Related papers: SwiftSolve: A Self-Iterative, Complexity-Aware Mul…

Large Language Models (LLMs) have shown remarkable capabilities as autonomous agents, yet existing benchmarks either focus on single-agent tasks or are confined to narrow domains, failing to capture the dynamics of multi-agent coordination…

The integration of Large Language Models (LLMs) into software engineering has driven a transition from traditional rule-based systems to autonomous agentic systems capable of solving complex problems. However, systematic progress is…

Large Language Model (LLM) agents are rapidly improving to handle increasingly complex web-based tasks. Most of these agents rely on general-purpose, proprietary models like GPT-4 and focus on designing better prompts to improve their…

Large-scale LP problems from industry usually contain much redundancy that severely hurts the efficiency and reliability of solving LPs, making presolve (i.e., the problem simplification module) one of the most critical components in modern…

Superoptimization is the task of transforming a program into a faster one while preserving its input-output behavior. In this work, we investigate whether large language models (LLMs) can serve as superoptimizers, generating assembly…

The rapid advancement of large language models has opened new avenues for automating complex problem-solving tasks such as algorithmic coding and competitive programming. This paper introduces a novel evaluation technique, LLM-ProS, to…

With software maintenance accounting for 50% of the cost of developing software, enhancing code quality and reliability has become more critical than ever. In response to this challenge, this doctoral research proposal aims to explore…

Instructed code editing is a significant challenge for large language models (LLMs). On the EditBench benchmark, 39 of 40 evaluated models obtain a task success rate (TSR) below 60 percent, highlighting a gap between general code generation…

Large language models (LLMs) have empowered AI agents to tackle increasingly complex tasks. However, most existing agents remain limited to static planning and brittle interactions, falling short of true collaboration or adaptive reasoning.…

We introduce AgenticSimLaw, a role-structured, multi-agent debate framework that provides transparent and controllable test-time reasoning for high-stakes tabular decision-making tasks. Unlike black-box approaches, our courtroom-style…

We present SWE-Lego, a supervised fine-tuning (SFT) recipe designed to achieve state-ofthe-art performance in software engineering (SWE) issue resolving. In contrast to prevalent methods that rely on complex training paradigms (e.g.,…

Large Language Models (LLMs) have demonstrated impressive capabilities in natural language and code generation, and are increasingly deployed as automatic judges of model outputs and learning activities. Yet, their behavior on structured…

While scaling training compute has led to remarkable improvements in large language models (LLMs), scaling inference compute has not yet yielded analogous gains. We hypothesize that a core missing component is a lack of diverse LLM outputs,…

Scaling test-time computation improves large language model performance without additional training. Recent work demonstrates that techniques such as repeated sampling, self-verification, and self-reflection can significantly enhance task…

A promising research direction in enabling LLMs to generate consistently correct code involves addressing their inability to properly estimate program execution, particularly for code they generate. In this work, we demonstrate that Code…

Test-time scaling (TTS) enhances the performance of large language models (LLMs) by allocating additional compute resources during inference. However, existing research primarily investigates TTS in single-stage tasks; while many real-world…

From professional research to everyday planning, many tasks are bottlenecked by wide-scale information seeking, which is more repetitive than cognitively complex. With the rapid development of Large Language Models (LLMs), automated search…

Code efficiency is a fundamental aspect of software quality, yet how to harness large language models (LLMs) to optimize programs remains challenging. Prior approaches have sought for one-shot rewriting, retrieved exemplars, or prompt-based…

Multi-robot task planning requires decomposing natural-language instructions into executable actions for heterogeneous robot teams. Conventional Planning Domain Definition Language (PDDL) planners provide rigorous guarantees but struggle to…

Verifiers play a crucial role in large language model (LLM) reasoning, needed by post-training techniques such as reinforcement learning. However, reliable verifiers are hard to get for difficult coding problems, because a well-disguised…