Publications
A full list of my peer-reviewed conference proceedings, journal articles, and workshop papers in Automated Planning, Reinforcement Learning, Generative AI, and Human-AI Interaction. You can also view my live citation metrics on Google Scholar Profile.
Key Highlights:- 🏆 Best Industry Paper Award — ACM International Conference on AI in Finance (ICAIF 2023)
- 🎙️ Oral Presentation (Top 2% of accepted papers) — AAAI Conference on Artificial Intelligence (AAAI-24)
- 🎖️ Top Performer — DARPA SAIL-ON Novelty Handling in Open World Environments
Workshop on Planning in the Era of LLMs at the International Conference on Automated Planning and Scheduling (ICAPS-26) (2026)
Explores foundational challenges and opportunities in using automated planning to orchestrate stochastic generative AI agents.
Citation: Daneshi, R., Patra, S., Dwarakanath, K., Gopalakrishnan, S., Borrajo, D., & Sreedharan, S. (2026). The curious case of planning for unreliable agents: Challenges and opportunities in orchestrating generative AI agents. In Workshop on Planning in the Era of LLMs at ICAPS-26. Paper
NeurIPS Workshop on Bridging Language, Agent, and World Models (2025) (2025)
Unifies large language models with world models and symbolic planning engines to generate and verify executable plan trajectories.
Citation: Borrajo, D., Canonaco, G., de la Rosa, T., Garrachón, A., Gopalakrishnan, S., Kaur, S., & Veloso, M. (2025). GenPlanX: Generation of plans and execution. In NeurIPS Workshop on Bridging Language, Agent, and World Models.
NeurIPS Workshop on Efficient Reasoning (2025) (2025)
Introduces scalable pipelines to synthesize natural language reasoning benchmarks grounded in formal Boolean satisfiability (SAT) domains.
Citation: Patra, S., Ramani, K., Borrajo, D., & Gopalakrishnan, S. (2025). Generating domain specific natural language SAT reasoning datasets. In NeurIPS Workshop on Efficient Reasoning.
Proceedings of the European Conference on Artificial Intelligence (ECAI 2025) (2025)
Formulates inverse optimization algorithms to learn implicit action costs from human and expert plan demonstrations.
Citation: Morales, M., Pozanco, A., Canonaco, G., Gopalakrishnan, S., Borrajo, D., & Veloso, M. (2025). On learning action costs from input plans. In Proceedings of the European Conference on Artificial Intelligence (ECAI).
arXiv preprint arXiv:2406.10196 (2024) (2024)
A hybrid architecture marrying the fluid natural-language understanding of LLMs with the formal correctness guarantees of classical automated planning for travel itinerary synthesis.
Citation: de la Rosa, T., Gopalakrishnan, S., Pozanco, A., Zeng, Z., & Borrajo, D. (2024). TRIP-PAL: Travel planning with guarantees by combining large language models and automated planners. arXiv:2406.10196. Paper
🎙️ Oral Presentation (Top 2% of accepted papers)
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI-24) (2024)
Introduces SafeAR, a risk-aware sequential recourse framework that accounts for stochastic execution and minimizes downside risk via Conditional Value-at-Risk (CVaR) objectives.
Citation: Wu, H., Sharma, S., Patra, S., & Gopalakrishnan, S. (2024). SafeAR: Towards Safer Algorithmic Recourse by Risk-Aware Policies. In Proceedings of the AAAI Conference on Artificial Intelligence. Paper
Advances in Neural Information Processing Systems (NeurIPS 2023) (2023)
Addresses constrained time-series generation by combining diffusion models with non-convex optimization to guarantee domain constraints.
Citation: Coletta, A., Gopalakrishnan, S., Borrajo, D., & Vyetrenko, S. (2023). On the Constrained Time-Series Generation Problem. In Advances in Neural Information Processing Systems (NeurIPS). Paper
🏆 Best Industry Paper Award (ICAIF 2023)
Proceedings of the 4th ACM International Conference on AI in Finance (ICAIF 2023) (2023)
Presents a multi-modal projection framework to align financial text, news, and multivariate market time-series in a joint latent space for semantic retrieval.
Citation: Bamford, T., Coletta, A., Fons, E., Gopalakrishnan, S., Vyetrenko, S., Balch, T., & Veloso, M. (2023). Multi-Modal Financial Time-Series Retrieval Through Latent Space Projections. In Proceedings of the 4th ACM International Conference on AI in Finance. Paper
ICAPS Workshop on Planning and Reinforcement Learning (PRL 2023) (2023)
Introduces an open-source Python toolkit bridging symbolic RDDL domain specifications with modern OpenAI Gym / Gymnasium environments.
Citation: Taitler, A., Gimelfarb, M., Jeong, J., Gopalakrishnan, S., Mladenov, M., Liu, X., & Sanner, S. (2023). pyRDDLGym: From RDDL to Gym Environments. In ICAPS PRL Workshop. Paper
ICAPS Workshop on Planning for Financial Services (FinPlan 2023) (2023)
Explores expressing complex quantitative finance and portfolio management benchmarks within the RDDL planning framework.
Citation: Patra, S., Mahfouz, M., Gopalakrishnan, S., Magazzeni, D., & Veloso, M. (2023). FinRDDL: Can AI Planning be used for Quantitative Finance Problems? In ICAPS FinPlan Workshop. Paper
Proceedings of the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2023) (2023)
Proposes interactive architectures and novelty detection mechanisms for autonomous agents operating in adversarial game settings.
