Alexandre Piché

Torsten Scholak

Oleh Shliazhko

Jordan Prince Tremblay

Karam Ghanem

Soham Parikh

Mitul Tiwari

Quaizar Vohra

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.

2024-12-11

ArXiv (preprint)

Thibault Le Sellier De Chezelles

arxiv.org

Fine-Tuning Web Agents: It Works, But It's Trickier Than You Think

Massimo Caccia

Megh Thakkar

Léo Boisvert

Nicolas Chapados

Alexandre Drouin

Maxime Gasse

Alexandre Lacoste

Recent advancements in large language models (LLMs) have sparked interest in developing autonomous web agents capable of performing digital … (see more)tasks through web interfaces in a human-like manner. However, even the strongest closed-source models often struggle to achieve robust results on several benchmarks, while a notable performance gap exists between them and open-source counterparts. This study investigates the potential of fine-tuning to enhance the performance of a smaller, lower-performing but cost-efficient LLM by leveraging successful traces from stronger LLMs, referred to as experts. We outline a comprehensive pipeline for data collection, filtering, and supervised fine-tuning and explore various behavior cloning parameters. Our experiments provide key insights into the challenges of fine-tuning LLMs into web agents on benchmarks like MiniWoB and WorkArena. Notably, we find that the fine-tuned agents' ability to predict expert trajectories does not consistently lead to improved downstream task performance. This raises issues such as off-policy bias and the loss of reasoning abilities during fine-tuning. We discuss potential solutions to these challenges and make both the codebase and a dataset of 140M tokens open-source for the community to build upon.

2024-10-22

NeurIPS.cc/2024/Workshop/OWA (poster)

Thibault Le Sellier De Chezelles

Fine-Tuning Web Agents: It Works, But It's Trickier Than You Think

Massimo Caccia

Megh Thakkar

Léo Boisvert

Nicolas Chapados

Alexandre Drouin

Maxime Gasse

Alexandre Lacoste

Recent advancements in large language models (LLMs) have sparked interest in developing autonomous web agents capable of performing digital … (see more)tasks through web interfaces in a human-like manner. However, even the strongest closed-source models often struggle to achieve robust results on several benchmarks, while a notable performance gap exists between them and open-source counterparts. This study investigates the potential of fine-tuning to enhance the performance of a smaller, lower-performing but cost-efficient LLM by leveraging successful traces from stronger LLMs, referred to as experts. We outline a comprehensive pipeline for data collection, filtering, and supervised fine-tuning and explore various behavior cloning parameters. Our experiments provide key insights into the challenges of fine-tuning LLMs into web agents on benchmarks like MiniWoB and WorkArena. Notably, we find that the fine-tuned agents' ability to predict expert trajectories does not consistently lead to improved downstream task performance. This raises issues such as off-policy bias and the loss of reasoning abilities during fine-tuning. We discuss potential solutions to these challenges and make both the codebase and a dataset of 140M tokens open-source for the community to build upon.

2024-10-22

NeurIPS.cc/2024/Workshop/OWA (poster)

Thibault Le Sellier De Chezelles

AgentMerge: Enhancing Generalization in Fine-Tuned LLM Agents

Megh Thakkar

Léo Boisvert

Maxime Gasse

Alexandre Lacoste

Massimo Caccia

2024-10-10

NeurIPS.cc/2024/Workshop/AFM (poster)

Exploring validation metrics for offline model-based optimisation with diffusion models

2024-06-13

TMLR (accepted)

LLMs can learn self-restraint through iterative self-reflection

In order to be deployed safely, Large Language Models (LLMs) must be capable of dynamically adapting their behavior based on their level of … (see more)knowledge and uncertainty associated with specific topics. This adaptive behavior, which we refer to as self-restraint, is non-trivial to teach since it depends on the internal knowledge of an LLM. By default, LLMs are trained to maximize the next token likelihood, which does not teach the model to modulate its answer based on its level of uncertainty. In order to learn self-restraint, we devise a utility function that can encourage the model to produce responses only when it is confident in them. This utility function can be used to score generation of different length and abstention. To optimize this function, we introduce ReSearch, a process of"self-reflection"consisting of iterative self-prompting and self-evaluation. We use the ReSearch algorithm to generate synthetic data on which we finetune our models. Compared to their original versions, our resulting models generate fewer \emph{hallucinations} overall at no additional inference cost, for both known and unknown topics, as the model learns to selectively restrain itself. In addition, our method elegantly incorporates the ability to abstain by augmenting the samples generated by the model during the search procedure with an answer expressing abstention.

2024-05-15

ArXiv (preprint)

arxiv.org

Self-evaluation and self-prompting to improve the reliability of LLMs

In order to safely deploy Large Language Models (LLMs), they must be capable of dynamically adapting their behavior based on their level of … (see more)knowledge and uncertainty associated with specific topics. This adaptive behavior, which we refer to as self-restraint, is non-trivial to teach since it depends on the internal knowledge of an LLM. By default, LLMs are trained to maximize the next token likelihood which does not teach the model to modulate its answer based on its level of uncertainty. In order to learn self-restraint, we devise a simple objective that can encourage the model to produce generation that the model is confident in. To optimize this objective, we introduce ReSearch, an iterative search algorithm based on self-evaluation and self-prompting. Our method results in fewer hallucinations overall, both for known and unknown topics, as the model learns to selectively restrain itself. In addition, our method elegantly incorporates the ability to decline, when the model assesses that it cannot provide a response without a high proportion of hallucination.

