Publications

AFlow: Automating Agentic Workflow Generation
Jiayi Zhang
Jinyu Xiang
Zhaoyang Yu
Fengwei Teng
Xiong-Hui Chen
Jiaqi Chen
Mingchen Zhuge
Xin Cheng
Sirui Hong
Jinlin Wang
Bingnan Zheng
Bang Liu
Yuyu Luo
Chenglin Wu
Large language models (LLMs) have demonstrated remarkable potential in solving complex tasks across diverse domains, typically by employing … (voir plus)agentic workflows that follow detailed instructions and operational sequences. However, constructing these workflows requires significant human effort, limiting scalability and generalizability. Recent research has sought to automate the generation and optimization of these workflows, but existing methods still rely on initial manual setup and fall short of achieving fully automated and effective workflow generation. To address this challenge, we reformulate workflow optimization as a search problem over code-represented workflows, where LLM-invoking nodes are connected by edges. We introduce AFLOW, an automated framework that efficiently explores this space using Monte Carlo Tree Search, iteratively refining workflows through code modification, tree-structured experience, and execution feedback. Empirical evaluations across six benchmark datasets demonstrate AFLOW's efficacy, yielding a 5.7% average improvement over state-of-the-art baselines. Furthermore, AFLOW enables smaller models to outperform GPT-4o on specific tasks at 4.55% of its inference cost in dollars. The code is available at https://github.com/geekan/MetaGPT.
2025-01-21
ICLR.cc/2025/Conference (présentation orale)
openreview.net
openreview.net
Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models
Michael Noukhovitch
Shengyi Huang
Sophie Xhonneux
Arian Hosseini
Rishabh Agarwal
Aaron Courville
The dominant paradigm for RLHF is online and on-policy RL: synchronously generating from the large language model (LLM) policy, labelling wi… (voir plus)th a reward model, and learning using feedback on the LLM's own outputs. While performant, this paradigm is computationally inefficient. Inspired by classical deep RL literature, we propose separating generation and learning in RLHF. This enables asynchronous generation of new samples while simultaneously training on old samples, leading to faster training and more compute-optimal scaling. However, asynchronous training relies on an underexplored regime, online but off-policy RLHF: learning on samples from previous iterations of our model which give a worse training signal. We tackle the fundamental challenge in this regime: how much off-policyness can we tolerate for asynchronous training to speed up learning but maintain performance? Among several RLHF algorithms we test, online DPO is found to be most robust to off-policy data, and robustness increases with the scale of the policy model. We study further compute optimizations for asynchronous RLHF but find that they come at a performance cost, giving rise to a trade-off. We verify the scalability of asynchronous RLHF by training a general-purpose chatbot from LLaMA 3.1 8B on an instruction-following task ~40% faster than a synchronous run while matching final performance. Finally, we extend our results to math and reasoning to demonstrate asynchronous RL can finetune Rho 1B on GSM8k ~70% faster while matching synchronous accuracy.
