Publications

Generative Meta-Models are Adversarial Classifiers

Diego Calanzone

Pietro Greiner

Pierre-Luc Bacon

We study adversarial prompt detection in LLMs through the geometry of intermediate activations. Our hypothesis is that token-level adversari… (voir plus)al attacks induce hidden states that lie outside the activation manifold associated with typical prompts. To test this, we use Generative Latent Priors (GLP), diffusion-based meta-models trained on LLM residual stream activations, as proxies for this manifold (Luo et al., 2026). We evaluate several training-free anomaly scores derived from GLP, namely Guard-GLP, including reconstruction error, diffusion time estimation, and a density-based estimate using Hutchinson trace estimation. Empirically, GLP reconstruction error separates benign prompts from adversarial prompts and provides a competitive classifier without supervised fine-tuning. We also study GLP as a regularizer for activation steering, showing that denoising edited activations can reduce attack success while limiting over-refusal and nonsensical generations. Overall, our results suggest that generative priors over LLM activations provide a useful interface for both adversarial prompt detection and safer activation-level interventions.

2026-08-04

AIW @ Conference on Language Modeling (publié)

Inference for subgraph densities in noisy dynamic networks

Peter W. MacDonald

Eric D. Kolaczyk

In this work we develop statistical methodology to estimate and perform inference on subgraph densities using time-indexed, or dynamic netwo… (voir plus)rk sequences. These estimates explicitly adjust for observation errors for the network edges, and have good theoretical properties as the size of the network grows. By specifying a stochastically evolving hidden Markov network model, we address two important directions for further investigation identified by Chang et al. (2022): robustness to non-identical network replicates, and efficient aggregation of multiple available network snapshots. These new methods vastly expand the analysis of noisy networks to new data settings, as network replicates are commonly observed dynamically. The methodology is also extended to consider joint inference for subgraph densities at multiple time points, to facilitate formal statistical comparison of dynamic network snapshots.

2026-08-04

arXiv (prépublication)

A game theory for foundation models shows new paths to rational cooperation through similarity inference

Alexander Meulemans

Maciej Wołczyk

Marissa A. Weis

Rajai Nasser

Roberta Rocca

Seijin Kobayashi

Guillaume Lajoie

Angelika Steger

Blake Richards

Marcus Hutter

James Manyika

Rif A. Saurous

João Sacramento

Blaise Agüera y Arcas

As autonomous agents powered by foundation models are increasingly integrated into social and economic systems, understanding the principles… (voir plus) governing their collective behavior is essential for ensuring safety and cooperation. Classical game theory, the dominant framework for modeling rational interaction, is built upon the assumption of `decoupled agency,'where agents treat their own decision-making as independent of the environment and other actors. Modern AI agents, however, jointly predict their own future actions alongside external observations. Here, we report a striking finding: when interacting in stylized social dilemmas, foundation model agents engaging in optimal planning consistently converge to stable cooperation, directly contradicting classical game-theoretic predictions of mutual defection. To understand this phenomenon, we introduce the `embedded Bayesian agent,'a theoretical model for foundation model agents. By shifting from decoupled to embedded agency, these agents model themselves as part of the universe they inhabit, maintaining epistemic uncertainty about their own decision-making algorithms. We show that by inferring whether others are behaviorally similar, an embedded agent treats its own deliberation during planning as evidence: a decision to cooperate predicts a similar decision by a similar partner. We formalize this mechanism of similarity inference through the `embedded equilibrium,'a novel solution concept replacing the Nash equilibrium to provide a foundational game theory for the social behavior of modern AI agents.

2026-08-03

arXiv (prépublication)

Learning, Fast and Slow: Towards LLMs That Adapt Continually

Rishabh Tiwari

Kusha Sareen

Lakshya A Agrawal

Joseph E. Gonzalez

Matei Zaharia

Kurt Keutzer

Inderjit S Dhillon

Rishabh Agarwal

Devvrit Khatri

Large language models (LLMs) are trained for downstream tasks by updating their parameters (e.g., via RL). However, updating parameters forc… (voir plus)es them to absorb task-specific information, which can result in catastrophic forgetting and loss of plasticity. In contrast, in-context learning with fixed LLM parameters can cheaply and rapidly adapt to task-specific requirements (e.g., prompt optimization), but cannot by itself typically match the performance gains available through updating LLM parameters. There is no good reason for restricting learning to being in-context or in-weights. Moreover, humans also likely learn at different time scales (e.g., System 1 vs 2). To this end, we introduce a fast-slow learning framework for LLMs, with model parameters as "slow" weights and optimized context as "fast" weights. These fast "weights" can learn from textual feedback to absorb the task-specific information, while allowing slow weights to stay closer to the base model and persist general reasoning behaviors. Fast-Slow Training (FST) is up to 3x more sample-efficient than only slow learning (RL) across reasoning tasks, while consistently reaching a higher performance asymptote. Moreover, FST-trained models remain closer to the base LLM (up to 70% less KL divergence), resulting in less catastrophic forgetting than RL-training. This reduced drift also preserves plasticity: after training on one task, FST trained models adapt more effectively to a subsequent task than parameter-only trained models. In continual learning scenarios, where task domains change on the fly, FST continues to acquire each new task while parameter-only RL stalls.

