15 citations · 24 across the 11 of their papers we have counts for
12 papers
A Near-Zero Monitor Readout Is Not Evidence of Behavioral Control
Zhe Zhou, Tianhua Tao
Post-training with verifiable rewards can induce reward hacking, motivating the use of monitors within the training objective rather than solely for offline auditing. We show that…
Trace-Guided Synthesis of Effectful Test Generators
Zhe Zhou, Ankush Desai, Benjamin Delaware +1
Several recently proposed program logics have incorporated notions of underapproximation into their design, enabling them to reason about reachability rather than safety. In this p…
CharacterFlywheel: Scaling Iterative Improvement of Engaging and Steerable LLMs in Production
Yixin Nie, Lin Guan, Zhongyao Ma +19
This report presents CharacterFlywheel, an iterative flywheel process for improving large language models (LLMs) in production social chat applications across Instagram, WhatsApp,…
SWE-Hub: A Unified Production System for Scalable, Executable Software Engineering Tasks
Yucheng Zeng, Shupeng Li, Daxiang Dong +11
Progress in software-engineering agents is increasingly constrained by the scarcity of executable, scalable, and realistic data for training and evaluation. This scarcity stems fro…
LOGIGEN: Logic-Driven Generation of Verifiable Agentic Tasks
Yucheng Zeng, Weipeng Lu, Linyun Liu +9
The evolution of Large Language Models (LLMs) from static instruction-followers to autonomous agents necessitates operating within complex, stateful environments to achieve precise…
Adaptive Proof Refinement with LLM-Guided Strategy Selection
Minghai Lu, Zhe Zhou, Danning Xie +3
Formal verification via theorem proving enables the expressive specification and rigorous proof of software correctness, but it is difficult to scale due to the significant manual…
From Traces to Program Incorrectness: A Type-Theoretic Approach
Yongwei Yuan, Zhe Zhou, Julia Belyakova +2
We present a type-theoretic framework for reasoning about incorrectness in functional programs that interact with effectful, opaque library APIs. Our approach centers on traces --…
Type-Based Incorrectness Reasoning
Zhe Zhou, Benjamin Delaware, Suresh Jagannathan
A coverage type generalizes refinement types found in many functional languages with support for must-style underapproximate reasoning. Property-based testing frameworks are one pa…
We've Got You Covered: Type-Guided Repair of Incomplete Input Generators
Patrick LaFontaine, Zhe Zhou, Ashish Mishra +2
Property-based testing (PBT) is a popular technique for automatically testing semantic properties of a program, specified as a pair of pre- and post-conditions. The efficacy of thi…
Derivative-Guided Symbolic Execution
Yongwei Yuan, Zhe Zhou, Julia Belyakova +1
We consider the formulation of a symbolic execution (SE) procedure for functional programs that interact with effectful, opaque libraries. Our procedure allows specifications of li…
A HAT Trick: Automatically Verifying Representation Invariants Using Symbolic Finite Automata
Zhe Zhou, Qianchuan Ye, Benjamin Delaware +1
Functional programs typically interact with stateful libraries that hide state behind typed abstractions. One particularly important class of applications are data structure implem…
Data-Driven Abductive Inference of Library Specifications
Zhe Zhou, Robert Dickerson, Benjamin Delaware +1
Programmers often leverage data structure libraries that provide useful and reusable abstractions. Modular verification of programs that make use of these libraries naturally rely…