Unified Software Engineering agent as AI Software Engineer
Paper
•
2506.14683
•
Published
•
1
Lin Tan
lin-tan
AI & ML interests
AI-Software Synergy. LLM4Code (binary and source code).
Mary J. Elmore New Frontiers Professor
Purdue University
Recent Activity
upvoted
a
paper
12 days ago
Unified Software Engineering agent as AI Software Engineer
commented on
a paper
3 months ago
CORE: Benchmarking LLMs Code Reasoning Capabilities through Static
Analysis Tasks
Organizations
upvoted
a
paper
12 days ago
upvoted
a
paper
3 months ago
commented
a
paper
3 months ago
upvoted
a
paper
3 months ago
authored
3
papers
3 months ago
Unified Software Engineering agent as AI Software Engineer
Paper
•
2506.14683
•
Published
•
1
CORE: Benchmarking LLMs Code Reasoning Capabilities through Static Analysis Tasks
Paper
•
2507.05269
•
Published
•
1
TENET: Leveraging Tests Beyond Validation for Code Generation
Paper
•
2509.24148
•
Published
•
3
commented
a
paper
3 months ago
upvoted
a
paper
3 months ago
liked
a
dataset
3 months ago
updated
a
Space
3 months ago
upvoted
a
paper
5 months ago
liked
2
datasets
5 months ago
replied to
their
post
7 months ago
This paper has now been accepted to ACL 2025!
replied to
their
post
8 months ago
SELP is an ICRA 2025 Best Paper Award Finalist, among a selected few from 4,153 submissions!
replied to
their
post
10 months ago
We have added Qwen results on RepoCod Lite https://lt-asset.github.io/REPOCOD/#lite We have also got DeepSeek v3, OpenAI o1, and o3-mini results on RepoCod Lite. DeepSeek V3 outperforms o1 and o3-mini and has the best performance on RepoCod LITE.
reacted to
their
post with 👍
10 months ago
Post
3380
🚀 Excited to share that our paper, "SELP: Generating Safe and Efficient Task Plans for Robot Agents with Large Language Models", has been accepted to #ICRA2025! 🔗 Preprint: https://arxiv.org/pdf/2409.19471
We introduce SELP (Safe Efficient LLM Planner), a novel approach for generating plans that adhere to user-specified constraints while optimizing for time-efficient execution. By leveraging linear temporal logic (LTL) to interpret natural language commands, SELP effectively handles complex commands and long-horizon tasks. 🤖
💡SELP presents three key insights:
1️⃣ Equivalence Voting: Ensures robust translations from natural language instructions into LTL specifications.
2️⃣ Constrained Decoding: Uses the generated LTL formula to guide the autoregressive inference of plans, ensuring the generated plans conform to the LTL.
3️⃣ Domain-Specific Fine-Tuning: Customizes LLMs for specific robotic tasks, boosting both safety and efficiency.
📊 Experiment: Our experiments demonstrate SELP’s effectiveness and generalizability across diverse tasks. In drone navigation, SELP outperforms state-of-the-art LLM planners by 10.8% in safety rate and by 19.8% in plan efficiency. For robot manipulation, SELP achieves a 20.4% improvement in safety rate.
@yiwu @jiang719
#ICRA2025 #LLM #Robotics #Agent #LLMPlanner
We introduce SELP (Safe Efficient LLM Planner), a novel approach for generating plans that adhere to user-specified constraints while optimizing for time-efficient execution. By leveraging linear temporal logic (LTL) to interpret natural language commands, SELP effectively handles complex commands and long-horizon tasks. 🤖
💡SELP presents three key insights:
1️⃣ Equivalence Voting: Ensures robust translations from natural language instructions into LTL specifications.
2️⃣ Constrained Decoding: Uses the generated LTL formula to guide the autoregressive inference of plans, ensuring the generated plans conform to the LTL.
3️⃣ Domain-Specific Fine-Tuning: Customizes LLMs for specific robotic tasks, boosting both safety and efficiency.
📊 Experiment: Our experiments demonstrate SELP’s effectiveness and generalizability across diverse tasks. In drone navigation, SELP outperforms state-of-the-art LLM planners by 10.8% in safety rate and by 19.8% in plan efficiency. For robot manipulation, SELP achieves a 20.4% improvement in safety rate.
@yiwu @jiang719
#ICRA2025 #LLM #Robotics #Agent #LLMPlanner
-
- 3 replies
reacted to
their
post with 🔥
11 months ago
Post
3380
🚀 Excited to share that our paper, "SELP: Generating Safe and Efficient Task Plans for Robot Agents with Large Language Models", has been accepted to #ICRA2025! 🔗 Preprint: https://arxiv.org/pdf/2409.19471
We introduce SELP (Safe Efficient LLM Planner), a novel approach for generating plans that adhere to user-specified constraints while optimizing for time-efficient execution. By leveraging linear temporal logic (LTL) to interpret natural language commands, SELP effectively handles complex commands and long-horizon tasks. 🤖
💡SELP presents three key insights:
1️⃣ Equivalence Voting: Ensures robust translations from natural language instructions into LTL specifications.
