We use cookies to analyze the browsing and usage of our website and to personalize your experience. You can disable these technologies at any time, but this may limit certain functionalities of the site. Read our Privacy Policy for more information.
Setting cookies
You can enable and disable the types of cookies you wish to accept. However certain choices you make could affect the services offered on our sites (e.g. suggestions, personalised ads, etc.).
Essential cookies
These cookies are necessary for the operation of the site and cannot be deactivated. (Still active)
Analytics cookies
Do you accept the use of cookies to measure the audience of our sites?
Multimedia Player
Do you accept the use of cookies to display and allow you to watch the video content hosted by our partners (YouTube, etc.)?
Publications
Harnessing Pre-trained Generalist Agents for Software Engineering Tasks
Nowadays, we are witnessing an increasing adoption of Artificial Intelligence (AI) to develop techniques aimed at improving the reliability,… (see more) effectiveness, and overall quality of software systems. Deep reinforcement learning (DRL) has recently been successfully used for automation in complex tasks such as game testing and solving the job-shop scheduling problem. However, these specialized DRL agents, trained from scratch on specific tasks, suffer from a lack of generalizability to other tasks and they need substantial time to be developed and re-trained effectively. Recently, DRL researchers have begun to develop generalist agents, able to learn a policy from various environments and capable of achieving performances similar to or better than specialist agents in new tasks. In the Natural Language Processing or Computer Vision domain, these generalist agents are showing promising adaptation capabilities to never-before-seen tasks after a light fine-tuning phase and achieving high performance. This paper investigates the potential of generalist agents for solving SE tasks. Specifically, we conduct an empirical study aimed at assessing the performance of two generalist agents on two important SE tasks: the detection of bugs in games (for two games) and the minimization of makespan in a scheduling task, to solve the job-shop scheduling problem (for two instances). Our results show that the generalist agents outperform the specialist agents with very little effort for fine-tuning, achieving a 20% reduction of the makespan over specialized agent performance on task-based scheduling. In the context of game testing, some generalist agent configurations detect 85% more bugs than the specialist agents. Building on our analysis, we provide recommendations for researchers and practitioners looking to select generalist agents for SE tasks, to ensure that they perform effectively.
Describing skills in natural language has the potential to provide an accessible way to inject human knowledge about decision-making into an… (see more) AI system. We present MaestroMotif, a method for AI-assisted skill design, which yields high-performing and adaptable agents. MaestroMotif leverages the capabilities of Large Language Models (LLMs) to effectively create and reuse skills. It first uses an LLM's feedback to automatically design rewards corresponding to each skill, starting from their natural language description. Then, it employs an LLM's code generation abilities, together with reinforcement learning, for training the skills and combining them to implement complex behaviors specified in language. We evaluate MaestroMotif using a suite of complex tasks in the NetHack Learning Environment (NLE), demonstrating that it surpasses existing approaches in both performance and usability.
Describing skills in natural language has the potential to provide an accessible way to inject human knowledge about decision-making into an… (see more) AI system. We present MaestroMotif, a method for AI-assisted skill design, which yields high-performing and adaptable agents. MaestroMotif leverages the capabilities of Large Language Models (LLMs) to effectively create and reuse skills. It first uses an LLM's feedback to automatically design rewards corresponding to each skill, starting from their natural language description. Then, it employs an LLM's code generation abilities, together with reinforcement learning, for training the skills and combining them to implement complex behaviors specified in language. We evaluate MaestroMotif using a suite of complex tasks in the NetHack Learning Environment (NLE), demonstrating that it surpasses existing approaches in both performance and usability.
We present TapeAgents, an agent framework built around a granular, structured log tape of the agent session that also plays the role of the … (see more)session's resumable state. In TapeAgents we leverage tapes to facilitate all stages of the LLM Agent development lifecycle. The agent reasons by processing the tape and the LLM output to produce new thought and action steps and append them to the tape. The environment then reacts to the agent's actions by likewise appending observation steps to the tape. By virtue of this tape-centred design, TapeAgents can provide AI practitioners with holistic end-to-end support. At the development stage, tapes facilitate session persistence, agent auditing, and step-by-step debugging. Post-deployment, one can reuse tapes for evaluation, fine-tuning, and prompt-tuning; crucially, one can adapt tapes from other agents or use revised historical tapes. In this report, we explain the TapeAgents design in detail. We demonstrate possible applications of TapeAgents with several concrete examples of building monolithic agents and multi-agent teams, of optimizing agent prompts and finetuning the agent's LLM. We present tooling prototypes and report a case study where we use TapeAgents to finetune a Llama-3.1-8B form-filling assistant to perform as well as GPT-4o while being orders of magnitude cheaper. Lastly, our comparative analysis shows that TapeAgents's advantages over prior frameworks stem from our novel design of the LLM agent as a resumable, modular state machine with a structured configuration, that generates granular, structured logs and that can transform these logs into training text -- a unique combination of features absent in previous work.
We present TapeAgents, an agent framework built around a granular, structured log tape of the agent session that also plays the role of the … (see more)session's resumable state. In TapeAgents we leverage tapes to facilitate all stages of the LLM Agent development lifecycle. The agent reasons by processing the tape and the LLM output to produce new thought and action steps and append them to the tape. The environment then reacts to the agent's actions by likewise appending observation steps to the tape. By virtue of this tape-centred design, TapeAgents can provide AI practitioners with holistic end-to-end support. At the development stage, tapes facilitate session persistence, agent auditing, and step-by-step debugging. Post-deployment, one can reuse tapes for evaluation, fine-tuning, and prompt-tuning; crucially, one can adapt tapes from other agents or use revised historical tapes. In this report, we explain the TapeAgents design in detail. We demonstrate possible applications of TapeAgents with several concrete examples of building monolithic agents and multi-agent teams, of optimizing agent prompts and finetuning the agent's LLM. We present tooling prototypes and report a case study where we use TapeAgents to finetune a Llama-3.1-8B form-filling assistant to perform as well as GPT-4o while being orders of magnitude cheaper. Lastly, our comparative analysis shows that TapeAgents's advantages over prior frameworks stem from our novel design of the LLM agent as a resumable, modular state machine with a structured configuration, that generates granular, structured logs and that can transform these logs into training text -- a unique combination of features absent in previous work.
