Reinforcement Learning: A Survey
- Blog: P-FOLIO: Evaluating and Improving Logical Reasoning with Abundant Human-Written Reasoning Chains
- Blog: New Skills or Sharper Primitives? A Probabilistic Perspective on the Emergence of Reasoning in RLVR
- Blog: Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMs
- Blog: Short-Path Prompting in LLMs: Analyzing Reasoning Instability and Solutions for Robust Performance
- Blog: What Is Missing in Multilingual Visual Reasoning and How to Fix It
- Blog: ResearchRubrics: A Benchmark of Prompts and Rubrics For Evaluating Deep Research Agents
- Blog: LoRA: A Logical Reasoning Augmented Dataset for Visual Question Answering
- Blog: WorldTree V2: A Corpus of Science-Domain Structured Explanations and Inference Patterns supporting Multi-Hop Inference
- Blog: Premise Order Matters in Reasoning with Large Language Models
- Blog: DeepLogic: End-to-End Logical Reasoning
- Blog: QLEVR: A Diagnostic Dataset for Quantificational Language and Elementary Visual Reasoning
- Blog: P-FOLIO: Evaluating and Improving Logical Reasoning with Abundant Human-Written Reasoning Chains
- Blog: On the Eligibility of LLMs for Counterfactual Reasoning: A Decompositional Study
- Blog: Liar, Liar, Logical Mire: A Benchmark for Suppositional Reasoning in Large Language Models
Showing 60 of 624 papers.
History & citation
Current · Permanent link
- Performance Decay Across Multi-hop Relational Chains merged into this direction (92% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_multi_hop_reasoning_decay_b29b7b22,
title = {multi-hop reasoning decay},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/multi-hop-reasoning-decay/rdr_b29b7b22b1ad45cc9e33af8d5fca8f57},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 2, frozen text):
@misc{lacuna_multi_hop_reasoning_decay_b29b7b22_v2,
title = {multi-hop reasoning decay},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/multi-hop-reasoning-decay/rdr_b29b7b22b1ad45cc9e33af8d5fca8f57/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-19},
}