Aria: An Agent For Retrieval and Iterative Auto-Formalization via Dependency Graph
arxiv.org·5h
⚡Proof Automation
Towards a Typology of LLM Chains-of-Thought
1a3orn.com·14h·
Discuss: Hacker News
🌳Context free grammars
DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization
arxiv.org·5h
🎯Performance Proofs
Detecting Distillation Data from Reasoning Models
arxiv.org·5h
⚙️ABNF Mining
Design Principle: Composable Services
sleepingpotato.com·19h·
Discuss: Hacker News
⚡gRPC
Java Backend Coding Technology: Writing Code in the Era of AI #Version 1.1
dev.to·13h·
Discuss: DEV
⚡SMT Applications
FocusMed: A Large Language Model-based Framework for Enhancing Medical Question Summarization with Focus Identification
arxiv.org·5h
🔍Information Retrieval
How to Train an LLM to Do Proofs: Beyond Verifiable Rewards
tobysimonds.com·2d·
Discuss: Hacker News
🎯Interactive Provers
Property-based testing of batch-invariant operations
mmaaz.ca·1d·
Discuss: Hacker News
🧪Property-Based Testing
Is Odin Just a More Boring C?
dayvster.com·22h·
Discuss: Hacker News
🔩Systems Programming
ProofOfThought: LLM-based reasoning using Z3 theorem proving
dev.to·1d·
Discuss: DEV
⚡SMT Integration
The Debate on RLVR Reasoning Capability Boundary: Shrinkage, Expansion, or Both? A Two-Stage Dynamic View
arxiv.org·5h
🎯Proof Tactics
Constraint Satisfaction Approaches to Wordle: Novel Heuristics and Cross-Lexicon Validation
arxiv.org·1d
🧮SMT Solvers
Read the Scene, Not the Script: Outcome-Aware Safety for LLMs
arxiv.org·5h
🔗Parser Combinators
Distilling Reasoning into Student LLMs: Local Naturalness for Selecting Teacher Data
arxiv.org·5h
💻Local LLMs
Rigorous Evaluation of Microarchitectural Side-Channels with Statistical Model Checking
arxiv.org·1d
🔧Hardware Verification
PsycholexTherapy: Simulating Reasoning in Psychotherapy with Small Language Models in Persian
arxiv.org·5h
💻Programming languages
Learning to Route: A Rule-Driven Agent Framework for Hybrid-Source Retrieval-Augmented Generation
arxiv.org·1d
🔍Information Retrieval
MedReflect: Teaching Medical LLMs to Self-Improve via Reflective Correction
arxiv.org·5h
💻Local LLMs
Operationalizing Data Minimization for Privacy-Preserving LLM Prompting
arxiv.org·5h
💻Local LLMs