AIConfPaper
← Search

Subbarao Kambhampati

25 accepted papers

2026

Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!

Subbarao Kambhampati, Karthik Valmeekam, Siddhant Bhambri, Vardhan Palod, Lucas Saldyt, Kaya Stechly +3
ICML 2026poster

Intermediate token generation (ITG), where a model produces output before the solution, has become a standard method to improve the performance of language models on reasoning tasks. These intermediate tokens have been called \say{reasoning traces} or even \say{thoughts} -- implicitly anthropomorphi…

Cited by 39Source ↗Scholar ↗
2025

Explain It as Simple as Possible, but No Simpler – Explanation via Model Simplification for Addressing Inferential Gap (Abstract Reprint)

Sarath Sreedharan, Siddharth Srivastava, Subbarao Kambhampati
IJCAI 2025

One of the core challenges of explaining decisions made by modern AI systems is the need to address the potential gap in the inferential capabilities of the system generating the decision and the user trying to make sense of it. This inferential capability gap becomes even more critical when it come

Cited by 0Source ↗PDF ↗Scholar ↗
2025

On the self-verification limitations of large language models on reasoning and planning tasks

Kaya Stechly, Karthik Valmeekam, Subbarao Kambhampati
ICLR 2025poster

There has been considerable divergence of opinion on the reasoning abilities of Large Language Models (LLMs). While the initial optimism that reasoning might emerge automatically with scale has been tempered thanks to a slew of counterexamples--ranging from multiplication to simple planning--there p…

Cited by 57Source ↗PDF ↗Scholar ↗
2024

Chain of Thoughtlessness? An Analysis of CoT in Planning

Kaya Stechly, Karthik Valmeekam, Subbarao Kambhampati
NeurIPS 2024poster

Large language model (LLM) performance on reasoning problems typically does not generalize out of distribution. Previous work has claimed that this can be mitigated with chain of thought prompting--a method of demonstrating solution procedures--with the intuition that it is possible to in-context te…

Cited by 47Source ↗PDF ↗Scholar ↗
2024

Learning from Ambiguous Demonstrations with Self-Explanation Guided Reinforcement Learning

Yantian Zha, Lin Guan, Subbarao Kambhampati
AAAI 2024technical

Our work aims at efficiently leveraging ambiguous demonstrations for the training of a reinforcement learning (RL) agent. An ambiguous demonstration can usually be interpreted in multiple ways, which severely hinders the RL agent from learning stably and efficiently. Since an optimal demonstration m…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

Position: LLMs Can’t Plan, But Can Help Planning in LLM-Modulo Frameworks

Subbarao Kambhampati, Karthik Valmeekam, Lin Guan, Mudit Verma, Kaya Stechly, Siddhant Bhambri +2
ICML 2024spotlight

We argue that auto-regressive LLMs cannot, by themselves, do planning or self-verification (which is after all a form of reasoning), and shed some light on the reasons for misunderstandings in the literature. We will also argue that LLMs should be viewed as universal approximate knowledge sources th…

Cited by 192Source ↗PDF ↗Scholar ↗
2024

‘Why Didn’t You Allocate This Task to Them?’ Negotiation-Aware Task Allocation and Contrastive Explanation Generation

Zahra Zahedi, Sailik Sengupta, Subbarao Kambhampati
AAAI 2024technical

In this work, we design an Artificially Intelligent Task Allocator (AITA) that proposes a task allocation for a team of humans. A key property of this allocation is that when an agent with imperfect knowledge (about their teammate's costs and/or the team's performance metric) contests the allocation…

Cited by 12Source ↗PDF ↗Scholar ↗
2023

Gradient-Based Mixed Planning with Symbolic and Numeric Action Parameters (Extended Abstract)

Kebing Jin, Hankz Hankui Zhuo, Zhanhao Xiao, Hai Wan, Subbarao Kambhampati
IJCAI 2023poster

Dealing with planning problems with both logical relations and numeric changes in real-world dynamic environments is challenging. Existing numeric planning systems for the problem often discretize numeric variables or impose convex constraints on numeric variables, which harms the performance when s…

