arxiv:2507.19457
Lakshya A Agrawal
LakshyAAAgrawal
·
AI & ML interests
AI for Code, Large Language Models, Programming Languages, Transpilers and Systems
Recent Activity
authored
a paper
14 days ago
Why Do Multi-Agent LLM Systems Fail?
authored
a paper
14 days ago
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
upvoted
a
paper
14 days ago
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Organizations
models
16
LakshyAAAgrawal/ToolHop_Agent-mopt-qwen_GRPO_qwen3-8b_devset
8B
•
Updated
•
5
LakshyAAAgrawal/Papillon_PAPILLON-mopt-llama_GRPO_llama31-8b-instruct_devset
8B
•
Updated
•
3
LakshyAAAgrawal/Papillon_PAPILLON-mopt-qwen_GRPO_qwen3-8b_devset
8B
•
Updated
•
3
LakshyAAAgrawal/Banking77_ChainOfThought_mipro-GRPO_llama31-8b-instruct_devset
8B
•
Updated
•
2
LakshyAAAgrawal/Banking77_CoT-mopt-qwen_mipro-GRPO_qwen3-8b_devset
8B
•
Updated
•
3
LakshyAAAgrawal/Banking77_CoT-mopt-llama_mipro-GRPO_llama31-8b-instruct_devset
8B
•
Updated
•
3
LakshyAAAgrawal/ToolHop_Agent-mopt-llama_GRPO_llama31-8b-instruct_devset
8B
•
Updated
•
3
LakshyAAAgrawal/Banking77_ChainOfThought_mipro-GRPO_qwen3-8b_devset
8B
•
Updated
•
3
LakshyAAAgrawal/Papillon_PAPILLON_GRPO_qwen3-8b_devset
8B
•
Updated
•
3
LakshyAAAgrawal/Banking77_CoT-mopt-llama_GRPO_llama31-8b-instruct_devset
8B
•
Updated
•
3
datasets
0
None public yet