AI Reasoning

Feeds to Scour
SubscribedAll
Scoured 45 posts in 12.3 ms

CRANE: Knowledge Editing for Reasoning MLLMs

 ✍️Prompt Engineering  Content type: Academic
arxiv.org·

When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models

 ✍️Prompt Engineering  Content type: Academic
arxiv.org·

avibe-bot/avibe: The local-first Agent OS — your AI partner lives on your own machine. Drive the official Claude Code, Codex & OpenCode from your browser or any chat app.

 ⌨️CLI Tools  Content type: Code
github.com··Hacker News

Tight Sample Complexity of Transformers

 ✍️Prompt Engineering  Content type: Academic
arxiv.org·

SafeRun: Enabling Determinism in LLM Planning for Running

 💬LLMs  Content type: Academic
arxiv.org·

TARPO: Token-Wise Latent-Explicit Reasoning via Action-Routing Policy Optimization

 🎮Reinforcement Learning  Content type: Academic
arxiv.org·

SSR: Can Simulated Patients Learn to Stigmatize Themselves? Modeling Self-Stigma through Internal Monologue

 ✍️Prompt Engineering  Content type: Academic
arxiv.org·

Latent Reasoning with Normalizing Flows

 ✍️Prompt Engineering  Content type: Academic
arxiv.org·

When No Answer Is Correct: Diagnosing Absent Answer Detection for MLLMs in Video Understanding

 ✍️Prompt Engineering  Content type: Academic
arxiv.org·

Entity Binding Failures in Speech LLM Reasoning: Diagnosis and Chain-of-Thought Intervention

 ✍️Prompt Engineering  Content type: Academic
arxiv.org·

BEACON: Behavioral Entropy Aggregation for Cross-Model Hallucination Detection in Large Language Models

 ✍️Prompt Engineering  Content type: Academic
arxiv.org·

Invariant Gradient Alignment for Robust Reasoning Distillation

 ✍️Prompt Engineering  Content type: Academic
arxiv.org·

LoRi: Low-Rank Distillation for Implicit Reasoning

 ✍️Prompt Engineering  Content type: Academic
arxiv.org·

Beyond tokens: a unified framework for latent communication in LLM-based multi-agent systems

 ✍️Prompt Engineering  Content type: Academic
arxiv.org·

You Only Index Once: Cross-Layer Sparse Attention with Shared Routing

 ✍️Prompt Engineering  Content type: Academic
arxiv.org·

How Small Can You Go? LoRA Fine-Tuning 270M-8B Models for Merchant Information Extraction in Financial Transactions

 💬LLMs  Content type: Academic
arxiv.org·

Solving Zebra Puzzles Using Constraint-Guided Multi-Agent Systems

 ✍️Prompt Engineering  Content type: Academic
arxiv.org·

MPCoT: Reward-Guided Multi-Path Latent Reasoning for Test-Time Scalable Vision-Language-Action

 ✍️Prompt Engineering  Content type: Academic
arxiv.org·

Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization

 ✍️Prompt Engineering  Content type: Academic
arxiv.org·

Hint Tuning: Less Data Makes Better Reasoners

 ✍️Prompt Engineering  Content type: Academic
arxiv.org·

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help