2026-08-03

CBW @ Conference on Language Modeling (poster)

A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents

Wei-Chieh Huang

Weizhi Zhang

Yueqing Liang

Yuanchen Bei

Yankai Chen

Tao Feng

xinyu Pan

Zhen Tan

Yu Wang

Tianxin Wei

Shanglin Wu

Ruiyao Xu

Liangwei Yang

Rui Yang

Wooseong Yang

Chin-Yuan Yeh

Hanrong Zhang

Haozhen Zhang

Siqi Zhu

Henry Peng Zou … (voir 40 de plus)

Wanjia Zhao

Song Wang

Wujiang Xu

Zixuan Ke

Zheng Hui

Dawei Li

Yaozu Wu

Langzhou He

Chen Wang

Xiongxiao Xu

Baixiang Huang

Juntao Tan

Shelby Heinecke

Huan Wang

Caiming Xiong

Ahmed Metwally

Jun Yan

Chen-Yu Lee

Hanqing Zeng

Yinglong Xia

Xiaokai Wei

Ali Payani

Yu Wang

Haitong Ma

Wenya Wang

Chenguang Wang

Yu Zhang

Xin Eric Wang

Yongfeng Zhang

Jiaxuan You

Hanghang Tong

Xiao Luo

Xue Liu

Yizhou Sun

Wei Wang

Julian McAuley

James Zou

Jiawei Han

Philip S. Yu

Kai Shu

Research in artificial intelligence is undergoing a paradigm shift from prioritizing model innovations and benchmark scores towards emphasiz… (voir plus)ing problem definition and rigorous real-world evaluation. As the field enters the "second half," the central challenge becomes real utility in long-horizon, dynamic, and user-dependent settings such as agentic coding, deep research, and computer use, where LLM-based agents face context explosion beyond fixed context windows and must continuously accumulate, manage, and selectively reuse large volumes of information across extended interactions. Memory, with hundreds of papers released in 2025, therefore emerges as the critical solution to fill the utility gap. Beyond serving as passive storage, memory is increasingly the substrate through which agents self-evolve: short-term memory gates which experiences are perceived, selected, and abstracted during execution, while long-term memory accumulates and consolidates them into reusable knowledge and skills, forming the loop through which agents improve from their own experience and sustain continual learning. In this survey, we provide a unified view of foundation agent memory along three dimensions: memory substrate (internal parametric state and external retrieval-augmented stores), cognitive mechanism (sensory, working, episodic, semantic, and procedural), and memory subject (user-centric personalization and agent-centric experience). We then analyze how memory is operated under single- and multi-agent topologies and highlight learning policies over memory operations, showing how memory management itself is becoming a trainable, self-evolving capability that spans reinforcement-learned context curation, experience consolidation at decision time, and the emerging ecosystem of explicit, portable, and shareable agent skills surfaced through agent harnesses, context engineering, and standardized tool-mediation protocols. Finally, we review evaluation benchmarks and metrics for assessing memory utility, and outline various open challenges and future directions.

2026-08-03

Transactions on Machine Learning Research (accepté)

Analytic Planning under Uncertainty with Moment Closure

Shishir Sharma

Doina Precup

Effective model-based reinforcement learning in stochastic environments requires planning that accounts for predictive uncertainty. Propagat… (voir plus)ing full state distributions analytically offers a principled way to do this, but has traditionally required restrictive policy or reward structures to remain tractable. Consequently, modern deep reinforcement learning has largely retreated to either stochastic sampling, which introduces significant target variance, or deterministic point estimates that ignore predictive covariance entirely. We investigate whether distribution-aware planning is possible without these constraints. Using a quadratic action-value parameterization, we first reduce the Bellman backup to an expectation over the state-value function alone; the key idea is then a compatibility principle between the predictive transition distribution and the value function class, under which this expectation is analytic in the distribution's moments. We instantiate this principle with a Gaussian transition model paired with a radial-basis value function, yielding a closed-form backup that propagates both predictive mean and covariance. Empirically, our approach reduces target variance and yields well-calibrated predictive uncertainty under stochastic observations in continuous control, providing a principled framework for planning with learned distribution models.

2026-08-02

arXiv (prépublication)

Can LLMs Faithfully Enact Superforecaster Personas?

