Open library
The essential reading of generative AI and agents, open in a clean reading view, with Meow and Standard summaries when available. No account needed to read.
563 papers · 561 with a Meow summary · 333 posts
Every paper prepared on Reading + AI, newest first.
Wallyson Lemes de Oliveira, Mekhron Bobokhonov, Matteo Caorsi et al.
The Abstraction and Reasoning Corpus (ARC) is designed to assess generalization beyond pattern matching, requiring models to infer symbolic rules from very few examples. In this work, we present a transformer-based system that advances ARC performance by combining neural inference with structure-aware priors and onlin…
Xuying Ning, Katherine Tieu, Dongqi Fu et al.
**Abstract:** Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level software engineering. In emerging agentic systems, code is no longer only a target output. It increasingly serves as an operational substrate fo…
Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional domains. We argue that this gap is largely an evaluation problem: widely used benchmarks lack sustained performance measurement on real and…
Jiazhan Feng, Shijue Huang, Xingwei Qu et al.
While reasoning models (e.g., DeepSeek R1) trained with reinforcement learning (RL), excel in textual reasoning, they struggle in scenarios requiring structured problem-solving, such as geometric reasoning, concise computation, or complex equation solving—areas where computational tools like code interpreters (CI) dem…
Mingchen Zhuge, Changsheng Zhao, Dylan R. Ashley et al.
Contemporary evaluation techniques are inadequate for agentic systems. These approaches either focus exclusively on final outcomes—ignoring the step-by-step nature of agentic systems, or require excessive manual labour. To address this, we introduce the **Agent-as-a-Judge** framework, wherein agentic systems are used…
Edoardo Debenedetti, Jie Zhang, Mislav Balunovic et al.
AI agents aim to solve complex tasks by combining text-based reasoning with external tool calls. Unfortunately, AI agents are vulnerable to prompt injection attacks where data returned by external tools hijacks the agent to execute malicious tasks. To measure the adversarial robustness of AI agents, we introduce Agent…
Samuel Miserendino, Michele Wang, Tejal Patwardhan et al.
We introduce SWE-Lancer, a benchmark of over 1,400 freelance software engineering tasks from Upwork, valued at \$1 million USD total in real-world payouts. SWE-Lancer encompasses both independent engineering tasks — ranging from \$50 bug fixes to \$32,000 feature implementations — and managerial tasks, where models ch…
⋆\star Adam Fourney, Gagan Bansal, Hussein Mozannar et al.
Modern AI agents, driven by advances in large foundation models, promise to enhance our productivity and transform our lives by augmenting our knowledge and capabilities. To achieve this vision, AI agents must effectively plan, perform multi-step reasoning and actions, respond to novel observations, and recover from e…
Runjin Chen, Andy Arditi, Henry Sleight et al.
Large language models interact with users through a simulated “Assistant” persona. While the Assistant is typically trained to be helpful, harmless, and honest, it sometimes deviates from these ideals. In this paper, we identify directions in the model’s activation space—persona vectors—underlying several traits, such…
Monte MacDiarmid, Benjamin Wright, Jonathan Uesato et al.
We show that when large language models learn to reward hack on production RL environments, this can result in egregious emergent misalignment. We start with a pretrained model, impart knowledge of reward hacking strategies via synthetic document finetuning or prompting, and train on a selection of real Anthropic prod…
We study subliminal learning, a surprising phenomenon where language models transmit behavioral traits via semantically unrelated data. In our main experiments, a “teacher” model with some trait T (such as liking owls or being misaligned) generates a dataset consisting solely of number sequences. Remarkably, a “studen…
Guibin Zhang, Hejia Geng, Xiaohang Yu et al.
