跳到正文
研踪PaperTrail

版本更新

查看已发布论文的最新修订,在详情页对照实际观测到的版本。

部分采集异常

全站更新概况

+197新增论文
+151其中 AI 相关
+16已有论文修订
+91新增 AI 导读

arXiv 最近完成扫描:2026-11-22 08:44 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-21 10:45 — 2026-11-22 10:45(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-22 08:44最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

29,158 已收录论文24,181 AI 相关8,992 有修订112 HF 社区发现

论文修订列表

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 8,992 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-22 08:42(北京时间)
版本更新 · v2arXiv:2505.23719Google Research

TiRex:借助增强的上下文学习实现跨长短期视野的零样本预测

TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning

Andreas Auer, Patrick Podest, Daniel Klotz, Sebastian Böck, Günter Klambauer, Sepp Hochreiter

AI 速读 基于摘要

提出基于 xLSTM 的零样本时间序列预测模型 TiRex,通过保留状态追踪能力与 CPM 训练掩码策略,在长短视野预测上取得作者报告的新最优结果。

cs.LG

查看原文摘要

In-context learning, the ability of large language models to perform tasks using only examples provided in the prompt, has recently been adapted for time series forecasting. This paradigm enables zero-shot prediction, where past values serve as context for forecasting future values, making powerful forecasting tools accessible to non-experts and increasing the performance when training data are scarce. Most existing zero-shot forecasting approaches rely on transformer architectures, which, despite their success in language, often fall short of expectations in time series forecasting, where recurrent models like LSTMs frequently have the edge. Conversely, while LSTMs are well-suited for time series modeling due to their state-tracking capabilities, they lack strong in-context learning abilities. We introduce TiRex that closes this gap by leveraging xLSTM, an enhanced LSTM with competitive in-context learning skills. Unlike transformers, state-space models, or parallelizable RNNs such as RWKV, TiRex retains state-tracking, a critical property for long-horizon forecasting. To further facilitate its state-tracking ability, we propose a training-time masking strategy called CPM. TiRex sets a new state of the art in zero-shot time series forecasting on the HuggingFace benchmarks GiftEval and Chronos-ZS, outperforming significantly larger models including TabPFN-TS (Prior Labs), Chronos Bolt (Amazon), TimesFM (Google), and Moirai (Salesforce) across both short- and long-term forecasts.

版本更新 · v2arXiv:2510.01070Google DeepMind

Eliciting Secret Knowledge from Language Models

Bartosz Cywiński, Emil Ryd, Rowan Wang, Senthooran Rajamanoharan, Neel Nanda, Arthur Conmy, Samuel Marks

原文摘要

We study secret elicitation: discovering knowledge that an AI possesses but does not explicitly verbalize. As a testbed, we train three families of large language models (LLMs) to possess specific knowledge that they apply downstream but deny knowing when asked directly. For example, in one setting, we train an LLM to generate replies that are consistent with knowing the user is female, while denying this knowledge when asked directly. We then design various black-box and white-box secret elicitation techniques and evaluate them based on whether they can help an LLM auditor successfully guess the secret knowledge. Many of our techniques improve on simple baselines. Our most effective techniques (performing best in all settings) are based on prefill attacks, a black-box technique where the LLM reveals secret knowledge when generating a completion from a predefined prefix. Our white-box techniques based on logit lens and sparse autoencoders (SAEs) also consistently increase the success rate of the LLM auditor, but are less effective. We release our models and code, establishing a public benchmark for evaluating secret elicitation methods.

cs.LG

版本更新 · v2arXiv:2510.16629Google Research

On the Impossibility of Retrain Equivalence in Machine Unlearning

Jiatong Yu, Yinghui He, Anirudh Goyal, Sanjeev Arora

原文摘要

Machine unlearning seeks to selectively remove the "influence" of specific training data on a model's outputs. The ideal goal is Retrain Equivalence--behavior identical to a model trained from scratch on only the retained data. This goal was formulated for models trained on i.i.d. data batches, but modern pipelines often involve multi-stage training, with each stage having a distinct data distribution and objective. Examples include LLM fine-tuning for alignment, reasoning ability, etc. Our study shows via theory and experiments that this shift to multi-stage training introduces a fundamental barrier for machine unlearning. The theory indicates that the outcome of local unlearning--methods that only use gradients computed on the forget set--is path-dependent. That is, a model's behavior during unlearning is influenced by the order of its training stages during learning, making it impossible for path-oblivious algorithms to universally achieve Retrain Equivalence. We empirically demonstrate the same phenomenon in LLM post-training across Llama and Qwen models (1B to 14B) with gradient ascent, NPO, and SimNPO local unlearning algorithms. Models fine-tuned via different orderings of identical training stages diverge in behavior during unlearning, with the degradation in GSM8K accuracy after unlearning varying by over 20% across paths. We also observe that some learning paths consistently produce models that unlearn slowly. During unlearning, whether the probability mass gets squeezed into paraphrasing or alternative concepts is also path-dependent. These results consistently show that Retrain Equivalence is an ill-posed target for local unlearning algorithms, so long as the target models are trained in stages. In situations where access to models' training histories is hard, the current work calls for rethinking the definition and desiderata of machine unlearning.