Andrew Robert Williams

Evan Jiang

Martin Weiss

Nasim Rahaman

Hugo Larochelle

Superforecasters are people that make forecasts that are statistically better than the average person; they offer an interesting testbed for… (voir plus) persona modelling. In this preliminary work, we investigate whether large language models (LLMs) can faithfully model superforecaster-like personas making similar forecasts and generating similar rationales behind the forecasts. When we compare LLM-generated responses to the ground truth responses of superforecasters, we find that few-shot prompting generates numerically closer forecasts than instruction-prompting baselines. We also measure the similarity of generated and real rationales, finding that the rationales generated based on examples are judged more similar to those of superforecasters than instruction-prompting baselines. However, an analysis of the reasoning patterns in the rationales shows significant differences between human and LLM forecasters, pointing to a gap between stylistic imitation and deep reasoning similarity. These preliminary results raise several interesting questions about how getting superforecaster-like behaviour from LLMs actually works, and open new avenues to explore for improving the forecasting behaviour of LLMs.

2026-08-02

Social_Sim @ Conference on Language Modeling (poster)

Reasoning with Preference Constraints: A Benchmark for Language Models in Many-to-One Matching Markets

2026-08-01

Transactions on Machine Learning Research (accepté)

Recursive Vision Language Models for General Symbolic Reasoning

Omid Nejati Manzari

Guillaume Lajoie

Hassan Rivaz

Hard symbolic-reasoning tasks such as Sudoku, maze pathfinding, and ARC remain challenging for LLMs due to their fixed-depth autoregressive … (voir plus)reasoning, which limits systematic search, refinement, and backtracking. While recursive models such as Hierarchical Reasoning Model (HRM) and Tiny Recursive Model (TRM) address this limitation through iterative latent-state refinement, they are typically task-specific and do not leverage pretrained language priors. We propose R-Qwen, a recursive reasoning framework built upon a pretrained Qwen backbone. R-Qwen repeatedly refines a candidate solution through programmatic self-recursion and deep supervision, combining the structured iterative computation of recursive models with the linguistic and reasoning priors of pretrained LLMs. We further adapt Hierarchical Supervision Weighting (HSW) to autoregressive models by exponentially weighting losses across recursive steps. HSW reduces gradient variance by at least 50\%, improves the signal-to-noise ratio of stochastic gradients, and accelerates convergence. Across eight challenging benchmarks, R-Qwen consistently outperforms prior recursive reasoning models and substantially larger LLMs while using a comparable number of trainable parameters. Notably, on ARC-AGI dataset, our model achieves a 27.6\% improvement over the baseline, highlighting the effectiveness of recursive refinement for general symbolic reasoning. These results suggest that recursive reasoning mechanisms and pretrained language model priors are complementary approaches for improving symbolic puzzle-solving. Code and models will be released after acceptance.

2026-08-01

arXiv (prépublication)

Inferring brain-wide interactions using data-constrained recurrent neural network models

Matthew G. Perich

Charlotte Arlt

Sofia Soares

Siyan Zhou

Manuel Beiran

Aaron S. Andalman

Tyler Benster

Megan E. Young

Clayton P. Mosher

Juri Minxha

Eugene Carter

Ueli Rutishauser

Peter H. Rudebeck

Christopher D. Harvey

Karl Deisseroth

Kanaka Rajan

2026-07-31

Neuron (publié)

De novo L-(+)-tartaric acid biosynthesis in multi-modular engineered yeasts

Xuan Zhou

Jiaheng Hou

Zikai Wang

Zhendong Li

Yang Li

Xitong Li

Xianhao Xu

Yanfeng Liu

Jianghua Li

Guocheng Du

Dacheng Ma

J. Tang

Jian Chen

Xueqin Lv

Long Liu

L-(+)-tartaric acid (L-TA) is a high-value chiral organic acid essential for food and pharmaceuticals. Despite its industrial importance, su… (voir plus)stainable green production is constrained by the lack of a fully defined biosynthetic pathway. Here, we report the de novo biosynthesis of L-TA in Saccharomyces cerevisiae through reaction-guided enzyme mining, experimental validation, and Enzyme Commission-specific Catalytic Hybrid Optimizer (ECHO)-assisted enzyme prioritization. We first elucidate the elusive two-step conversion from precursor 5-keto-D-gluconic acid (5-KGA) to L-TA, catalyzed by transketolase (TK) and succinate semialdehyde dehydrogenase (SSDH). To optimize this critical step, we develop the ECHO. This multimodal framework integrates sequence, substrate, and pocket-aware structural information to identify high-performance TK-SSDH pairs. By integrating this pathway with de novo precursor synthesis, cofactor engineering, and semi-rational protein engineering, a final L-TA titer of 6.59 mg L−1 was achieved in a 5-L bioreactor. By connecting computational mining and metabolic assembly through a multi-module engineering strategy, our study establishes a green platform for L-TA production and demonstrates an effective workflow for synthetic pathway design. L-(+)-tartaric acid (L-TA) is a high-value chiral organic acid for food and pharmaceuticals. Here the authors produce L-TA in S. cerevisiae through reaction-guided enzyme mining and Enzyme Commission-specific Catalytic Hybrid Optimizer (ECHO)-assisted enzyme prioritization.

2026-07-31

Nature Communications (publié)