Cited by 0Source ↗PDF ↗Scholar ↗
2023

Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning

Lin Guan, Karthik Valmeekam, Sarath Sreedharan, Subbarao Kambhampati
NeurIPS 2023poster

There is a growing interest in applying pre-trained large language models (LLMs) to planning problems. However, methods that use LLMs directly as planners are currently impractical due to several factors, including limited correctness of plans, strong reliance on feedback from interactions with simu…

Cited by 201Source ↗PDF ↗code ↗Scholar ↗
2023

On the Planning Abilities of Large Language Models - A Critical Investigation

Karthik Valmeekam, Matthew Marquez, Sarath Sreedharan, Subbarao Kambhampati
NeurIPS 2023spotlight

Intrigued by the claims of emergent reasoning capabilities in LLMs trained on general web corpora, in this paper, we set out to investigate their planning capabilities. We aim to evaluate (1) the effectiveness of LLMs in generating plans autonomously in commonsense planning tasks and (2) the potenti…

Cited by 280Source ↗PDF ↗Scholar ↗
2023

PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change

Karthik Valmeekam, Matthew Marquez, Alberto Olmo, Sarath Sreedharan, Subbarao Kambhampati
NeurIPS 2023poster

Generating plans of action, and reasoning about change have long been considered a core competence of intelligent agents. It is thus no surprise that evaluating the planning and reasoning capabilities of large language models (LLMs) has become a hot topic of research. Most claims about LLM planning…

Cited by 191Source ↗PDF ↗code ↗Scholar ↗
2023

Relative Behavioral Attributes: Filling the Gap between Symbolic Goal Specification and Reward Learning from Human Preferences

Lin Guan, Karthik Valmeekam, Subbarao Kambhampati
ICLR 2023poster

Generating complex behaviors that satisfy the preferences of non-expert users is a crucial requirement for AI agents. Interactive reward learning from trajectory comparisons (a.k.a. RLHF) is one way to allow non-expert users to convey complex objectives by expressing preferences over short clips of…

Cited by 13Source ↗PDF ↗code ↗Scholar ↗
2022

Bridging the Gap: Providing Post-Hoc Symbolic Explanations for Sequential Decision-Making Problems with Inscrutable Representations

Sarath Sreedharan, Utkarsh Soni, Mudit Verma, Siddharth Srivastava, Subbarao Kambhampati
ICLR 2022poster

As increasingly complex AI systems are introduced into our daily lives, it becomes important for such systems to be capable of explaining the rationale for their decisions and allowing users to contest these decisions. A significant hurdle to allowing for such explanatory dialogue could be the {\em…

Cited by 42Source ↗PDF ↗Scholar ↗
2022

Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity

Lin Guan, Sarath Sreedharan, Subbarao Kambhampati
ICML 2022spotlight

Creating reinforcement learning (RL) agents that are capable of accepting and leveraging task-specific knowledge from humans has been long identified as a possible strategy for developing scalable approaches for solving long-horizon problems. While previous works have looked at the possibility of us…

Cited by 28Source ↗PDF ↗code ↗Scholar ↗
2022

On the Computational Complexity of Model Reconciliations

Sarath Sreedharan, Pascal Bercher, Subbarao Kambhampati
IJCAI 2022poster

Model-reconciliation explanation is a popular framework for generating explanations for planning problems. While the framework has been extended to multiple settings since its introduction for classical planning problems, there is little agreement on the computational complexity of generating minima…

Cited by 10Source ↗PDF ↗Scholar ↗
2021

A Unifying Bayesian Formulation of Measures of Interpretability in Human-AI Interaction

Sarath Sreedharan, Anagha Kulkarni, David Smith, Subbarao Kambhampati
IJCAI 2021poster

Existing approaches for generating human-aware agent behaviors have considered different measures of interpretability in isolation. Further, these measures have been studied under differing assumptions, thus precluding the possibility of designing a single framework that captures these measures unde…