cs.LG

版本更新 · v2arXiv:2510.22414Google Research

Complementary Human-AI Clinical Reasoning in Ophthalmology

Mertcan Sevgi, Fares Antaki, Abdullah Zafar Khan, Ariel Yuhan Ong, David Adrian Merle, Kuang Hu, Shafi Balal, Sophie-Christin Kornelia Ernst 等 29 位作者

原文摘要

Vision impairment and blindness are a major global health challenge where gaps in the ophthalmology workforce limit access to specialist care. We evaluate AMIE, a medically fine-tuned conversational system based on Gemini with integrated web search and self-critique reasoning, using real-world clinical vignettes that reflect scenarios a general ophthalmologist would be expected to manage. We conducted two complementary evaluations: (1) a human-AI interactive diagnostic reasoning study in which ophthalmologists recorded initial differentials and plans, then reviewed AMIE's structured output and revised their answers; and (2) a masked preference and quality study comparing AMIE's narrative outputs with case author reference answers using a predefined rubric. AMIE showed standalone diagnostic performance comparable to clinicians at baseline. Crucially, after reviewing AMIE's responses, ophthalmologists tended to rank the correct diagnosis higher, reached greater agreement with one another, and enriched their investigation and management plans. Improvements were observed even when AMIE's top choice differed from or underperformed the clinician baseline, consistent with a complementary effect in which structured reasoning support helps clinicians re-rank rather than simply accept the model output. Preferences varied by clinical grade, suggesting opportunities to personalise responses by experience. Without ophthalmology-specific fine-tuning, AMIE matched clinician baseline and augmented clinical reasoning at the point of need, motivating multi-axis evaluation, domain adaptation, and prospective multimodal studies in real-world settings.

cs.HC

版本更新 · v2arXiv:2505.17638Google Research

Why Diffusion Models Don't Memorize: The Role of Implicit Dynamical Regularization in Training

Tony Bonnaire, Raphaël Urfin, Giulio Biroli, Marc Mézard

原文摘要

Diffusion models have achieved remarkable success across a wide range of generative tasks. A key challenge is understanding the mechanisms that prevent their memorization of training data and allow generalization. In this work, we investigate the role of the training dynamics in the transition from generalization to memorization. Through extensive experiments and theoretical analysis, we identify two distinct timescales: an early time $τ_\mathrm{gen}$ at which models begin to generate high-quality samples, and a later time $τ_\mathrm{mem}$ beyond which memorization emerges. Crucially, we find that $τ_\mathrm{mem}$ increases linearly with the training set size $n$, while $τ_\mathrm{gen}$ remains constant. This creates a growing window of training times with $n$ where models generalize effectively, despite showing strong memorization if training continues beyond it. It is only when $n$ becomes larger than a model-dependent threshold that overfitting disappears at infinite training times. These findings reveal a form of implicit dynamical regularization in the training dynamics, which allow to avoid memorization even in highly overparameterized settings. Our results are supported by numerical experiments with standard U-Net architectures on realistic and synthetic datasets, and by a theoretical analysis using a tractable random features model studied in the high-dimensional limit.

cs.LG · cond-mat.dis-nn · stat.ML

版本更新 · v3arXiv:2506.04168Berkeley BAIR

缩短视野使强化学习具备可扩展性

Horizon Reduction Makes RL Scalable

Seohong Park, Kevin Frans, Deepinder Mann, Benjamin Eysenbach, Aviral Kumar, Sergey Levine

AI 速读 基于摘要

该论文研究离线强化学习的可扩展性,发现长视野是主要瓶颈,并提出通过视野缩减技术(如SHARSA)提升性能与扩展性。

cs.LG · cs.AI

查看原文摘要

In this work, we study the scalability of offline reinforcement learning (RL) algorithms. In principle, a truly scalable offline RL algorithm should be able to solve any given problem, regardless of its complexity, given sufficient data, compute, and model capacity. We investigate if and how current offline RL algorithms match up to this promise on diverse, challenging, previously unsolved tasks, using datasets up to 1000x larger than typical offline RL datasets. We observe that despite scaling up data, many existing offline RL algorithms exhibit poor scaling behavior, saturating well below the maximum performance. We hypothesize that the horizon is the main cause behind the poor scaling of offline RL. We empirically verify this hypothesis through several analysis experiments, showing that long horizons indeed present a fundamental barrier to scaling up offline RL. We then show that various horizon reduction techniques substantially enhance scalability on challenging tasks. Based on our insights, we also introduce a minimal yet scalable method named SHARSA that effectively reduces the horizon. SHARSA achieves the best asymptotic performance and scaling behavior among our evaluation methods, showing that explicitly reducing the horizon unlocks the scalability of offline RL. Code: https://github.com/seohongpark/horizon-reduction

版本更新 · v3arXiv:2405.18754Google Research

GIST: Greedy Independent Set Thresholding for Max-Min Diversification with Submodular Utility

Matthew Fahrbach, Srikumar Ramalingam, Morteza Zadimoghaddam, Sara Ahmadian, Gui Citovsky, Giulia DeSalvo