2024-03-04

ICLR.cc/2024/Workshop/SeT_LLM (published)

Self-evaluation and self-prompting to improve the reliability of LLMs

In order to safely deploy Large Language Models (LLMs), they must be capable of dynamically adapting their behavior based on their level of … (see more)knowledge and uncertainty associated with specific topics. This adaptive behavior, which we refer to as self-restraint, is non-trivial to teach since it depends on the internal knowledge of an LLM. By default, LLMs are trained to maximize the next token likelihood which does not teach the model to modulate its answer based on its level of uncertainty. In order to learn self-restraint, we devise a simple objective that can encourage the model to produce generation that the model is confident in. To optimize this objective, we introduce ReSearch, an iterative search algorithm based on self-evaluation and self-prompting. Our method results in fewer hallucinations overall, both for known and unknown topics, as the model learns to selectively restrain itself. In addition, our method elegantly incorporates the ability to decline, when the model assesses that it cannot provide a response without a high proportion of hallucination.

2024-03-04

ICLR.cc/2024/Workshop/SeT_LLM (published)

Exploring validation metrics for ofﬂine model-based optimisation

In ofﬂine model-based optimisation (MBO) we are interested in using machine learning to de-sign candidates that maximise some measure of d… (see more)esirability through an expensive but real-world scoring process. Ofﬂine MBO tries to approximate this expensive scoring function and use that to evaluate generated designs, however evaluation is non-exact because one approximation is being evaluated with another. Instead, we ask ourselves: if we did have the real world scoring function at hand, what cheap-to-compute validation metrics would correlate best with this? Since the real-world scoring function is available for simulated MBO datasets, insights obtained from this can be transferred over to real-world ofﬂine MBO tasks where the real-world scoring function is expensive to compute. To address this, we propose a conceptual evaluation framework that is amenable to measuring extrapolation, and apply this to conditional denoising diffusion models. Empirically, we ﬁnd that two validation metrics – agreement and Frechet distance – correlate quite well with the ground truth. When there is high variability in conditional generation, feedback is required in the form of an approximated version of the real-world scoring function. Furthermore, we ﬁnd that generating high-scoring samples may require heavily weighting the generative model in favour of sample quality, potentially at the cost of sample diversity.

2024-01-01

Trans. Mach. Learn. Res. (published)

dblp.uni-trier.de

Bridging the Gap Between Target Networks and Functional Regularization

Valentin Thomas

Joseph Marino

Gian Maria Marconi

Rafael Pardinas

Chris Pal

Mohammad Emtiyaz Khan

2023-09-06

TMLR (accepted)

Causal Discovery with Language Models as Imperfect Experts

Stephanie Long

Valentina Zantedeschi

Tibor Schuster

Alexandre Drouin

Understanding the causal relationships that underlie a system is a fundamental prerequisite to accurate decision-making. In this work, we ex… (see more)plore how expert knowledge can be used to improve the data-driven identification of causal graphs, beyond Markov equivalence classes. In doing so, we consider a setting where we can query an expert about the orientation of causal relationships between variables, but where the expert may provide erroneous information. We propose strategies for amending such expert knowledge based on consistency properties, e.g., acyclicity and conditional independencies in the equivalence class. We then report a case study, on real data, where a large language model is used as an imperfect expert.

2023-06-19

ICML.cc/2023/Workshop/SPIGM (poster)

Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels

Sai Rajeswar

Pietro Mazzaglia

Tim Verbelen

Bart Dhoedt

Aaron Courville

Alexandre Lacoste

Controlling artificial agents from visual sensory data is an arduous task. Reinforcement learning (RL) algorithms can succeed but require la… (see more)rge amounts of interactions between the agent and the environment. To alleviate the issue, unsupervised RL proposes to employ self-supervised interaction and learning, for adapting faster to future tasks. Yet, as shown in the Unsupervised RL Benchmark (URLB; Laskin et al. 2021), whether current unsupervised strategies can improve generalization capabilities is still unclear, especially in visual control settings. In this work, we study the URLB and propose a new method to solve it, using unsupervised model-based RL, for pre-training the agent, and a task-aware fine-tuning strategy combined with a new proposed hybrid planner, Dyna-MPC, to adapt the agent for downstream tasks. On URLB, our method obtains 93.59% overall normalized performance, surpassing previous baselines by a staggering margin. The approach is empirically evaluated through a large-scale empirical study, which we use to validate our design choices and analyze our models. We also show robust performance on the Real-Word RL benchmark, hinting at resiliency to environment perturbations during adaptation. Project website: https://masteringurlb.github.io/

2023-04-24

ICML.cc/2023/Conference (poster)

proceedings.mlr.press