Cited by 19Source ↗PDF ↗Scholar ↗
2021

Not all users are the same: Providing personalized explanations for sequential decision making problems

Utkarsh Soni, Sarath Sreedharan, Subbarao Kambhampati
IROS 2021poster

There is a growing interest in designing robots that can work alongside humans. Such robots will undoubtedly be expected to explain their behavior and decisions. While generating explanations is an actively researched topic, most works tend to focus on methods that generate explanations that are one…

Cited by 10Source ↗Scholar ↗
2021

Widening the Pipeline in Human-Guided Reinforcement Learning with Explanation and Context-Aware Data Augmentation

Lin Guan, Mudit Verma, Sihang Guo, Ruohan Zhang, Subbarao Kambhampati
NeurIPS 2021spotlight

Human explanation (e.g., in terms of feature importance) has been recently used to extend the communication channel between human and agent in interactive machine learning. Under this setting, human trainers provide not only the ground truth but also some form of explanation. However, this kind of h…

Cited by 50Source ↗PDF ↗Scholar ↗
2020

Designing Environments Conducive to Interpretable Robot Behavior

Anagha Kulkarni, Sarath Sreedharan, Sarah Keren, Tathagata Chakraborti, David E. Smith, Subbarao Kambhampati
IROS 2020poster

Designing robots capable of generating interpretable behavior is essential for effective human-robot collaboration. This requires robots to be able to generate behavior that aligns with human expectations but exhibiting such behavior in arbitrary environments could be quite expensive for robots, and…

Cited by 29Source ↗Scholar ↗
2020

The Emerging Landscape of Explainable Automated Planning & Decision Making

Tathagata Chakraborti, Sarath Sreedharan, Subbarao Kambhampati
IJCAI 2020poster

In this paper, we provide a comprehensive outline of the different threads of work in Explainable AI Planning (XAIP) that has emerged as a focus area in the last couple of years and contrast that with earlier efforts in the field in terms of techniques, target users, and delivery mechanisms. We hope…

Cited by 0Source ↗PDF ↗Scholar ↗
2018

Projection-Aware Task Planning and Execution for Human-in-the-Loop Operation of Robots in a Mixed-Reality Workspace

Tathagata Chakraborti, Sarath Sreedharan, Anagha Kulkarni, Subbarao Kambhampati
IROS 2018poster

Recent advances in mixed-reality technologies have renewed interest in alternative modes of communication for human-robot interaction. However, most of the work in this direction has been confined to tasks such as teleoperation, simulation or explication of individual actions of a robot. In this pap…

Cited by 73Source ↗Scholar ↗
2017

Plan explicability and predictability for robot task planning

Yu Zhang, Sarath Sreedharan, Anagha Kulkarni, Tathagata Chakraborti, Hankz Hankui Zhuo, Subbarao Kambhampati
ICRA 2017poster

Intelligent robots and machines are becoming pervasive in human populated environments. A desirable capability of these agents is to respond to goal-oriented commands by autonomously constructing task plans. However, such autonomy can add significant cognitive load and potentially introduce safety r…

Cited by 227Source ↗Scholar ↗
2015

A human factors analysis of proactive support in human-robot teaming

Yu Zhang, Vignesh Narayanan, Tathagata Chakraborti, Subbarao Kambhampati
IROS 2015poster

It has long been assumed that for effective human-robot teaming, it is desirable for assistive robots to infer the goals and intents of the humans, and take proactive actions to help them achieve their goals. However, there has not been any systematic evaluation of the accuracy of this claim. On the…

Cited by 42Source ↗Scholar ↗
2015

Planning for serendipity

Tathagata Chakraborti, Gordon Briggs, Kartik Talamadupula, Yu Zhang, Matthias Scheutz, David Smith +1
IROS 2015poster

Recently there has been a lot of focus on human robot co-habitation issues that are often orthogonal to many aspects of human-robot teaming; e.g. on producing socially acceptable behaviors of robots and de-conflicting plans of robots and humans in shared environments. However, an interesting offshoo…

Cited by 60Source ↗Scholar ↗