2025-01-21
International Conference on Learning Representations (poster)
doi.org
openreview.net
BigDocs: An Open Dataset for Training Multi-modal Models on Document and Code Tasks
Juan Rodriguez
Xiangru Jian
Siba Smarak Panigrahi
Tianyu Zhang
Aarash Feizi
Abhay Puri
Akshay Kalkunte
François Savard
Ahmed Masry
Shravan Nayak
Rabiul Awal
Mahsa Massoud
Amirhossein Abaskohi
Zichao Li
Suyuchen Wang
Pierre-Andre Noel
Mats Leon Richter
Saverio Vadacchino
Shubham Agarwal
Sanket Biswas … (voir 23 de plus)
Sara Shanian
Ying Zhang
Noah Bolger
Kurt MacDonald
Simon Fauvel
Sathwik Tejaswi
Srinivas Sunkara
Joao Monteiro
Krishnamurthy Dj Dvijotham
Torsten Scholak
Nicolas Chapados
Sepideh Kharagani
Sean Hughes
M. Özsu
Siva Reddy
Marco Pedersoli
Yoshua Bengio
Christopher Pal
Issam Laradji
Spandana Gella
Perouz Taslakian
David Vázquez
Sai Rajeswar
Multimodal AI has the potential to significantly enhance document-understanding tasks, such as processing receipts, understanding workflows,… (voir plus) extracting data from documents, and summarizing reports. Code generation tasks that require long-structured outputs can also be enhanced by multimodality. Despite this, their use in commercial applications is often limited due to limited access to training data and restrictive licensing, which hinders open access. To address these limitations, we introduce BigDocs-7.5M, a high-quality, open-access dataset comprising 7.5 million multimodal documents across 30 tasks. We use an efficient data curation process to ensure our data is high-quality and license-permissive. Our process emphasizes accountability, responsibility, and transparency through filtering rules, traceable metadata, and careful content analysis. Additionally, we introduce BigDocs-Bench, a benchmark suite with 10 novel tasks where we create datasets that reflect real-world use cases involving reasoning over Graphical User Interfaces (GUI) and code generation from images. Our experiments show that training with BigDocs-Bench improves average performance up to 25.8% over closed-source GPT-4o in document reasoning and structured output tasks such as Screenshot2HTML or Image2Latex generation. Finally, human evaluations showed a preference for outputs from models trained on BigDocs over GPT-4o. This suggests that BigDocs can help both academics and the open-source community utilize and improve AI tools to enhance multimodal capabilities and document reasoning. The project is hosted at https://bigdocs.github.io .
2025-01-21
International Conference on Learning Representations (poster)
doi.org
openreview.net
Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces
DiJia Su
Sainbayar Sukhbaatar
Michael G. Rabbat
Yuandong Tian
Qinqing Zheng
2025-01-21
ICLR.cc/2025/Conference (poster)
doi.org
openreview.net
Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inference
Matthew D Riemer
Gopeshh Subbaraj
Glen Berseth
Irina Rish
Realtime environments change even as agents perform action inference and learning, thus requiring high interaction frequencies to effectivel… (voir plus)y minimize regret. However, recent advances in machine learning involve larger neural networks with longer inference times, raising questions about their applicability in realtime systems where reaction time is crucial. We present an analysis of lower bounds on regret in realtime reinforcement learning (RL) environments to show that minimizing long-term regret is generally impossible within the typical sequential interaction and learning paradigm, but often becomes possible when sufficient asynchronous compute is available. We propose novel algorithms for staggering asynchronous inference processes to ensure that actions are taken at consistent time intervals, and demonstrate that use of models with high action inference times is only constrained by the environment's effective stochasticity over the inference horizon, and not by action frequency. Our analysis shows that the number of inference processes needed scales linearly with increasing inference times while enabling use of models that are multiple orders of magnitude larger than existing approaches when learning from a realtime simulation of Game Boy games such as Pokémon and Tetris.
2025-01-21
ICLR.cc/2025/Conference (poster)
doi.org
openreview.net
Forgetting Transformer: Softmax Attention with a Forget Gate
Zhixuan Lin
Evgenii Nikishin
Xu He
Aaron Courville
An essential component of modern recurrent sequence models is the forget gate. While Transformers do not have an explicit recurrent form, we… (voir plus) show that a forget gate can be naturally incorporated into Transformers by down-weighting the unnormalized attention scores in a data-dependent way. We name this attention mechanism Forgetting Attention and the resulting model the Forgetting Transformer (FoX). We show that FoX outperforms the Transformer on long-context language modeling, length extrapolation, and short-context downstream tasks, while performing on par with the Transformer on long-context downstream tasks. Moreover, it is compatible with the FlashAttention algorithm and does not require any positional embeddings. Several analyses, including the needle-in-the-haystack test, show that FoX also retains the Transformer's superior long-context capabilities over recurrent sequence models such as Mamba-2, HGRN2, and DeltaNet. We also introduce a "Pro" block design that incorporates some common architectural components in recurrent sequence models and find it significantly improves the performance of both FoX and the Transformer. Our code is available at [`https://github.com/zhixuan-lin/forgetting-transformer`](https://github.com/zhixuan-lin/forgetting-transformer).
