5 papers · 1 filter
Agentic Verified Optimization of Real-World Software
Zhe Ye, Udaya Ghai, Zhizhen Qin +2
Program optimization aims to improve performance while preserving behavior. Coding agents can already make programs faster by changing algorithms, data structures, and execution st…
Instruct, Not Answer: Using Instruction Privileges in On-Policy Context Distillation
Hantao Yu, Sandy Han, Xiaoxue Han +6
On-Policy Context Distillation (OPCD) has recently emerged as a powerful technique for transferring context to student models and for self-improvement. In OPCD, the teacher is cond…
The Bicameral Model: Bidirectional Hidden-State Coupling Between Parallel Language Models
Cedric Flamant, Udaya Ghai, Kanna Shimizu
Existing multi-model and tool-augmented systems communicate by generating text, serializing every exchange through the output vocabulary. Can two pretrained language models instead…
Intent-aligned Formal Specification Synthesis via Traceable Refinement
Zhe Ye, Aidan Z. H. Yang, Huangyuan Su +6
Large language models are increasingly used to generate code from natural language, but ensuring correctness remains challenging. Formal verification offers a principled way to obt…
Learning Adaptive LLM Decoding
Chloe H. Su, Zhe Ye, Samuel Tenka +3
Decoding from large language models (LLMs) typically relies on fixed sampling hyperparameters (e.g., temperature, top-p), despite substantial variation in task difficulty and uncer…