We present TapeAgents, an agent framework built around a granular, structured log tape of the agent session that also plays the role of the … (see more)session's resumable state. In TapeAgents we leverage tapes to facilitate all stages of the LLM Agent development lifecycle. The agent reasons by processing the tape and the LLM output to produce new thought and action steps and append them to the tape. The environment then reacts to the agent's actions by likewise appending observation steps to the tape. By virtue of this tape-centred design, TapeAgents can provide AI practitioners with holistic end-to-end support. At the development stage, tapes facilitate session persistence, agent auditing, and step-by-step debugging. Post-deployment, one can reuse tapes for evaluation, fine-tuning, and prompt-tuning; crucially, one can adapt tapes from other agents or use revised historical tapes. In this report, we explain the TapeAgents design in detail. We demonstrate possible applications of TapeAgents with several concrete examples of building monolithic agents and multi-agent teams, of optimizing agent prompts and finetuning the agent's LLM. We present tooling prototypes and report a case study where we use TapeAgents to finetune a Llama-3.1-8B form-filling assistant to perform as well as GPT-4o while being orders of magnitude cheaper. Lastly, our comparative analysis shows that TapeAgents's advantages over prior frameworks stem from our novel design of the LLM agent as a resumable, modular state machine with a structured configuration, that generates granular, structured logs and that can transform these logs into training text -- a unique combination of features absent in previous work.
Synthetic biology holds great promise for bioengineering applications such as environmental bioremediation, probiotic formulation, and produ… (see more)ction of renewable biofuels. Humans’ capacity to design biological systems from scratch is limited by their sheer size and complexity. We introduce a framework for training a machine learning model to learn the basic genetic principles underlying the gene composition of bacterial genomes. Our variational autoencoder model, DeepGenomeVector, was trained to take as input corrupted bacterial genetic blueprints (i.e. complete gene sets, henceforth ‘genome vectors’) in which most genes had been “removed”, and re-create the original. The resulting model effectively captures the complex dependencies in genomic networks, as evaluated by both qualitative and quantitative metrics. An in-depth functional analysis of a generated gene vector shows that its encoded pathways are interconnected and nearly complete. On the test set, where the model’s ability to re-generate the original, uncorrupted genome vector was evaluated, an AUC score of 0.98 and an F1 score of 0.82 provide support for the model’s ability to generate diverse, high-quality genome vectors. This work showcases the power of machine learning approaches for synthetic biology and highlights the possibility that just as humans can design an AI that animates a robot, AIs may one day be able to design a genomic blueprint that animates a carbon-based cell. SIGNIFICANCE STATEMENT Genomes serve as the blueprints for life, encoding complex networks of genes whose products must seamlessly interact to result in living organisms. In this work, we develop a framework for training a machine learning algorithm to learn the basic genetic principles that underlie genome composition. This innovation may eventually lead to improvements in the genome design process, increasing the speed and reliability of designs while decreasing cost. It further suggests that AI agents may one day have the potential to design blueprints for carbon-based life.
2024-12-11
Proceedings of the Royal Society B: Biological Sciences (published)
Imitation learning is a data-driven approach to learning policies from expert behavior, but it is prone to unreliable outcomes in out-of-sam… (see more)ple (OOS) regions. While previous research relying on stable dynamical systems guarantees convergence to a desired state, it often overlooks transient behavior. We propose a framework for learning policies using modeled by contractive dynamical systems, ensuring that all policy rollouts converge regardless of perturbations, and in turn, enable efficient OOS recovery. By leveraging recurrent equilibrium networks and coupling layers, the policy structure guarantees contractivity for any parameter choice, which facilitates unconstrained optimization. Furthermore, we provide theoretical upper bounds for worst-case and expected loss terms, rigorously establishing the reliability of our method in deployment. Empirically, we demonstrate substantial OOS performance improvements in robotics manipulation and navigation tasks in simulation.
While one commonly trains large diffusion models by collecting datasets on target downstream tasks, it is often desired to align and finetun… (see more)e pretrained diffusion models on some reward functions that are either designed by experts or learned from small-scale datasets. Existing methods for finetuning diffusion models typically suffer from lack of diversity in generated samples, lack of prior preservation, and/or slow convergence in finetuning. Inspired by recent successes in generative flow networks (GFlowNets), a class of probabilistic models that sample with the unnormalized density of a reward function, we propose a novel GFlowNet method dubbed Nabla-GFlowNet (abbreviated as
While one commonly trains large diffusion models by collecting datasets on target downstream tasks, it is often desired to align and finetun… (see more)e pretrained diffusion models on some reward functions that are either designed by experts or learned from small-scale datasets. Existing methods for finetuning diffusion models typically suffer from lack of diversity in generated samples, lack of prior preservation, and/or slow convergence in finetuning. Inspired by recent successes in generative flow networks (GFlowNets), a class of probabilistic models that sample with the unnormalized density of a reward function, we propose a novel GFlowNet method dubbed Nabla-GFlowNet (abbreviated as