原文摘要

This work studies a novel subset selection problem called max-min diversification with monotone submodular utility ($\textsf{MDMS}$), which has a wide range of applications in machine learning, e.g., data sampling and feature selection. Given a set of points in a metric space, the goal of $\textsf{MDMS}$ is to maximize $f(S) = g(S) + λ\cdot \texttt{div}(S)$ subject to a cardinality constraint $|S| \le k$, where $g(S)$ is a monotone submodular function and $\texttt{div}(S) = \min_{u,v \in S : u \ne v} \text{dist}(u,v)$ is the max-min diversity objective. We propose the $\texttt{GIST}$ algorithm, which gives a $\frac{1}{2}$-approximation guarantee for $\textsf{MDMS}$ by approximating a series of maximum independent set problems with a bicriteria greedy algorithm. We also prove that it is NP-hard to approximate within a factor of $0.5584$. Finally, we show in our empirical study that $\texttt{GIST}$ outperforms state-of-the-art benchmarks for a single-shot data sampling task on ImageNet.

cs.DS · cs.LG

版本更新 · v3arXiv:2502.09863Berkeley BAIR

闭式训练动力学揭示类Word2Vec模型中学到的特征与线性结构

Closed-Form Training Dynamics Reveal Learned Features and Linear Structure in Word2Vec-like Models

Dhruva Karkada, James B. Simon, Yasaman Bahri, Michael R. DeWeese

AI 速读 基于摘要

作者对word2vec损失的四次Taylor近似进行解析求解,得到仅由语料统计和超参数表达的梯度流训练动力学与最终词嵌入,并据此解释线性子空间与语义概念的形成。

cs.LG · cs.CL · stat.ML

查看原文摘要

Self-supervised word embedding algorithms such as word2vec provide a minimal setting for studying representation learning in language modeling. We examine the quartic Taylor approximation of the word2vec loss around the origin, and we show that both the resulting training dynamics and the final performance on downstream tasks are empirically very similar to those of word2vec. Our main contribution is to analytically solve for both the gradient flow training dynamics and the final word embeddings in terms of only the corpus statistics and training hyperparameters. The solutions reveal that these models learn orthogonal linear subspaces one at a time, each one incrementing the effective rank of the embeddings until model capacity is saturated. Training on Wikipedia, we find that each of the top linear subspaces represents an interpretable topic-level concept. Finally, we apply our theory to describe how linear representations of more abstract semantic concepts emerge during training; these can be used to complete analogies via vector addition.

版本更新 · v3arXiv:2510.06189Google Research

Barbarians at the Gate: How AI is Upending Systems Research

Audrey Cheng, Shu Liu, Melissa Pan, Zhifei Li, Bowen Wang, Alex Krentsel, Tian Xia, Mert Cemri 等 17 位作者

原文摘要

Artificial Intelligence (AI) is starting to transform the research process as we know it by automating the discovery of new solutions. Given a task, the typical AI-driven approach is (i) to generate a set of diverse solutions, and then (ii) to verify these solutions and select one that solves the problem. Crucially, this approach assumes the existence of a reliable verifier, i.e., one that can accurately determine whether a solution solves the given problem. We argue that systems research, long focused on designing and evaluating new performance-oriented algorithms, is particularly well-suited for AI-driven solution discovery. This is because system performance problems naturally admit reliable verifiers: solutions are typically implemented in real systems or simulators, and verification reduces to running these software artifacts against predefined workloads and measuring performance. We term this approach as AI-Driven Research for Systems (ADRS), which iteratively generates, evaluates, and refines solutions. Using penEvolve, an existing open-source ADRS instance, we present case studies across diverse domains, including load balancing for multi-region cloud scheduling, Mixture-of-Experts inference, LLM-based SQL queries, and transaction scheduling. In multiple instances, ADRS discovers algorithms that outperform state-of-the-art human designs (e.g., achieving up to 5.0x runtime improvements or 50% cost reductions). We distill best practices for guiding algorithm evolution, from prompt design to evaluator construction, for existing frameworks. We then discuss the broader implications for the systems community: as AI assumes a central role in algorithm design, we argue that human researchers will increasingly focus on problem formulation and strategic guidance. Our results highlight both the disruptive potential and the urgent need to adapt systems research practices in the age of AI.

cs.AI

版本更新 · v2arXiv:2510.06124Google Research

Taxonomy of User Needs and Actions

Renee Shelby, Fernando Diaz, Vinodkumar Prabhakaran

原文摘要

The growing ubiquity of conversational AI highlights the need for frameworks that capture not only users' instrumental goals but also the situated, adaptive, and social practices through which they achieve them. Existing taxonomies of conversational behavior either overgeneralize, remain domain-specific, or reduce interactions to narrow dialogue functions. To address this gap, we introduce the Taxonomy of User Needs and Actions (TUNA), an empirically grounded framework developed through iterative qualitative analysis of 1193 human-AI conversations, supplemented by theoretical review and validation across diverse contexts. TUNA organizes user actions into a three-level hierarchy encompassing behaviors associated with information seeking, synthesis, procedural guidance, content creation, social interaction, and meta-conversation. By centering user agency and appropriation practices, TUNA enables multi-scale evaluation, supports policy harmonization across products, and provides a backbone for layering domain-specific taxonomies. This work contributes a systematic vocabulary for describing AI use, advancing both scholarly understanding and practical design of safer, more responsive, and more accountable conversational systems.

