Bhrij Patel

Bhrij Patel, Kasun Weerakoon, Wesley A. Suttle et al.

Reinforcement learning (RL) is a promising approach for robotic navigation, allowing robots to learn through trial and error. However, real-world robotic tasks often suffer from sparse rewards, leading to inefficient exploration and suboptimal policies due to sample inefficiency of RL. In this work, we introduce Confidence-Controlled Exploration (CCE), a novel method that improves sample efficiency in RL-based robotic navigation without modifying the reward function. Unlike existing approaches, such as entropy regularization and reward shaping, which can introduce instability by altering rewards, CCE dynamically adjusts trajectory length based on policy entropy. Specifically, it shortens trajectories when uncertainty is high to enhance exploration and extends them when confidence is high to prioritize exploitation. CCE is a principled and practical solution inspired by a theoretical connection between policy entropy and gradient estimation. It integrates seamlessly with on-policy and off-policy RL methods and requires minimal modifications. We validate CCE across REINFORCE, PPO, and SAC in both simulated and real-world navigation tasks. CCE outperforms fixed-trajectory and entropy-regularized baselines, achieving an 18\% higher success rate, 20-38\% shorter paths, and 9.32\% lower elevation costs under a fixed training sample budget. Finally, we deploy CCE on a Clearpath Husky robot, demonstrating its effectiveness in complex outdoor environments.

Bhrij Patel, Souradip Chakraborty, Mengdi Wang et al.

Large Language Models (LLMs) for unsupervised code correctness evaluation have recently gained attention because they can judge if code runs as intended without requiring reference implementations or unit tests, which may be unavailable, sparse, or unreliable. However, most prior approaches condition LLM evaluators directly on the full code implementation, forcing the model to jointly infer program behavior and evaluate correctness in a single step. This entanglement leads to misinterpretations of code behavior and unreliable judgments. To mitigate this issue, we introduce CoCoA, an unsupervised Code Comprehension then Auditing framework that first comprehends functionality to generate a natural-language explanation. Then it evaluates task alignment based on this explanation. By sequentially sampling comprehension before evaluation, CoCoA improves the quality of inferred program behavior and enables the evaluator to focus on behavioral alignment rather than raw implementation details. Across multiple datasets, programming languages, and models, CoCoA achieves up to $68\%$ increased F1 score and up to $20\%$ increased accuracy over the best-performing baselines.

Wesley A. Suttle, Amrit Singh Bedi, Bhrij Patel et al.

Many existing reinforcement learning (RL) methods employ stochastic gradient iteration on the back end, whose stability hinges upon a hypothesis that the data-generating process mixes exponentially fast with a rate parameter that appears in the step-size selection. Unfortunately, this assumption is violated for large state spaces or settings with sparse rewards, and the mixing time is unknown, making the step size inoperable. In this work, we propose an RL methodology attuned to the mixing time by employing a multi-level Monte Carlo estimator for the critic, the actor, and the average reward embedded within an actor-critic (AC) algorithm. This method, which we call \textbf{M}ulti-level \textbf{A}ctor-\textbf{C}ritic (MAC), is developed especially for infinite-horizon average-reward settings and neither relies on oracle knowledge of the mixing time in its parameter selection nor assumes its exponential decay; it, therefore, is readily applicable to applications with slower mixing times. Nonetheless, it achieves a convergence rate comparable to the state-of-the-art AC algorithms. We experimentally show that these alleviated restrictions on the technical conditions required for stability translate to superior performance in practice for RL problems with sparse rewards.

Bhrij Patel, Davide Belli, Amir Jalalirad et al.

Function calling agents powered by Large Language Models (LLMs) select external tools to automate complex tasks. On-device agents typically use a retrieval module to select relevant tools, improving performance and reducing context length. However, existing retrieval methods rely on static and limited inputs, failing to capture multi-step tool dependencies and evolving task context. This limitation often introduces irrelevant tools that mislead the agent, degrading efficiency and accuracy. We propose Dynamic Tool Dependency Retrieval (DTDR), a lightweight retrieval method that conditions on both the initial query and the evolving execution context. DTDR models tool dependencies from function calling demonstrations, enabling adaptive retrieval as plans unfold. We benchmark DTDR against state-of-the-art retrieval methods across multiple datasets and LLM backbones, evaluating retrieval precision, downstream task accuracy, and computational efficiency. Additionally, we explore strategies to integrate retrieved tools into prompts. Our results show that dynamic tool retrieval improves function calling success rates between $23\%$ and $104\%$ compared to state-of-the-art static retrievers.

Bhrij Patel, Wesley A. Suttle, Alec Koppel et al.

In the context of average-reward reinforcement learning, the requirement for oracle knowledge of the mixing time, a measure of the duration a Markov chain under a fixed policy needs to achieve its stationary distribution, poses a significant challenge for the global convergence of policy gradient methods. This requirement is particularly problematic due to the difficulty and expense of estimating mixing time in environments with large state spaces, leading to the necessity of impractically long trajectories for effective gradient estimation in practical applications. To address this limitation, we consider the Multi-level Actor-Critic (MAC) framework, which incorporates a Multi-level Monte-Carlo (MLMC) gradient estimator. With our approach, we effectively alleviate the dependency on mixing time knowledge, a first for average-reward MDPs global convergence. Furthermore, our approach exhibits the tightest available dependence of $\mathcal{O}\left( \sqrt{τ_{mix}} \right)$known from prior work. With a 2D grid world goal-reaching navigation experiment, we demonstrate that MAC outperforms the existing state-of-the-art policy gradient-based method for average reward settings.