2025-01-21
ICLR.cc/2025/Conference (poster)
openreview.net
openreview.net
Geometry-Aware Generative Autoencoders for Warped Riemannian Metric Learning and Generative Modeling on Data Manifolds
Xingzhi Sun
Danqi Liao
Kincaid MacDonald
Yanlei Zhang
Guillaume Huguet
Guy Wolf
Ian Adelstein
Tim G. J. Rudner
Smita Krishnaswamy
Rapid growth of high-dimensional datasets in fields such as single-cell RNA sequencing and spatial genomics has led to unprecedented opportu… (voir plus)nities for scientific discovery, but it also presents unique computational and statistical challenges. Traditional methods struggle with geometry-aware data generation, interpolation along meaningful trajectories, and transporting populations via feasible paths. To address these issues, we introduce Geometry-Aware Generative Autoencoder (GAGA), a novel framework that combines extensible manifold learning with generative modeling. GAGA constructs a neural network embedding space that respects the intrinsic geometries discovered by manifold learning and learns a novel warped Riemannian metric on the data space. This warped metric is derived from both the points on the data manifold and negative samples off the manifold, allowing it to characterize a meaningful geometry across the entire latent space. Using this metric, GAGA can uniformly sample points on the manifold, generate points along geodesics, and interpolate between populations across the learned manifold using geodesic-guided flows. GAGA shows competitive performance in simulated and real-world datasets, including a 30% improvement over the state-of-the-art methods in single-cell population-level trajectory inference.
2025-01-21
Artificial Intelligence and Statistics (poster)
doi.org
proceedings.mlr.press
Handling Delay in Real-Time Reinforcement Learning
Ivan Anokin
Rishav Rishav
Matthew Riemer
Stephen Chung
Irina Rish
Samira Ebrahimi Kahou
Real-time reinforcement learning (RL) introduces several challenges. First, policies are constrained to a fixed number of actions per second… (voir plus) due to hardware limitations. Second, the environment may change while the network is still computing an action, leading to observational delay. The first issue can partly be addressed with pipelining, leading to higher throughput and potentially better policies. However, the second issue remains: if each neuron operates in parallel with an execution time of
2025-01-21
International Conference on Learning Representations (poster)
doi.org
openreview.net
Influence Functions for Scalable Data Attribution in Diffusion Models
Bruno Mlodozeniec
Runa Eschenhagen
Juhan Bae
Alexander Immer
David Krueger
Richard Turner
Diffusion models have led to significant advancements in generative modelling. Yet their widespread adoption poses challenges regarding data… (voir plus) attribution and interpretability. In this paper, we aim to help address such challenges in diffusion models by developing an influence functions framework. Influence function-based data attribution methods approximate how a model's output would have changed if some training data were removed. In supervised learning, this is usually used for predicting how the loss on a particular example would change. For diffusion models, we focus on predicting the change in the probability of generating a particular example via several proxy measurements. We show how to formulate influence functions for such quantities and how previously proposed methods can be interpreted as particular design choices in our framework. To ensure scalability of the Hessian computations in influence functions, we systematically develop K-FAC approximations based on generalised Gauss-Newton matrices specifically tailored to diffusion models. We recast previously proposed methods as specific design choices in our framework and show that our recommended method outperforms previous data attribution approaches on common evaluations, such as the Linear Data-modelling Score (LDS) or retraining without top influences, without the need for method-specific hyperparameter tuning.