cs.HC · cs.CL

版本更新 · v11arXiv:2502.12110Berkeley BAIR

A-MEM:面向LLM智能体的智能体式记忆

A-MEM: Agentic Memory for LLM Agents

Wujiang Xu, Zujie Liang, Kai Mei, Hang Gao, Juntao Tan, Yongfeng Zhang

AI 速读 基于摘要

提出一种借鉴Zettelkasten方法、由智能体动态组织和演化记忆的LLM智能体记忆系统。

cs.CL · cs.HC

查看原文摘要

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 databases. Moreover, these systems' fixed operations and structures limit their adaptability across diverse tasks. To address this limitation, this paper proposes a novel agentic memory system for LLM agents that can dynamically organize memories in an agentic way. Following the basic principles of the Zettelkasten method, we designed our memory system to create interconnected knowledge networks through dynamic indexing and linking. When a new memory is added, we generate a comprehensive note containing multiple structured attributes, including contextual descriptions, keywords, and tags. The system then analyzes historical memories to identify relevant connections, establishing links where meaningful similarities exist. Additionally, this process enables memory evolution - as new memories are integrated, they can trigger updates to the contextual representations and attributes of existing historical memories, allowing the memory network to continuously refine its understanding. Our approach combines the structured organization principles of Zettelkasten with the flexibility of agent-driven decision making, allowing for more adaptive and context-aware memory management. Empirical experiments on six foundation models show superior improvement against existing SOTA baselines. The source code for evaluating performance is available at https://github.com/WujiangXu/A-mem, while the source code of the agentic memory system is available at https://github.com/WujiangXu/A-mem-sys.

版本更新 · v2arXiv:2505.24858Google Research

MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs

Gabrielle Kaili-May Liu, Gal Yona, Avi Caciularu, Idan Szpektor, Tim G. J. Rudner, Arman Cohan

原文摘要

A critical component in the trustworthiness of LLMs is reliable uncertainty communication, yet LLMs often use assertive language when conveying false claims, leading to over-reliance and eroded trust. We present the first systematic study of $\textit{faithful confidence calibration}$ of LLMs, benchmarking models' ability to use linguistic expressions of uncertainty that $\textit{faithfully reflect}$ their intrinsic uncertainty, across a comprehensive array of models, datasets, and prompting strategies. Our results demonstrate that LLMs largely fail at this task, and that existing interventions are insufficient: standard prompt approaches provide only marginal gains, and existing, factuality-based calibration techniques can even harm faithful calibration. To address this critical gap, we introduce MetaFaith, a novel prompt-based calibration approach inspired by human metacognition. We show that MetaFaith robustly improves faithful calibration across diverse models and task domains, enabling up to 61% improvement in faithfulness and achieving an 83% win rate over original generations as judged by humans.

cs.CL · cs.LG

版本更新 · v4arXiv:2509.13348Google Research

Towards an AI-Augmented Textbook

LearnLM Team, Google, :, Alicia Martín, Amir Globerson, Amy Wang, Anirudh Shekhawat, Anna Iurchenko 等 37 位作者

原文摘要

Textbooks are a cornerstone of education, but they have a fundamental limitation: they are a one-size-fits-all medium. Any new material or alternative representation requires arduous human effort, so that textbooks cannot be adapted in a scalable manner. We present an approach for transforming and augmenting textbooks using generative AI, adding layers of multiple representations and personalization while maintaining content integrity and quality. We refer to the system built with this approach as Learn Your Way. We report pedagogical evaluations of the different transformations and augmentations, and present the results of a a randomized control trial, highlighting the advantages of learning with Learn Your Way over regular textbook usage.

cs.CY · cs.HC

版本更新 · v2arXiv:2506.04681Google Research

Urania: Differentially Private Insights into AI Use

Daogao Liu, Edith Cohen, Badih Ghazi, Peter Kairouz, Pritish Kamath, Alexander Knop, Ravi Kumar, Pasin Manurangsi 等 11 位作者

原文摘要

We introduce $Urania$, a novel framework for generating insights about LLM chatbot interactions with rigorous differential privacy (DP) guarantees. The framework employs a private clustering mechanism and innovative keyword extraction methods, including frequency-based, TF-IDF-based, and LLM-guided approaches. By leveraging DP tools such as clustering, partition selection, and histogram-based summarization, $Urania$ provides end-to-end privacy protection. Our evaluation assesses lexical and semantic content preservation, pair similarity, and LLM-based metrics, benchmarking against a non-private Clio-inspired pipeline (Tamkin et al., 2024). Moreover, we develop a simple empirical privacy evaluation that demonstrates the enhanced robustness of our DP pipeline. The results show the framework's ability to extract meaningful conversational insights while maintaining stringent user privacy, effectively balancing data utility with privacy preservation.

cs.LG · cs.AI · cs.CL · cs.CR · cs.CY

版本更新 · v2arXiv:2506.10943Google Research

自适应语言模型

Self-Adapting Language Models

Adam Zweiger, Jyothish Pari, Han Guo, Ekin Akyürek, Yoon Kim, Pulkit Agrawal

AI 速读 基于摘要

提出 SEAL 框架,让大语言模型通过生成自编辑(自生成微调数据与更新指令)并经强化学习训练,实现持久的权重自适应。

cs.LG

查看原文摘要

Large language models (LLMs) are powerful but static; they lack mechanisms to adapt their weights in response to new tasks, knowledge, or examples. We introduce Self-Adapting LLMs (SEAL), a framework that enables LLMs to self-adapt by generating their own finetuning data and update directives. Given a new input, the model produces a self-edit-a generation that may restructure the information in different ways, specify optimization hyperparameters, or invoke tools for data augmentation and gradient-based updates. Through supervised finetuning (SFT), these self-edits result in persistent weight updates, enabling lasting adaptation. To train the model to produce effective self-edits, we use a reinforcement learning loop with the downstream performance of the updated model as the reward signal. Unlike prior approaches that rely on separate adaptation modules or auxiliary networks, SEAL directly uses the model's own generation to control its adaptation process. Experiments on knowledge incorporation and few-shot generalization show that SEAL is a promising step toward language models capable of self-directed adaptation. Our website and code is available at https://jyopari.github.io/posts/seal.

