Towards Fair In-Context Learning with Tabular Foundation Models
Patrik Joslin Kenfack
Tabular foundational models have shown promising in-context learning capabilities on structured data by using training examples as context w… (voir plus)ithout further parameter adjustments. This emerging approach positions itself as a competitive alternative to traditional gradient-boosted tree methods. However, while biases in conventional machine learning models are well documented, it remains unclear how these biases manifest in Tabular ICL. The paper investigates the fairness implications of Tabular ICL and explores three preprocessing strategies—correlation removal, group-balanced demonstration selection, and uncertainty-based demonstration selection—to address bias. Comprehensive experiments indicate that uncertainty-based demonstration selection consistently enhances group fairness in the predictions. The source code for reproducing the results of this work can be found at https://anonymous.4open.science/r/Fair-TabICL-DD84.
Tracing the representation geometry of language models from pretraining to post-training
Melody Zixuan Li
Kumar Krishna Agrawal
Arna Ghosh
Komal Kumar Teru
The geometry of representations in a neural network can significantly impact downstream generalization. It is unknown how representation geo… (voir plus)metry changes in large language models (LLMs) over pretraining and post-training. Here, we characterize the evolving geometry of LLM representations using spectral methods (effective rank and eigenspectrum decay). With the OLMo and Pythia model families we uncover a consistent non-monotonic sequence of three distinct geometric phases in pretraining. An initial \warmup phase sees rapid representational compression. This is followed by an "entropy-seeking" phase, characterized by expansion of the representation manifold's effective dimensionality, which correlates with an increase in memorization. Subsequently, a "compression seeking" phase imposes anisotropic consolidation, selectively preserving variance along dominant eigendirections while contracting others, correlating with improved downstream task performance. We link the emergence of these phases to the fundamental interplay of cross-entropy optimization, information bottleneck, and skewed data distribution. Additionally, we find that in post-training the representation geometry is further transformed: Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) correlate with another "entropy-seeking" dynamic to integrate specific instructional or preferential data, reducing out-of-distribution robustness. Conversely, Reinforcement Learning with Verifiable Rewards (RLVR) often exhibits a "compression seeking" dynamic, consolidating reward-aligned behaviors and reducing the entropy in its output distribution. This work establishes the utility of spectral measures of representation geometry for understanding the multiphase learning dynamics within LLMs.
Two-point deterministic equivalence for SGD in random feature models
Alexander Atanasov
Blake Bordelon
Jacob A Zavatone-Veth
Cengiz Pehlevan
Ultrasound and MRI-based evaluation of relationships between morphological and mechanical properties of the lower lumbar multifidus muscle in chronic low back pain.
Neda Naghdi
Sara Masi
Cléo Bertrand
Brent Rosenstein
Hassan Rivaz
Mathieu Roy
Maryse Fortin
DoomArena: A framework for Testing AI Agents Against Evolving Security Threats
Léo Boisvert
Abhay Puri
Gabriel Huang
Mihir Bansal
Chandra Kiran Reddy Evuru
Avinandan Bose
Maryam Fazel
Alexandre Lacoste
Jason Stanley
Krishnamurthy Dj Dvijotham
We present DoomArena, a security evaluation framework for AI agents. DoomArena is designed on three principles: 1) It is a plug-in framework… (voir plus) and integrates easily into realistic agentic frameworks like BrowserGym (for web agents) and
How to Train Your LLM Web Agent: A Statistical Diagnosis
Dheeraj Vattikonda
Santhoshi Ravichandran
Emiliano Penaloza
Hadi Nekoei
Megh Thakkar
Thibault Le Sellier de Chezelles
Nicolas Gontier
Miguel Muñoz-Mármol
Sahar Omidi Shayegan
Stefania Raimondo
Alexandre Piché
Alexandre Lacoste
Massimo Caccia
Large language model (LLM) agents for web interfaces have advanced rapidly, yet open-source systems still lag behind proprietary agents. Bri… (voir plus)dging this gap is key to enabling customizable, efficient, and privacy-preserving agents. Two challenges hinder progress: the reproducibility issues in RL and LLM agent training, where results often depend on sensitive factors like seeds and decoding parameters, and the focus of prior work on single-step tasks, overlooking the complexities of web-based, multi-step decision-making. We address these gaps by providing a statistically driven study of training LLM agents for web tasks. Our two-stage pipeline combines imitation learning from a Llama 3.3 70B teacher with on-policy fine-tuning via Group Relative Policy Optimization (GRPO) on a Llama 3.1 8B student. Through 240 configuration sweeps and rigorous bootstrapping, we chart the first compute allocation curve for open-source LLM web agents. Our findings show that dedicating one-third of compute to teacher traces and the rest to RL improves MiniWoB++ success by 6 points and closes 60% of the gap to GPT-4o on WorkArena, while cutting GPU costs by 45%. We introduce a principled hyperparameter sensitivity analysis, offering actionable guidelines for robust and cost-effective agent training.
Silent Sabotage: Injecting Backdoors into AI Agents Through Fine-Tuning
Léo Boisvert
Abhay Puri
Chandra Kiran Reddy Evuru
Joshua Kazdan
Avinandan Bose
Maryam Fazel
Sai Rajeswar
Jason Stanley
Krishnamurthy Dj Dvijotham
The rise of AI agents that can use tools, browse the web and interact with computers on behalf of a user, has sparked strong interest in imp… (voir plus)roving these capabilities by explicitly fine-tuning the LLMs/VLMs that power these agents. Several researchers have proposed collecting data by letting the agents interact with their environment (e.g., a computer operating system, the web or a collection of APIs exposed as tools), and improve agent performance by fine tuning on this data. In this work, we show that such data collection can be manipulated by adversaries to insert poisoned traces. By modifying just 5% of collected traces, adversaries can embed stealthy bad behaviors into agents—like leaking confidential user information whenever the tool or webpage exposes a trigger. Our results raise important security concerns in the development of AI agents, and underscore the importance of careful scrutiny of all data collection processes used to improve agentic AI.
