With the increasing adoption of Large Language Models (LLMs), there are proposals to replace human Teaching Assistants (TAs) with LLM-based AI agents for providing feedback to students. In this paper, we explore a new hybrid model where human TAs receive AI-generated feedback for CS1 programming exercises, which they can then review and modify as needed. We conducted a large-scale randomized intervention with 185 CS1 undergraduate students, comparing the efficacy of this hybrid approach against manual feedback and direct AI-generated feedback.

Automated feedback generation for introductory programming assignments is useful for programming education. Most works try to generate feedback to correct a student program by comparing its behavior with an instructor’s reference program on selected tests. In this work, our aim is to generate verifiably correct program repairs as student feedback. A student-submitted program is aligned and composed with a reference solution in terms of control flow, and the variables of the two programs are automatically aligned via predicates describing the relationship between the variables. When verification attempt for the obtained aligned program fails, we turn a verification problem into a MaxSMT problem whose solution leads to a minimal repair. We have conducted experiments on student assignments curated from a widely deployed intelligent tutoring system. Our results show that generating verified repair without sacrificing the overall repair rate is possible. In fact, our implementation, Verifix, is shown to outperform Clara, a state-of-the-art tool, in terms of repair rate. This shows the promise of using verified repair to generate high confidence feedback in programming pedagogy settings.

Block-based visual programming environments play a critical role in introducing computing concepts to K-12 students. One of the key pedagogical challenges in these environments is in designing new practice tasks for a student that match a desired level of difficulty and exercise specific programming concepts. In this paper, we formalize the problem of synthesizing visual programming tasks. In particular, given a reference visual task $\task^{in}$ and its solution code $\code^{in}$, we propose a novel methodology to automatically generate a set $\{(\task^{out}, \code^{out})\}$ of new tasks along with solution codes such that tasks $\task^{in}$ and $\task^{out}$ are conceptually similar but visually dissimilar. Our methodology is based on the realization that the mapping from the space of visual tasks to their solution codes is highly discontinuous; hence, directly mutating reference task $\task^{in}$ to generate new tasks is futile. Our task synthesis algorithm operates by first mutating code $\code^{in}$ to obtain a set of codes $\{\code^{out}\}$. Then, the algorithm performs symbolic execution over a code $\code^{out}$ to obtain a visual task $\task^{out}$; this step uses the Monte Carlo Tree Search (MCTS) procedure to guide the search in the symbolic tree. We demonstrate the effectiveness of our algorithm through an extensive empirical evaluation and user study on reference tasks taken from the Hour of Code: Classic Maze challenge by Code.org and the Intro to Programming with Karel course by CodeHS.com.

We present TEGCER, an automated feedback tool for novice programmers. TEGCER uses supervised classification to match compilation errors in new code submissions with relevant pre-existing errors, submitted by other students before. The dense neural network used to perform this classification task is trained on 15000+ error-repair code examples. The proposed model yields a test set classification Pred@3 accuracy of 97.7% across 212 error category labels. Using this model as its base, TEGCER presents students with the closest relevant examples of solutions for their specific error on demand. A large scale (N>230) usability study shows that students who use TEGCER are able to resolve errors more than 25% faster on average than students being assisted by human tutors.

Automated program repair has been used to provide feedback for incorrect student programming assignments, since program repair captures the code modification needed to make a given buggy program pass a given test-suite. Existing student feedback generation techniques are limited because they either require manual effort in the form of providing an error model, or require a large number of correct student submissions to learn from, or suffer from lack of scalability and accuracy. In this work, we propose a fully automated approach for generating student program repairs in real-time. This is achieved by first re-factoring all available correct solutions to semantically equivalent solutions. Given an incorrect program, we match the program with the closest matching refactored program based on its control flow structure. Subsequently, we infer the input-output specifications of the incorrect program's basic blocks from the executions of the correct program's aligned basic blocks. Finally, these specifications are used to modify the blocks of the incorrect program via search-based synthesis. Our dataset consists of almost 1,800 real-life incorrect Python program submissions from 361 students for an introductory programming course at a large public university. Our experimental results suggest that our method is more effective and efficient than recently proposed feedback generation approaches. About 30% of the patches produced by our tool Refactory are smaller than those produced by the state-of-art tool Clara, and can be produced given fewer correct solutions (often a single correct solution) and in a shorter time. We opine that our method is applicable not only to programming assignments, and could be seen as a general-purpose program repair method that can achieve good results with just a single correct reference solution.

Despite the fact an intelligent tutoring system for programming (ITSP) education has long attracted interest, its widespread use has been hindered by the difficulty of generating personalized feedback automatically. Meanwhile, automated program repair (APR) is an emerging new technology that automatically fixes software bugs, and it has been shown that APR can fix the bugs of large real-world software. In this paper, we study the feasibility of marrying intelligent programming tutoring and APR. We perform our feasibility study with four state-of-the-art APR tools (GenProg, AE, Angelix, and Prophet), and 661 programs written by the students taking an introductory programming course. We found that when APR tools are used out of the box, only about 30% of the programs in our dataset are repaired. This low repair rate is largely due to the student programs often being significantly incorrect - in contrast, professional software for which APR was successfully applied typically fails only a small portion of tests. To bridge this gap, we adopt in APR a new repair policy akin to the hint generation policy employed in the existing ITSP. This new repair policy admits partial repairs that address part of failing tests, which results in 84% improvement of repair rate. We also performed a user study with 263 novice students and 37 graders, and identified an understudied problem; while novice students do not seem to know how to effectively make use of generated repairs as hints, the graders do seem to gain benefits from repairs.

Simple board games, like Tic-Tac-Toe and CONNECT-4, play an important role not only in the development of mathematical and logical skills, but also in the emotional and social development. In this paper, we address the problem of generating targeted starting positions for such games. This can facilitate new approaches for bringing novice players to mastery, and also leads to discovery of interesting game variants. We present an approach that generates starting states of varying hardness levels for player 1 in a two-player board game, given rules of the board game, the desired number of steps required for player 1 to win, and the expertise levels of the two players. Our approach leverages symbolic methods and iterative simulation to efficiently search the extremely large state space. We present experimental results that include discovery of states of varying hardness levels for several simple grid-based board games. The presence of such states for standard game variants like 4 x 4 Tic-Tac-Toe opens up new games to be played that have never been played as the default start state is heavily biased.