版本更新 · v4arXiv:2503.15299Google Research

Inside-Out: Hidden Factual Knowledge in LLMs

Zorik Gekhman, Eyal Ben David, Hadas Orgad, Eran Ofek, Yonatan Belinkov, Idan Szpektor, Jonathan Herzig, Roi Reichart

原文摘要

This work presents a framework for assessing whether large language models (LLMs) encode more factual knowledge in their parameters than what they express in their outputs. While a few studies hint at this possibility, none has clearly defined or demonstrated this phenomenon. We first propose a formal definition of knowledge, quantifying it for a given question as the fraction of correct-incorrect answer pairs where the correct one is ranked higher. This gives rise to external and internal knowledge, depending on the information used to score individual answer candidates: either the model's observable token-level probabilities or its intermediate computations. Hidden knowledge arises when internal knowledge exceeds external knowledge. We then present a case study, applying this framework to three popular open-weights LLMs in a closed-book QA setup. Our results indicate that: (1) LLMs consistently encode more factual knowledge internally than what they express externally, with an average relative gap of 40%. (2) Surprisingly, some knowledge is so deeply hidden that a model can internally know an answer perfectly, yet fail to generate it even once, despite large-scale repeated sampling of 1,000 answers. This reveals fundamental limitations in the generation capabilities of LLMs, which (3) put a practical constraint on scaling test-time compute via repeated answer sampling in closed-book QA: significant performance improvements remain inaccessible because some answers are practically never sampled, yet if they were, we would be guaranteed to rank them first.

cs.CL

版本更新 · v4arXiv:2406.13632Google Research

DoubleDipper: Improving Long-Context LLMs via Context Recycling

Arie Cattan, Alon Jacovi, Alex Fabrikant, Jonathan Herzig, Roee Aharoni, Hannah Rashkin, Dror Marcus, Avinatan Hassidim 等 11 位作者

原文摘要

Despite recent advancements in Large Language Models (LLMs), their performance on tasks involving long contexts remains sub-optimal. In this work, we propose DoubleDipper, a novel In-Context-Learning method that automatically generates few-shot examples for long context QA tasks by recycling contexts. Specifically, given a long input context (1-3k tokens) and a query, we generate additional query-output pairs from the given context as few-shot examples, while introducing the context only once. This ensures that the demonstrations are leveraging the same context as the target query while only adding a small number of tokens to the prompt. We further enhance each demonstration by instructing the model to explicitly identify the relevant paragraphs before the answer, which improves performance while providing fine-grained attribution to the answer source. We apply our method on multiple LLMs and obtain substantial improvements (+16 absolute points on average across models) on various QA datasets with long context. Surprisingly, despite introducing only single-hop ICL examples, LLMs successfully generalize to multi-hop long-context QA using our approach.

cs.CL

版本更新 · v2arXiv:2409.00920Google Research

ToolACE:赢得LLM函数调用的关键

ToolACE: Winning the Points of LLM Function Calling

Weiwen Liu, Xu Huang, Xingshan Zeng, Xinlong Hao, Shuai Yu, Dexun Li, Shuai Wang, Weinan Gan 等 27 位作者

AI 速读 基于摘要

ToolACE提出一种自动化的智能体流水线,用于生成准确、复杂且多样的工具学习数据,以提升大语言模型的函数调用能力。

cs.LG · cs.AI · cs.CL

查看原文摘要

Function calling significantly extends the application boundary of large language models, where high-quality and diverse training data is critical for unlocking this capability. However, real function-calling data is quite challenging to collect and annotate, while synthetic data generated by existing pipelines tends to lack coverage and accuracy. In this paper, we present ToolACE, an automatic agentic pipeline designed to generate accurate, complex, and diverse tool-learning data. ToolACE leverages a novel self-evolution synthesis process to curate a comprehensive API pool of 26,507 diverse APIs. Dialogs are further generated through the interplay among multiple agents, guided by a formalized thinking process. To ensure data accuracy, we implement a dual-layer verification system combining rule-based and model-based checks. We demonstrate that models trained on our synthesized data, even with only 8B parameters, achieve state-of-the-art performance on the Berkeley Function-Calling Leaderboard, rivaling the latest GPT-4 models. Our model and a subset of the data are publicly available at https://huggingface.co/Team-ACE.

