Papers by Md. Ashraful Islam
MapCoder: Multi-Agent Code Generation for Competitive Problem Solving (2024.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have impressive proficiency in natural language processing, but performance in code generation tasks remains limited. |
| Approach: | They propose a framework that emulates the full cycle of program synthesis as observed in humans. |
| Outcome: | The proposed framework replicates the full cycle of program synthesis as observed in human developers. |
CodeSim: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debugging (2025.findings-naacl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have made significant strides in code generation and problem solving. |
| Approach: | They propose a multi-agent code generation framework that integrates human-like perception to address the stages of program synthesis. |
| Outcome: | The proposed framework achieves state-of-the-art (pass@1) results and shows potential for even greater enhancement when cascaded with external debuggers. |
Similar Region Search using LLMs on Spatial Feature Space (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing similarity search methods fail to capture contextual richness of spatial data . existing methods fail in capturing regional characteristics, authors say . |
| Approach: | They propose a similar region search framework that ranks candidate regions based on their similarity to a query region using large language models. |
| Outcome: | The proposed similar region search framework outperforms state-of-the-art methods on real-world city datasets. |