Bhrij Patel, Ashish Jagmohan, Aditya Vempaty

Digital tool-based agents, powered by Large Language Models (LLMs), that invoke external Application Programming Interfaces (APIs) often rely on documentation to understand API functionality. However, such documentation is frequently missing, outdated, privatized, or inconsistent-hindering the development of reliable, general-purpose agents. In this work, we propose a new research direction: learning of API functionality directly from in-context demonstrations. This task is a new paradigm applicable in scenarios without documentation. Using API benchmarks, we collect demonstrations from both expert agents and from self-exploration. To understand what information demonstrations must convey for successful task completion, we extensively study how the number of demonstrations and the use of LLM-generated summaries and evaluations affect the task success rate of the API-based agent. Our experiments across 3 datasets and 6 models show that learning functionality from in-context demonstrations remains a non-trivial challenge, even for state-of-the-art LLMs. We find that providing explicit function calls and natural language critiques significantly improves the agent's task success rate due to more accurate parameter filling. We analyze failure modes, identify sources of error, and highlight key open challenges for future work in documentation-free, self-improving, API-based agents.

Bhrij Patel, Vishnu Sashank Dorbala, Amrit Singh Bedi et al.

Large language models (LLMs) have grown in popularity due to their natural language interface and pre trained knowledge, leading to rapidly increasing success in question-answering (QA) tasks. More recently, multi-agent systems with LLM-based agents (Multi-LLM) have been utilized increasingly more for QA. In these scenarios, the models may each answer the question and reach a consensus or each model is specialized to answer different domain questions. However, most prior work dealing with Multi-LLM QA has focused on scenarios where the models are asked in a zero-shot manner or are given information sources to extract the answer. For question answering of an unknown environment, embodied exploration of the environment is first needed to answer the question. This skill is necessary for personalizing embodied AI to environments such as households. There is a lack of insight into whether a Multi-LLM system can handle question-answering based on observations from embodied exploration. In this work, we address this gap by investigating the use of Multi-Embodied LLM Explorers (MELE) for QA in an unknown environment. Multiple LLM-based agents independently explore and then answer queries about a household environment. We analyze different aggregation methods to generate a single, final answer for each query: debating, majority voting, and training a central answer module (CAM). Using CAM, we observe a $46\%$ higher accuracy compared against the other non-learning-based aggregation methods. We provide code and the query dataset for further research.

Vishnu Sashank Dorbala, Bhrij Patel, Amrit Singh Bedi et al.

Embodied navigation methods commonly operate in static environments with stationary targets. In this work, we present a new algorithm for navigation in dynamic scenarios with non-stationary targets. Our novel Transit-Aware Strategy (TAS) enriches embodied navigation policies with object path information. TAS improves performance in non-stationary environments by rewarding agents for synchronizing their routes with target routes. To evaluate TAS, we further introduce Dynamic Object Maps (DOMs), a dynamic variant of node-attributed topological graphs with structured object transitions. DOMs are inspired by human habits to simulate realistic object routes on a graph. Our experiments show that on average, TAS improves agent Success Rate (SR) by 21.1 in non-stationary environments, while also generalizing better from static environments by 44.5% when measured by Relative Change in Success (RCS). We qualitatively investigate TAS-agent performance on DOMs and draw various inferences to help better model generalist navigation policies. To the best of our knowledge, ours is the first work that quantifies the adaptability of embodied navigation methods in non-stationary environments. Code and data for our benchmark will be made publicly available.

Caroline Wang, Bin Han, Bhrij Patel et al.

Objectives: We study interpretable recidivism prediction using machine learning (ML) models and analyze performance in terms of prediction ability, sparsity, and fairness. Unlike previous works, this study trains interpretable models that output probabilities rather than binary predictions, and uses quantitative fairness definitions to assess the models. This study also examines whether models can generalize across geographic locations. Methods: We generated black-box and interpretable ML models on two different criminal recidivism datasets from Florida and Kentucky. We compared predictive performance and fairness of these models against two methods that are currently used in the justice system to predict pretrial recidivism: the Arnold PSA and COMPAS. We evaluated predictive performance of all models on predicting six different types of crime over two time spans. Results: Several interpretable ML models can predict recidivism as well as black-box ML models and are more accurate than COMPAS or the Arnold PSA. These models are potentially useful in practice. Similar to the Arnold PSA, some of these interpretable models can be written down as a simple table. Others can be displayed using a set of visualizations. Our geographic analysis indicates that ML models should be trained separately for separate locations and updated over time. We also present a fairness analysis for the interpretable models. Conclusions: Interpretable machine learning models can perform just as well as non-interpretable methods and currently-used risk assessment scales, in terms of both prediction accuracy and fairness. Machine learning models might be more accurate when trained separately for distinct locations and kept up-to-date.