The emergence of agentic reinforcement learning (Agentic RL) marks a paradigm shift from conventional reinforcement learning applied to large language models (LLM RL), reframing LLMs from passive sequence generators into autonomous, decision-making agents embedded in complex, dynamic worlds. This survey formalizes thi…
Tomek Korbak UK AI Security Institute Mikita Balesni Apollo Research Elizabeth Barnes METR Yoshua Bengio University of Montreal & Mila Joe Benton Anthropic Joseph Bloom UK AI Security Institute Mark Chen OpenAI Alan Cooney UK AI Security Institute Allan Dafoe Google DeepMind Anca Dragan Google DeepMind Scott Emmons Google DeepMind Owain Evans Truthful AI & UC Berkeley David Farhi OpenAI Ryan Greenblatt Redwood Research Dan Hendrycks Center for AI Safety Marius Hobbhahn Apollo Research Evan Hubinger Anthropic Geoffrey Irving UK AI Security Institute Erik Jenner Google DeepMind Daniel Kokotajlo AI Futures Project Victoria Krakovna Google DeepMind Shane Legg Google DeepMind David Lindner Google DeepMind David Luan Amazon Aleksander Mądry OpenAI Julian Michael Scale AI Neel Nanda Google DeepMind Dave Orr Google DeepMind Jakub Pachocki OpenAI Ethan Perez Anthropic Mary Phuong Google DeepMind Fabien Roger Anthropic Joshua Saxe Meta Buck Shlegeris Redwood Research Martín Soto UK AI Security Institute Eric Steinberger Magic Jasmine Wang UK AI Security Institute Wojciech Zaremba OpenAI Bowen Baker OpenAI Rohin Shah Google DeepMind Vlad Mikulik Anthropic
AI systems that “think” in human language offer a unique opportunity for AI safety: we can monitor their chains of thought (CoT) for the intent to misbehave. Like all other known AI oversight methods, CoT monitoring is imperfect and allows some misbehavior to go unnoticed. Nevertheless, it shows promise and we recomme…
Aengus Lynch, Benjamin Wright, Caleb Larson et al.
We stress-tested 16 leading models from multiple developers in hypothetical corporate environments to identify potentially risky agentic behaviors before they cause real harm. In the scenarios, we allowed models to autonomously send emails and access sensitive information. They were assigned only harmless business goa…
Hierarchical Reasoning Model (HRM) is a novel approach using two small neural networks recursing at different frequencies. This biologically inspired method beats Large Language models (LLMs) on hard puzzle tasks such as Sudoku, Maze, and ARC-AGI while trained with small models (27M parameters) on small data ($\sim$ 1…
Xinyu Guan, Li Lyna Zhang, Yifei Liu et al.
We present rStar-Math to demonstrate that small language models (SLMs) can rival or even surpass the math reasoning capability of OpenAI o1, without distillation from superior models. rStar-Math achieves this by exercising “deep thinking” through Monte Carlo Tree Search (MCTS), where a math policy SLM performs test-ti…
Peter Belcak Greg Heinrich Shizhe Diao Yonggan Fu Xin Dong, Saurav Muralidharan Yingyan Celine Lin Pavlo Molchanov
Large language models (LLMs) are often praised for exhibiting near-human performance on a wide range of tasks and valued for their ability to hold a general conversation. The rise of agentic AI systems is, however, ushering in a mass of applications in which language models perform a small number of specialized tasks…
Xufang Luo, Yuge Zhang, Zhiyuan He et al.
We present Agent Lightning, a flexible and extensible framework that enables Reinforcement Learning (RL)-based training of Large Language Models (LLMs) for any AI agent. Unlike existing methods that tightly couple RL training with agent or rely on sequence concatenation with masking, Agent Lightning achieves complete…
Wujiang Xu, Zujie Liang, Kai Mei et al.
While large language model (LLM) agents can effectively use external tools for complex real-world tasks, they require memory systems to leverage historical experiences. Current memory systems enable basic storage and retrieval but lack sophisticated memory organization, despite recent attempts to incorporate graph dat…
Mike A. Merrill, Alexander G. Shaw, Nicholas Carlini et al.
AI agents may soon become capable of autonomously completing valuable, long-horizon tasks in diverse domains. Current benchmarks either do not measure real-world tasks, or are not sufficiently difficult to meaningfully measure frontier models. To this end, we present Terminal-Bench 2.0: a carefully curated hard benchm…
Prateek Chhikara, Dev Khant, Saket Aryan et al.
Large Language Models (LLMs) have demonstrated remarkable prowess in generating contextually coherent responses, yet their fixed context windows pose fundamental challenges for maintaining consistency over prolonged multi-session dialogues. We introduce Mem0, a scalable memory-centric architecture that addresses this…
Zora Zhiruo Wang, Jiayuan Mao, Daniel Fried et al.
Despite the potential of language model-based agents to solve real-world tasks such as web navigation, current methods still struggle with long-horizon tasks with complex action trajectories. In contrast, humans can flexibly solve complex tasks by learning reusable task workflows from past experiences and using them t…
Alexander Novikov, Ngân Vũ, Marvin Eisenberger et al.
In this white paper, we present AlphaEvolve, an evolutionary coding agent that substantially enhances capabilities of state-of-the-art LLMs on highly challenging tasks such as tackling open scientific problems or optimizing critical pieces of computational infrastructure. AlphaEvolve orchestrates an autonomous pipelin…
Jenny Zhang, Shengran Hu, Cong Lu et al.
