Peiyang-Song/Awesome-LLM-Reasoning-Failures
Repo for "Large Language Model Reasoning Failures"
This project compiles a detailed list of academic papers focusing on why Large Language Models (LLMs) make errors in reasoning, what causes these failures, and how they can be fixed. It organizes research on LLM limitations across various reasoning types, from everyday social interactions to complex logic and math. Anyone developing, evaluating, or deploying AI applications that rely on LLM outputs would use this to understand and address common pitfalls.
165 stars.
Use this if you are a researcher, AI product manager, or ML engineer who needs to understand the current state of LLM reasoning capabilities and their documented failure modes, guiding more robust AI development.
Not ideal if you are looking for a practical guide or a tool for immediate, hands-on debugging of an LLM in a production environment, as it primarily curates academic literature.
Stars
165
Forks
13
Language
—
License
MIT
Category
Last pushed
Feb 17, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/Peiyang-Song/Awesome-LLM-Reasoning-Failures"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
open-thought/reasoning-gym
[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards
Hmbown/Hegelion
Dialectical reasoning architecture for LLMs (Thesis → Antithesis → Synthesis)
LLM360/Reasoning360
A repo for open research on building large reasoning models
TsinghuaC3I/Awesome-RL-for-LRMs
A Survey of Reinforcement Learning for Large Reasoning Models
bowang-lab/BioReason
BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model | NeurIPS '25