Language Model (LM)-based agents remain challenging to evaluate systematically in mixed-motive settings where agents must leverage short-term cooperation for long-term competitive goals (e.g., multi-party politics). We introduce Cooperate to Compete (C2C), a multi-agent environment where players can engage in private negotiations while competing to be the first to achieve their secret objective. Players have asymmetric objectives and negotiations are non-binding, allowing alliances to form and break as players’ short-term interests align and diverge. We run AI-only games and conduct a user study pitting human players against AI opponents. We find that humans favor lower-complexity deals and talk to more unique partners over the course of the game. We also find that humans are more aggressive negotiators, closing deals only 73.5% of the time compared to 94.0% for LM-based agents. Interventions inspired by these findings shift agent negotiation behavior and can raise win rates from 22.2% to 32.7%, demonstrating that language coordination strategies in C2C substantially alter negotiation dynamics. We run over 1,300 games with over 20,000 private conversations totaling over 180,000 player actions. By combining multi-party, long-horizon play with partial observability, asymmetric objectives, and non-binding negotiations, C2C provides a controlled, gamified testbed for studying strategic coordination in LM-based agents.

Evaluating Artificial Intelligence (AI) tutor feedback before deployment requires anticipating student engagement, typically assessed through real interaction data. We introduce ParaStudent, a fine-tuning framework for simulating novice programming revisions to support AI tutor evaluation. Compared with prompted baselines, ParaStudent’s revisions more closely match real student code distributions across functional, stylistic, and semantic metrics. Our best variant achieves AUCs of 0.80 for both feedback relevance and successful uptake when distinguishing streams with real engagement above versus at or below the median, while prompted baselines remain near chance on successful uptake. These findings demonstrate the promise of simulated engagement for pre-deployment feedback triage.

Students learning algorithms often need support as they interpret traces, debug reasoning errors, and apply procedures across unfamiliar problem instances. In this paper, we present KITE (Knowledge-Informed Tutoring Engine), a Retrieval-Augmented Generation (RAG)-based intelligent tutoring system designed to serve as a classroom teaching assistant for algorithmic reasoning and problem-solving tasks. KITE uses an intent-aware Socratic response strategy to tailor support to different student needs, responding with targeted hints, guiding questions, and progressive scaffolding intended to strengthen students’ algorithmic problem-solving ability. To keep responses aligned with course content, KITE uses a multimodal RAG pipeline that retrieves relevant information from course materials. We evaluate KITE using three forms of assessment: RAGAs-based metrics for response grounding and quality, expert evaluation of pedagogical quality, and a simulated student pipeline in which a weaker language model interacts with KITE across two-turn dialogues and produces revised answers after receiving feedback. Results indicate that KITE produces contextually grounded and pedagogically appropriate responses. Further, using simulated students, KITE’s feedback helped the student models produce more accurate follow-up responses on procedural and tracing questions, suggesting that its scaffolding can support algorithmic problem-solving. This work contributes a tutoring architecture and an evaluation approach for assessing retrieval-grounded explanations and scaffolded problem-solving feedback.

When programming students encounter errors in their code, compiler messages or static analysis output often provide limited guidance, particularly for novice programmers. Personalized feedback from instructors can be effective but does not scale well. Recent advances in large language models (LLMs) enable automated feedback generation at scale.This study examines whether LLM-generated feedback with different levels of guidance is associated with differences in students’ problem-solving behavior. We analyze effects on time to solution and number of attempts, and examine whether these effects differ by programming experience. We design three feedback types and compare them to a baseline in which students receive only compiler error messages. Results from an online programming course show that LLM-generated feedback is associated with faster time to solution compared to the no-feedback baseline, with less guided feedback showing slightly stronger effects. Overall, the findings suggest that feedback structure plays an important role in how students progress toward correct solutions and motivate further work on adaptive feedback designs and longer-term learning outcomes.

We compare traditional machine-learning models and instruction-tuned Gemma 3 models for identifying knowledge components from student code. On 1,800 GPT-4o-annotated Dart submissions, feature-based ML is more accurate and substantially faster than LLM approaches. Joint multi-KC prompting also suffers from format failures, highlighting deployment-oriented advantages of traditional ML.

We perform the natural language generation (NLG) task by mapping sets of Resource Description Framework (RDF) triples into text. First we investigate the impact of increasing the number of entity types in delexicalisaiton on the generation quality. Second we conduct different experiments to evaluate two widely applied language generation systems, encoder-decoder with attention and the Transformer model on a large benchmark dataset. We evaluate different models on automatic metrics, as well as the training time. To our knowledge, we are the first to apply Transformer model to this task.