2025-01-21
ICLR.cc/2025/Conference (présentation orale)
doi.org
openreview.net
Input Space Mode Connectivity in Deep Neural Networks
Jakub Vrabel
Ori Shem-Ur
Yaron Oz
David M. Krueger
We extend the concept of loss landscape mode connectivity to the input space of deep neural networks. Initially studied in parameter space, … (voir plus)mode connectivity describes the existence of low-loss paths between solutions (loss minimizers) found via gradient descent. We present theoretical and empirical evidence of its presence in the input space of deep networks, thereby highlighting the broader nature of the phenomenon. We observe that different input images with similar predictions are generally connected, and for trained models, the path tends to be simple, with only a small deviation from being a linear path. We conjecture that input space mode connectivity in high-dimensional spaces is a geometric phenomenon, present even in untrained models, and can be explained by percolation theory. We exploit mode connectivity to obtain new insights about adversarial examples and show its potential for adversarial detection and interpretability.
2025-01-21
ICLR.cc/2025/Conference (poster)
openreview.net
openreview.net
InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation
Gaurav Sahu
Abhay Puri
Juan Rodriguez
Amirhossein Abaskohi
Mohammad Chegini
Alexandre Drouin
Perouz Taslakian
Valentina Zantedeschi
Alexandre Lacoste
David Vázquez
Nicolas Chapados
Christopher Pal
Sai Rajeswar Mudumba
Issam Hadj Laradji
Data analytics is essential for extracting valuable insights from data that can assist organizations in making effective decisions. We intro… (voir plus)duce InsightBench, a benchmark dataset with three key features. First, it consists of 100 datasets representing diverse business use cases such as finance and incident management, each accompanied by a carefully curated set of insights planted in the datasets. Second, unlike existing benchmarks focusing on answering single queries, InsightBench evaluates agents based on their ability to perform end-to-end data analytics, including formulating questions, interpreting answers, and generating a summary of insights and actionable steps. Third, we conducted comprehensive quality assurance to ensure that each dataset in the benchmark had clear goals and included relevant and meaningful questions and analysis. Furthermore, we implement a two-way evaluation mechanism using LLaMA-3 as an effective, open-source evaluator to assess agents' ability to extract insights. We also propose AgentPoirot, our baseline data analysis agent capable of performing end-to-end data analytics. Our evaluation on InsightBench shows that AgentPoirot outperforms existing approaches (such as Pandas Agent) that focus on resolving single queries. We also compare the performance of open- and closed-source LLMs and various evaluation strategies. Overall, this benchmark serves as a testbed to motivate further development in comprehensive automated data analytics and can be accessed here: https://github.com/ServiceNow/insight-bench.
2025-01-21
ICLR.cc/2025/Conference (poster)
doi.org
openreview.net
Interpreting Emergent Planning in Model-Free Reinforcement Learning
Thomas Bush
Stephen Chung
Usman Anwar
Adrià Garriga-Alonso
David M. Krueger
We present the first mechanistic evidence that model-free reinforcement learning agents can learn to plan. This is achieved by applying a me… (voir plus)thodology based on concept-based interpretability to a model-free agent in Sokoban -- a commonly used benchmark for studying planning. Specifically, we demonstrate that DRC, a generic model-free agent introduced by [Guez et al. (2019)](https://arxiv.org/abs/1901.03559), uses learned concept representations to internally formulate plans that both predict the long-term effects of actions on the environment and influence action selection. Our methodology involves: (1) probing for planning-relevant concepts, (2) investigating plan formation within the agent's representations, and (3) verifying that discovered plans (in the agent's representations) have a causal effect on the agent's behavior through interventions. We also show that the emergence of these plans coincides with the emergence of a planning-like property: the ability to benefit from additional test-time compute. Finally, we perform a qualitative analysis of the planning algorithm learned by the agent and discover a strong resemblance to parallelized bidirectional search. Our findings advance understanding of the internal mechanisms underlying planning behavior in agents, which is important given the recent trend of emergent planning and reasoning capabilities in LLMs through RL.
2025-01-21
ICLR.cc/2025/Conference (présentation orale)
openreview.net
openreview.net