Most of today’s AI systems are constrained by human-designed, fixed architectures and cannot autonomously and continuously improve themselves. The scientific method, on the other hand, is a cumulative and open-ended system, where each innovation builds upon previous artifacts, enabling future discoveries. There is gro…
Jiayi Pan, Xingyao Wang, Graham Neubig et al.
We present SWE-Gym, the first environment for training software engineering (SWE) agents. SWE-Gym contains 2,438 real-world task instances, each comprising a Python codebase with an executable runtime environment, unit tests, and a task specified in natural language. We use SWE-Gym to train language model based SWE ag…
John Yang, Kilian Lieret, Carlos E. Jimenez et al.
Despite recent progress in Language Models (LMs) for software engineering, collecting training data remains a significant pain point. Existing datasets are small, with at most $1{,}000$s of training instances from $11$ or fewer GitHub repositories. The procedures to curate such datasets are often complex, necessitatin…
Naman Jain Jaskirat Singh Manish Shetty Liang Zheng Koushik Sen Ion Stoica
Improving open-source models on real-world Swe tasks (solving GitHub issues) faces two key challenges: 1) scalable curation of execution environments to train these models, and 2) optimal scaling of test-time compute. We introduce R2E-Gym, the largest procedurally-curated executable gym environment for training real-w…
Andy Arditi, Oscar Obeso, Aaquib Syed et al.
Conversational large language models are fine-tuned for both instruction-following and safety, resulting in models that obey benign requests but refuse harmful ones. While this refusal behavior is widespread across chat models, its underlying mechanisms remain poorly understood. In this work, we show that refusal is m…
Meredith Ringel Morris, Jascha Sohl-Dickstein, Noah Fiedel et al.
We propose a framework for classifying the capabilities and behavior of Artificial General Intelligence (AGI) models and their precursors. This framework introduces levels of AGI performance, generality, and autonomy, providing a common language to compare models, assess risks, and measure progress along the path to A…
Leo Gao, Tom Dupré la Tour, Henk Tillman et al.
Sparse autoencoders provide a promising unsupervised approach for extracting interpretable features from a language model by reconstructing activations from a sparse bottleneck layer. Since language models learn many concepts, autoencoders need to be very large to recover all relevant features. However, studying the p…
Andy Zou, Long Phan, Sarah Chen et al.
We identify and characterize the emerging area of representation engineering (RepE), an approach to enhancing the transparency of AI systems that draws on insights from cognitive neuroscience. RepE places representations, rather than neurons or circuits, at the center of analysis, equipping us with novel methods for m…
Junnan Li, Dongxu Li, Silvio Savarese et al.
The cost of vision-and-language pre-training has become increasingly prohibitive due to end-to-end training of large-scale models. This paper proposes BLIP-2, a generic and efficient pre-training strategy that bootstraps vision-language pre-training from off-the-shelf frozen pre-trained image encoders and frozen large…
Samuel Marks, Max Tegmark
Large Language Models (LLMs) have impressive capabilities, but are prone to outputting falsehoods. Recent work has developed techniques for inferring whether a LLM is telling the truth by training probes on the LLM’s internal activations. However, this line of work is controversial, with some authors pointing out fail…
Collin Burns, Haotian Ye, Dan Klein et al.
Existing techniques for training language models can be misaligned with the truth: if we train models with imitation learning, they may reproduce errors that humans make; if we train them to generate text that humans rate highly, they may output errors that human evaluators can’t detect. We propose circumventing this…
Arthur Conmy, Augustine N. Mavor-Parker, Aengus Lynch et al.
Through considerable effort and intuition, several recent works have reverse-engineered nontrivial behaviors of transformer models. This paper systematizes the mechanistic interpretability process they followed. First, researchers choose a metric and dataset that elicit the desired model behavior. Then, they apply act…
Kevin Meng, David Bau, Alex Andonian et al.
We analyze the storage and recall of factual associations in autoregressive transformer language models, finding evidence that these associations correspond to localized, directly-editable computations. We first develop a causal intervention for identifying neuron activations that are decisive in a model’s factual pre…
Kevin Wang, Alexandre Variengien, Arthur Conmy, Buck Shlegeris & Jacob Steinhardt
Research in mechanistic interpretability seeks to explain behaviors of machine learning (ML) models in terms of their internal components. However, most previous work either focuses on simple behaviors in small models or describes complicated behaviors in larger models with broad strokes. In this work, we bridge this…
Moo Jin Kim, Karl Pertsch, Siddharth Karamcheti et al.
Large policies pretrained on a combination of Internet-scale vision-language data and diverse robot demonstrations have the potential to change how we teach robots new skills: rather than training new behaviors from scratch, we can fine-tune such vision-language-action (VLA) models to obtain robust, generalizable poli…