版本更新 · v2arXiv:2506.15841Berkeley BAIR

MEM1:学习协同记忆与推理以实现高效长程智能体

MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents

Zijian Zhou, Ao Qu, Zhaoxuan Wu, Sunghwan Kim, Alok Prakash, Daniela Rus, Jinhua Zhao, Bryan Kian Hsiang Low 等 9 位作者

AI 速读 基于摘要

MEM1 是一个端到端强化学习框架,让语言智能体在长多轮任务中以恒定内存运行,通过紧凑共享状态协同记忆巩固与推理。

cs.CL · cs.AI · cs.IR

查看原文摘要

Modern language agents must operate over long-horizon, multi-turn interactions, where they retrieve external information, adapt to observations, and answer interdependent queries. Yet, most LLM systems rely on full-context prompting, appending all past turns regardless of their relevance. This leads to unbounded memory growth, increased computational costs, and degraded reasoning performance on out-of-distribution input lengths. We introduce MEM1, an end-to-end reinforcement learning framework that enables agents to operate with constant memory across long multi-turn tasks. At each turn, MEM1 updates a compact shared internal state that jointly supports memory consolidation and reasoning. This state integrates prior memory with new observations from the environment while strategically discarding irrelevant or redundant information. To support training in more realistic and compositional settings, we propose a simple yet effective and scalable approach to constructing multi-turn environments by composing existing datasets into arbitrarily complex task sequences. Experiments across three domains, including internal retrieval QA, open-domain web QA, and multi-turn web shopping, show that MEM1-7B improves performance by 3.5x while reducing memory usage by 3.7x compared to Qwen2.5-14B-Instruct on a 16-objective multi-hop QA task, and generalizes beyond the training horizon. Our results demonstrate the promise of reasoning-driven memory consolidation as a scalable alternative to existing solutions for training long-horizon interactive agents, where both efficiency and performance are optimized.

版本更新 · v4arXiv:2502.13497Google Research

Towards Geo-Culturally Grounded LLM Generations

Piyawat Lertvittayakumjorn, David Kinney, Vinodkumar Prabhakaran, Donald Martin, Sunipa Dev

原文摘要

Generative large language models (LLMs) have demonstrated gaps in diverse cultural awareness across the globe. We investigate the effect of retrieval augmented generation and search-grounding techniques on LLMs' ability to display familiarity with various national cultures. Specifically, we compare the performance of standard LLMs, LLMs augmented with retrievals from a bespoke knowledge base (i.e., KB grounding), and LLMs augmented with retrievals from a web search (i.e., search grounding) on multiple cultural awareness benchmarks. We find that search grounding significantly improves the LLM performance on multiple-choice benchmarks that test propositional knowledge (e.g., cultural norms, artifacts, and institutions), while KB grounding's effectiveness is limited by inadequate knowledge base coverage and a suboptimal retriever. However, search grounding also increases the risk of stereotypical judgments by language models and fails to improve evaluators' judgments of cultural familiarity in a human evaluation with adequate statistical power. These results highlight the distinction between propositional cultural knowledge and open-ended cultural fluency when it comes to evaluating LLMs' cultural awareness.

cs.CL · cs.AI

版本更新 · v2arXiv:2412.21033Google Research

Plancraft: an evaluation dataset for planning with LLM agents

Gautier Dagan, Frank Keller, Alex Lascarides

原文摘要

We present Plancraft, a multi-modal evaluation dataset for LLM agents. Plancraft has both a text-only and multi-modal interface, based on the Minecraft crafting GUI. We include the Minecraft Wiki to evaluate tool use and Retrieval Augmented Generation (RAG), as well as a handcrafted planner and Oracle Retriever, to ablate the different components of a modern agent architecture. To evaluate decision-making, Plancraft also includes a subset of examples that are intentionally unsolvable, providing a realistic challenge that requires the agent not only to complete tasks but also to decide whether they are solvable at all. We benchmark both open-source and closed-source LLMs and compare their performance and efficiency to a handcrafted planner. Overall, we find that LLMs and VLMs struggle with the planning problems that Plancraft introduces, and offer suggestions on how to improve their capabilities.

cs.CL · cs.AI

版本更新 · v2arXiv:2507.07789Berkeley BAIR

交替优化的计算高效信息驱动光学设计

Computationally Efficient Information-Driven Optical Design with Interchanging Optimization

Eric Markley, Henry Pinkard, Leyla Kabuli, Nalini Singh, Laura Waller

AI 速读 基于摘要

提出 IDEAL-IO,通过交替优化将密度估计与光学参数优化解耦,以更低内存和运行时间实现信息驱动的成像系统设计。

eess.IV · cs.CE · cs.CV · cs.IT

查看原文摘要

Recent work has demonstrated that imaging systems can be evaluated through the information content of their measurements alone, enabling application-agnostic optical design that avoids computational decoding challenges. Information-Driven Encoder Analysis Learning (IDEAL) was proposed to automate this process through gradient-based optimization. In this work, we study IDEAL across diverse imaging systems and find that it suffers from high memory usage, long runtimes, and a potentially mismatched objective function due to end-to-end differentiability requirements. We introduce IDEAL with Interchanging Optimization (IDEAL-IO), a method that decouples density estimation from optical parameter optimization by alternating between fitting models to current measurements and updating optical parameters using fixed models for information estimation. This approach reduces runtime and memory usage by up to 6x while enabling more expressive density models that guide optimization toward superior designs. We validate our method on diffractive optics, lensless imaging, and snapshot 3D microscopy applications, establishing information-theoretic optimization as a practical, scalable strategy for real-world imaging system design.