Citation: Thai, T., Verma, M., Soni, U., Gopalakrishnan, S., Shen, M., Garg, M., & Scheutz, M. (2023). Methods and Mechanisms for Interactive Novelty Handling in Adversarial Environments. In Proceedings of the 22nd International Conference on Autonomous Agents and MultiAgent Systems. Paper
Proceedings of the 32nd International Conference on Automated Planning and Scheduling (ICAPS 2022) (2022)
Develops algorithms for decentralized task assignment and prioritization under execution duration uncertainty and human context-switching costs.
Citation: Gopalakrishnan, S., & Borrajo, D. (2022). Assignment and Prioritization Of Tasks With Uncertain Durations For Satisfying Makespans In Decentralized Execution. In Proceedings of the 32nd International Conference on Automated Planning and Scheduling. Paper
Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2022) (2022)
Formulates graph reduction techniques to maximize human observer predictability of robot motion and destinations.
Citation: Gopalakrishnan, S., & Kambhampati, S. (2022). Minimizing Robot Navigation-Graph For Position-Based Predictability By Humans. In Proceedings of the 21st International Conference on Autonomous Agents and MultiAgent Systems. Paper
ICAPS Workshop on Explainable AI in Planning (XAIP 2021) (2021)
Synthesizes sequential decision policies that explicitly anticipate and mitigate human execution errors arising from perceptual confusion.
Citation: Gopalakrishnan, S., Verma, S., & Kambhampati, S. (2021). Synthesizing Policies That Account For Human Execution Errors Caused By State Aliasing In Markov Decision Processes. In ICAPS XAIP Workshop. Paper
🎖️ Top Performer in DARPA SAIL-ON Monopoly Program
ICAPS Workshop on Integrating Planning and Execution (IntEx 2021) (2021)
Designs a hybrid agent architecture combining symbolic planning, execution monitoring, and reinforcement learning capable of adapting to unexpected open-world novelties.
Citation: Gopalakrishnan, S., Soni, U., Thai, T., Lymperopoulos, P., Scheutz, M., & Kambhampati, S. (2021). Integrating Planning, Execution and Monitoring in the Presence of Open World Novelties: Case Study of an Open World Monopoly Solver. In ICAPS IntEx Workshop. Paper
ICAPS Workshop on Planning for Financial Services (FinPlan 2020) (2020)
Investigates combining model-driven planning representations with data-driven machine learning models to identify user financial intentions.
Citation: Borrajo, D., Gopalakrishnan, S., & Potluru, V. (2020). Goal Recognition via Model-based and Model-free Techniques. In ICAPS FinPlan Workshop. Paper
Proceedings of the 13th Annual Symposium on Combinatorial Search (SOCS 2020) (2020)
Presents FastMap-D, a fast polynomial-time heuristic for embedding asymmetric, directed graphs into potential fields for accelerated shortest-path queries.
Citation: Gopalakrishnan, S., Cohen, L., Koenig, S., & Kumar, T. S. (2020). Embedding Directed Graphs in Potential Fields Using FastMap-D. In Proceedings of the 13th Annual Symposium on Combinatorial Search. Paper
System Demonstration & Extended Abstract, ICAPS 2019 (2019)
Demonstrates an interactive visualization tool mapping complex state-space planning traces into lower-dimensional embeddings for human interpretability.
Citation: Gopalakrishnan, S., & Kambhampati, S. (2019). TGE-viz: Transition Graph Embedding for Visualization of Plan Traces and Domains. In ICAPS System Demonstrations. Paper
ICAPS Workshop on Explainable AI in Planning (XAIP 2019) (2019)
Introduces active learning strategies guided by domain feature attributions to query human domain experts efficiently during model acquisition.
Citation: Gopalakrishnan, S., Soni, U., & Kambhampati, S. (2019). Feature Directed Active Learning. In ICAPS XAIP Workshop. Paper
Proceedings of the 17th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2018) (2018)
Formulates continuous representation learning on action sequence distributions for plan recognition without requiring full domain models.
Citation: Zha, Y., Li, Y., Gopalakrishnan, S., Li, B., & Kambhampati, S. (2018). Recognizing Plans by Learning Embeddings from Observed Action Distributions. In Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems. Paper
AI Communications Journal, 31(2): 119-137 (2018) (2018)
Presents Word2HTN and semantic embedding algorithms to discover Hierarchical Task Networks (HTN) from unannotated plan traces and natural language descriptors.
Citation: Gopalakrishnan, S., Muñoz-Avila, H., & Kuter, U. (2018). Learning Task Hierarchies Using Statistical Semantics and Goal Reasoning. AI Communications, 31(2), 119-137. Paper
IEEE Conference on Computational Intelligence and Games (CIG 2017) (2017)
Applies automated HTN learning algorithms to synthesize high-level agent decision hierarchies in Minecraft.
Citation: Nguyen, C., Reifsnyder, N., Gopalakrishnan, S., & Muñoz-Avila, H. (2017). Automated Learning of Hierarchical Task Networks for Controlling Minecraft Agents. In IEEE CIG. Paper
4th Workshop on Goal Reasoning at IJCAI 2016 (2016)
Leverages word embedding representations to cluster task actions and learn HTN methods from plan traces.
Citation: Gopalakrishnan, S., Muñoz-Avila, H., & Kuter, U. (2016). Word2HTN: Learning Task Hierarchies Using Statistical Semantics and Goal Reasoning. In IJCAI Goal Reasoning Workshop. Paper