2️⃣ Constrained Decoding: Uses the generated LTL formula to guide the autoregressive inference of plans, ensuring the generated plans conform to the LTL.
3️⃣ Domain-Specific Fine-Tuning: Customizes LLMs for specific robotic tasks, boosting both safety and efficiency.
📊 Experiment: Our experiments demonstrate SELP’s effectiveness and generalizability across diverse tasks. In drone navigation, SELP outperforms state-of-the-art LLM planners by 10.8% in safety rate and by 19.8% in plan efficiency. For robot manipulation, SELP achieves a 20.4% improvement in safety rate.
@yiwu @jiang719
#ICRA2025 #LLM #Robotics #Agent #LLMPlanner
We introduce SELP (Safe Efficient LLM Planner), a novel approach for generating plans that adhere to user-specified constraints while optimizing for time-efficient execution. By leveraging linear temporal logic (LTL) to interpret natural language commands, SELP effectively handles complex commands and long-horizon tasks. 🤖
💡SELP presents three key insights:
1️⃣ Equivalence Voting: Ensures robust translations from natural language instructions into LTL specifications.
2️⃣ Constrained Decoding: Uses the generated LTL formula to guide the autoregressive inference of plans, ensuring the generated plans conform to the LTL.
3️⃣ Domain-Specific Fine-Tuning: Customizes LLMs for specific robotic tasks, boosting both safety and efficiency.
📊 Experiment: Our experiments demonstrate SELP’s effectiveness and generalizability across diverse tasks. In drone navigation, SELP outperforms state-of-the-art LLM planners by 10.8% in safety rate and by 19.8% in plan efficiency. For robot manipulation, SELP achieves a 20.4% improvement in safety rate.
@yiwu @jiang719
#ICRA2025 #LLM #Robotics #Agent #LLMPlanner
-
-
- 3 replies
posted
an
update
11 months ago
Post
3380
🚀 Excited to share that our paper, "SELP: Generating Safe and Efficient Task Plans for Robot Agents with Large Language Models", has been accepted to #ICRA2025! 🔗 Preprint: https://arxiv.org/pdf/2409.19471
We introduce SELP (Safe Efficient LLM Planner), a novel approach for generating plans that adhere to user-specified constraints while optimizing for time-efficient execution. By leveraging linear temporal logic (LTL) to interpret natural language commands, SELP effectively handles complex commands and long-horizon tasks. 🤖
💡SELP presents three key insights:
1️⃣ Equivalence Voting: Ensures robust translations from natural language instructions into LTL specifications.
2️⃣ Constrained Decoding: Uses the generated LTL formula to guide the autoregressive inference of plans, ensuring the generated plans conform to the LTL.
3️⃣ Domain-Specific Fine-Tuning: Customizes LLMs for specific robotic tasks, boosting both safety and efficiency.
📊 Experiment: Our experiments demonstrate SELP’s effectiveness and generalizability across diverse tasks. In drone navigation, SELP outperforms state-of-the-art LLM planners by 10.8% in safety rate and by 19.8% in plan efficiency. For robot manipulation, SELP achieves a 20.4% improvement in safety rate.
@yiwu @jiang719
#ICRA2025 #LLM #Robotics #Agent #LLMPlanner
We introduce SELP (Safe Efficient LLM Planner), a novel approach for generating plans that adhere to user-specified constraints while optimizing for time-efficient execution. By leveraging linear temporal logic (LTL) to interpret natural language commands, SELP effectively handles complex commands and long-horizon tasks. 🤖
💡SELP presents three key insights:
1️⃣ Equivalence Voting: Ensures robust translations from natural language instructions into LTL specifications.
2️⃣ Constrained Decoding: Uses the generated LTL formula to guide the autoregressive inference of plans, ensuring the generated plans conform to the LTL.
3️⃣ Domain-Specific Fine-Tuning: Customizes LLMs for specific robotic tasks, boosting both safety and efficiency.
📊 Experiment: Our experiments demonstrate SELP’s effectiveness and generalizability across diverse tasks. In drone navigation, SELP outperforms state-of-the-art LLM planners by 10.8% in safety rate and by 19.8% in plan efficiency. For robot manipulation, SELP achieves a 20.4% improvement in safety rate.
@yiwu @jiang719
#ICRA2025 #LLM #Robotics #Agent #LLMPlanner
-
-
- 3 replies