版本更新 · v4arXiv:2502.18968Google Research

Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles

Kuang Wang, Xianfei Li, Shenghao Yang, Li Zhou, Feng Jiang, Haizhou Li

原文摘要

User simulators are crucial for replicating human interactions with dialogue systems, supporting both collaborative training and automatic evaluation, especially for large language models (LLMs). However, current role-playing methods face challenges such as a lack of utterance-level authenticity and user-level diversity, often hindered by role confusion and dependence on predefined profiles of well-known figures. In contrast, direct simulation focuses solely on text, neglecting implicit user traits like personality and conversation-level consistency. To address these issues, we introduce the User Simulator with Implicit Profiles (USP), a framework that infers implicit user profiles from human-machine interactions to simulate personalized and realistic dialogues. We first develop an LLM-driven extractor with a comprehensive profile schema, then refine the simulation using conditional supervised fine-tuning and reinforcement learning with cycle consistency, optimizing at both the utterance and conversation levels. Finally, a diverse profile sampler captures the distribution of real-world user profiles. Experimental results show that USP outperforms strong baselines in terms of authenticity and diversity while maintaining comparable consistency. Additionally, using USP to evaluate LLM on dynamic multi-turn aligns well with mainstream benchmarks, demonstrating its effectiveness in real-world applications.

cs.CL

版本更新 · v3arXiv:2506.06266Berkeley BAIRGoogle Research

Cartridges:通过自学实现轻量且通用的长上下文表示

Cartridges: Lightweight and general-purpose long context representations via self-study

Sabri Eyuboglu, Ryan Ehrlich, Simran Arora, Neel Guha, Dylan Zinsley, Emily Liu, Will Tennien, Atri Rudra 等 11 位作者

AI 速读 基于摘要

提出 Cartridge 方法:针对每个语料离线训练小型 KV cache,并用 self-study(合成对话+上下文蒸馏)训练,使其在长上下文任务上接近 ICL 效果且显著降低服务成本。

cs.CL · cs.AI · cs.LG

查看原文摘要

Large language models are often used to answer queries grounded in large text corpora (e.g. codebases, legal documents, or chat histories) by placing the entire corpus in the context window and leveraging in-context learning (ICL). Although current models support contexts of 100K-1M tokens, this setup is costly to serve because the memory consumption of the KV cache scales with input length. We explore an alternative: training a smaller KV cache offline on each corpus. At inference time, we load this trained KV cache, which we call a Cartridge, and decode a response. Critically, the cost of training a Cartridge can be amortized across all the queries referencing the same corpus. However, we find that the naive approach of training the Cartridge with next-token prediction on the corpus is not competitive with ICL. Instead, we propose self-study, a training recipe in which we generate synthetic conversations about the corpus and train the Cartridge with a context-distillation objective. We find that Cartridges trained with self-study replicate the functionality of ICL, while being significantly cheaper to serve. On challenging long-context benchmarks, Cartridges trained with self-study match ICL performance while using 38.6x less memory and enabling 26.4x higher throughput. Self-study also extends the model's effective context length (e.g. from 128k to 484k tokens on MTOB) and surprisingly, leads to Cartridges that can be composed at inference time without retraining.

版本更新 · v2arXiv:2506.01372Google Research

AI Scientists Fail Without Strong Implementation Capability

Minjun Zhu, Qiujie Xie, Yixuan Weng, Jian Wu, Zhen Lin, Linyi Yang, Yue Zhang

原文摘要

The emergence of Artificial Intelligence (AI) Scientist represents a paradigm shift in scientific discovery, with large language models (LLMs) taking the lead as the primary executor in the entire scientific workflow from idea generation to experiment implementation. Recent AI Scientist studies demonstrate sufficient capabilities for independent scientific discovery, with the generated research reports gaining acceptance at the ICLR 2025 workshop and ACL 2025, arguing that a human-level AI Scientist, capable of uncovering phenomena previously unknown to humans, may be imminent. Despite this substantial progress, AI Scientist has yet to produce a groundbreaking achievement in the domain of computer science on par with automated scientific tools. Based on extensive quantitative evidence from existing benchmarks in complex engineering tasks and a systematic evaluation assess 28 research papers generated by five advanced AI Scientist systems, we argue that \textbf{the fundamental bottleneck for AI Scientists lies in their capability to execute the requisite verification procedures.} Current AI Scientist systems lack the execution capabilities needed to execute rigorous experiments and produce high-quality scientific papers. To better illustrate the root cause of this \textbf{implementation gap}, we provide an in-depth discussion on the fundamental limitations of AI Scientist. This position paper aims to call for the participants in the community to bridge the implementation gap.

