1 citations · 5 across the 9 of their papers we have counts for
15 papers
Eat Your Precision: Precision Objective Mitigates Reward Hacking in Rubric-based RL
Hyun Ryu, Jong-Heon Kim, Yiqing Xie +3
Rubric-based rewards enable effective reinforcement learning on non-verifiable tasks. However, because these rewards are typically defined as a weighted measure of rubric coverage,…
AdaPRA: Process Reward Agents with Adaptive Rubrics for Data Science
Atharva Naik, Vivek Chari, Pol Llado +5
Data science agents can automate end-to-end machine learning workflows, yet they remain far from competitive on human leaderboards. Agents make process errors such as insufficient…
Ulysses: A Security Harness For Synthesizing Verifiable Web Exploits
Aditya Oke, André Vicente Duarte, Rui Melo +6
How can an AI agent automatically discover security vulnerabilities in any software repository? Existing approaches use LLMs to generate software vulnerability exploits. However, i…
Self-Evolving Static Analysis via LLM Pseudo-Labeling
Rui Melo, Andre Duarte, Aditya Oke +5
Security bugs often slip past static analysis not because they are impossible to detect, but because detection rules have not yet been written for the code in front of us. New fram…
ABSENTIA: Detecting Broken Access Control Vulnerabilities in Web Applications
André V. Duarte, Aditya Oke, Rui Melo +7
Broken access control, the failure of authorization, is one of the most prevalent web security risks. Unlike injection, a flow of untrusted input into a dangerous operation, author…
ReaComp: Compiling LLM Reasoning into Symbolic Solvers for Efficient Program Synthesis
Atharva Naik, Yash Mathur, Prakam +2
LLMs can solve program synthesis tasks but remain inefficient and unreliable on hard instances requiring large combinatorial search. Given a small set of reasoning traces, we use c…
MetaLint: Easy-to-Hard Generalization for Code Linting
Atharva Naik, Lawanya Baghel, Dhakshin Govindarajan +4
Large language models excel at code generation but struggle with code linting, particularly in generalizing to unseen or evolving best practices beyond those observed during traini…
CRScore++: Reinforcement Learning with Verifiable Tool and AI Feedback for Code Review
Manav Nitin Kapadnis, Atharva Naik, Carolyn Rose
Reinforcement learning (RL) to improve code review comment generation requires handling unstructured outputs, making reinforcement learning (RL) feedback challenging. The two main…
An Empirical Study on Strong-Weak Model Collaboration for Repo-level Code Generation
Shubham Gandhi, Atharva Naik, Yiqing Xie +1
We study cost-efficient collaboration between strong and weak language models for repository-level code generation, where the weak model handles simpler tasks at lower cost, and th…
PBEBench: A Multi-Step Programming by Examples Reasoning Benchmark inspired by Historical Linguistics
Atharva Naik, Prakam, Yash Mathur +6
Although many benchmarks evaluate the reasoning abilities of Large Language Models (LLMs) within domains such as mathematics, coding, or data wrangling, few abstract away from doma…
RepoST: Scalable Repository-Level Coding Environment Construction with Sandbox Testing
Yiqing Xie, Alex Xie, Divyanshu Sheth +3
We present RepoST, a scalable method to construct environments that provide execution feedback for repository-level code generation for both training and evaluation. Unlike existin…
Programming by Examples Meets Historical Linguistics: A Large Language Model Based Approach to Sound Law Induction
Atharva Naik, Darsh Agrawal, Hong Sng +8
Historical linguists have long written "programs" that convert reconstructed words in an ancestor language into their attested descendants via ordered string rewrite functions (cal…
CRScore: Grounding Automated Evaluation of Code Review Comments in Code Claims and Smells
Atharva Naik, Marcus Alenius, Daniel Fried +1
The task of automated code review has recently gained a lot of attention from the machine learning community. However, current review comment evaluation metrics rely on comparisons…
CodeBenchGen: Creating Scalable Execution-based Code Generation Benchmarks
Yiqing Xie, Alex Xie, Divyanshu Sheth +3
To adequately test modern code generation systems, evaluation benchmarks must execute and test the code generated by the system. However, these execution and testing requirements h…
Data Augmentation for Code Translation with Comparable Corpora and Multiple References
Yiqing Xie, Atharva Naik, Daniel Fried +1
One major challenge of translating code between programming languages is that parallel training data is often limited. To overcome this challenge, we present two data augmentation…