State Entropy Regularization for Robust Reinforcement Learning
Uri Koren
Yonatan Ashlag
Mirco Mutti
Esther Derman
Shie Mannor
State entropy regularization has empirically shown better exploration and sample complexity in reinforcement learning (RL). However, its the… (voir plus)oretical guarantees have not been studied. In this paper, we show that state entropy regularization improves robustness to structured and spatially correlated perturbations. These types of variation are common in transfer learning but often overlooked by standard robust RL methods, which typically focus on small, uncorrelated changes. We provide a comprehensive characterization of these robustness properties, including formal guarantees under reward and transition uncertainty, as well as settings where the method performs poorly. Much of our analysis contrasts state entropy with the widely used policy entropy regularization, highlighting their different benefits. Finally, from a practical standpoint, we illustrate that compared with policy entropy, the robustness advantages of state entropy are more sensitive to the number of rollouts used for policy evaluation.
State Entropy Regularization for Robust Reinforcement Learning
Uri Koren
Yonatan Ashlag
Mirco Mutti
Esther Derman
Shie Mannor
State entropy regularization has empirically shown better exploration and sample complexity in reinforcement learning (RL). However, its the… (voir plus)oretical guarantees have not been studied. In this paper, we show that state entropy regularization improves robustness to structured and spatially correlated perturbations. These types of variation are common in transfer learning but often overlooked by standard robust RL methods, which typically focus on small, uncorrelated changes. We provide a comprehensive characterization of these robustness properties, including formal guarantees under reward and transition uncertainty, as well as settings where the method performs poorly. Much of our analysis contrasts state entropy with the widely used policy entropy regularization, highlighting their different benefits. Finally, from a practical standpoint, we illustrate that compared with policy entropy, the robustness advantages of state entropy are more sensitive to the number of rollouts used for policy evaluation.
Boosting LLM Reasoning via Spontaneous Self-Correction
Xutong Zhao
Tengyu Xu
Xuewei Wang
Zhengxing Chen
Di Jin
Liang Tan
Zishun Yu
Zhuokai Zhao
Yun He
Sinong Wang
Han Fang
Chen Zhu
MetaAI
Mila - Québec
AI Institute
Polytechnique Montréal
While large language models (LLMs) have demonstrated remarkable success on a broad range of tasks, math reasoning remains a challenging one.… (voir plus) One of the approaches for improving math reasoning is self-correction, which designs self-improving loops to let the model correct its own mistakes. However, existing self-correction approaches treat corrections as standalone post-generation refinements, relying on extra prompt and system designs to elicit self-corrections, instead of performing real-time, spontaneous self-corrections in a single pass. To address this, we propose SPOC, a spontaneous self-correction approach that enables LLMs to generate interleaved solutions and verifications in a single inference pass, with generation dynamically terminated based on verification outcomes, thereby effectively scaling inference time compute. SPOC considers a multi-agent perspective by assigning dual roles -- solution proposer and verifier -- to the same model. We adopt a simple yet effective approach to generate synthetic data for fine-tuning, enabling the model to develop capabilities for self-verification and multi-agent collaboration. We further improve its solution proposal and verification accuracy through online reinforcement learning. Experiments on mathematical reasoning benchmarks show that SPOC significantly improves performance. Notably, SPOC boosts the accuracy of Llama-3.1-8B and 70B Instruct models, achieving gains of 8.8% and 11.6% on MATH500, 10.0% and 20.0% on AMC23, and 3.3% and 6.7% on AIME24, respectively.
Boosting LLM Reasoning via Spontaneous Self-Correction
Xutong Zhao
Tengyu Xu
Xuewei Wang
Zhengxing Chen
Di Jin
Liang Tan
Zishun Yu
Zhuokai Zhao
Yun He
Sinong Wang
Si-Yuan Wang
Han Fang
Chen Zhu
MetaAI
Mila - Québec
AI Institute
Polytechnique Montréal
While large language models (LLMs) have demonstrated remarkable success on a broad range of tasks, math reasoning remains a challenging one.… (voir plus) One of the approaches for improving math reasoning is self-correction, which designs self-improving loops to let the model correct its own mistakes. However, existing self-correction approaches treat corrections as standalone post-generation refinements, relying on extra prompt and system designs to elicit self-corrections, instead of performing real-time, spontaneous self-corrections in a single pass. To address this, we propose SPOC, a spontaneous self-correction approach that enables LLMs to generate interleaved solutions and verifications in a single inference pass, with generation dynamically terminated based on verification outcomes, thereby effectively scaling inference time compute. SPOC considers a multi-agent perspective by assigning dual roles -- solution proposer and verifier -- to the same model. We adopt a simple yet effective approach to generate synthetic data for fine-tuning, enabling the model to develop capabilities for self-verification and multi-agent collaboration. We further improve its solution proposal and verification accuracy through online reinforcement learning. Experiments on mathematical reasoning benchmarks show that SPOC significantly improves performance. Notably, SPOC boosts the accuracy of Llama-3.1-8B and 70B Instruct models, achieving gains of 8.8% and 11.6% on MATH500, 10.0% and 20.0% on AMC23, and 3.3% and 6.7% on AIME24, respectively.
A Self-Supervised Foundation Model for Robust and Generalizable Representation Learning in STED Microscopy
Anthony Bilodeau
Frédéric Beaupré
Julia Chabbert
Jean-Michel Bellavance
Koraly Lessard
Andréanne Deschênes
Renaud Bernatchez
Paul De Koninck
Flavie Lavoie-Cardinal