cs.AI · cs.CL · cs.LG

版本更新 · v2arXiv:2412.20292Google Research

An analytic theory of creativity in convolutional diffusion models

Mason Kamb, Surya Ganguli

原文摘要

We obtain an analytic, interpretable and predictive theory of creativity in convolutional diffusion models. Indeed, score-matching diffusion models can generate highly original images that lie far from their training data. However, optimal score-matching theory suggests that these models should only be able to produce memorized training examples. To reconcile this theory-experiment gap, we identify two simple inductive biases, locality and equivariance, that: (1) induce a form of combinatorial creativity by preventing optimal score-matching; (2) result in fully analytic, completely mechanistically interpretable, local score (LS) and equivariant local score (ELS) machines that, (3) after calibrating a single time-dependent hyperparameter can quantitatively predict the outputs of trained convolution only diffusion models (like ResNets and UNets) with high accuracy (median $r^2$ of $0.95, 0.94, 0.94, 0.96$ for our top model on CIFAR10, FashionMNIST, MNIST, and CelebA). Our model reveals a locally consistent patch mosaic mechanism of creativity, in which diffusion models create exponentially many novel images by mixing and matching different local training set patches at different scales and image locations. Our theory also partially predicts the outputs of pre-trained self-attention enabled UNets (median $r^2 \sim 0.77$ on CIFAR10), revealing an intriguing role for attention in carving out semantic coherence from local patch mosaics.

cs.LG · cond-mat.dis-nn · cs.AI · q-bio.NC · stat.ML

版本更新 · v3arXiv:2406.01388Google Research

AutoStudio:在多轮交互式图像生成中塑造一致的主体

AutoStudio: Crafting Consistent Subjects in Multi-turn Interactive Image Generation

Junhao Cheng, Xi Lu, Hanhui Li, Khun Loun Zai, Baiqiao Yin, Yuhao Cheng, Yiqiang Yan, Xiaodan Liang

AI 速读 基于摘要

提出免训练的多智能体框架 AutoStudio,通过 LLM 智能体与改进的扩散模型,在多轮交互中保持多主体一致性。

cs.CV

查看原文摘要

As cutting-edge Text-to-Image (T2I) generation models already excel at producing remarkable single images, an even more challenging task, i.e., multi-turn interactive image generation begins to attract the attention of related research communities. This task requires models to interact with users over multiple turns to generate a coherent sequence of images. However, since users may switch subjects frequently, current efforts struggle to maintain subject consistency while generating diverse images. To address this issue, we introduce a training-free multi-agent framework called AutoStudio. AutoStudio employs three agents based on large language models (LLMs) to handle interactions, along with a stable diffusion (SD) based agent for generating high-quality images. Specifically, AutoStudio consists of (i) a subject manager to interpret interaction dialogues and manage the context of each subject, (ii) a layout generator to generate fine-grained bounding boxes to control subject locations, (iii) a supervisor to provide suggestions for layout refinements, and (iv) a drawer to complete image generation. Furthermore, we introduce a Parallel-UNet to replace the original UNet in the drawer, which employs two parallel cross-attention modules for exploiting subject-aware features. We also introduce a subject-initialized generation method to better preserve small subjects. Our AutoStudio hereby can generate a sequence of multi-subject images interactively and consistently. Extensive experiments on the public CMIGBench benchmark and human evaluations show that AutoStudio maintains multi-subject consistency across multiple turns well, and it also raises the state-of-the-art performance by 13.65% in average Frechet Inception Distance and 2.83% in average character-character similarity.

版本更新 · v2arXiv:2505.22257Google Research

重新审视组相对策略优化:在策略与离策略训练的洞见

Revisiting Group Relative Policy Optimization: Insights into On-Policy and Off-Policy Training

Youssef Mroueh, Nicolas Dupuis, Brian Belgodere, Apoorva Nitsure, Mattia Rigotti, Kristjan Greenewald, Jiri Navratil, Jerret Ross 等 9 位作者

AI 速读 基于摘要

作者将 GRPO 扩展到离策略设定,并比较在策略与离策略两种 GRPO 变体在可验证奖励强化学习后训练中的表现。

cs.LG · stat.ML

查看原文摘要

We revisit Group Relative Policy Optimization (GRPO) in both on-policy and off-policy optimization regimes. Our motivation comes from recent work on off-policy Proximal Policy Optimization (PPO), which improves training stability, sampling efficiency, and memory usage. In addition, a recent analysis of GRPO suggests that estimating the advantage function with off-policy samples could be beneficial. Building on these observations, we adapt GRPO to the off-policy setting. We show that both on-policy and off-policy GRPO objectives yield an improvement in the reward. This result motivates the use of clipped surrogate objectives in the off-policy version of GRPO. We then compare the empirical performance of reinforcement learning with verifiable rewards in post-training using both GRPO variants. Our results show that off-policy GRPO either significantly outperforms or performs on par with its on-policy counterpart.

版本更新 · v2arXiv:2504.17502Google Research

RefVNLI: Towards Scalable Evaluation of Subject-driven Text-to-image Generation

Aviv Slobodkin, Hagai Taitelbaum, Yonatan Bitton, Brian Gordon, Michal Sokolik, Nitzan Bitton Guetta, Almog Gueta, Royi Rassin 等 10 位作者

原文摘要

Subject-driven text-to-image (T2I) generation aims to produce images that align with a given textual description, while preserving the visual identity from a referenced subject image. Despite its broad downstream applicability - ranging from enhanced personalization in image generation to consistent character representation in video rendering - progress in this field is limited by the lack of reliable automatic evaluation. Existing methods either assess only one aspect of the task (i.e., textual alignment or subject preservation), misalign with human judgments, or rely on costly API-based evaluation. To address this gap, we introduce RefVNLI, a cost-effective metric that evaluates both textual alignment and subject preservation in a single run. Trained on a large-scale dataset derived from video-reasoning benchmarks and image perturbations, RefVNLI outperforms or statistically matches existing baselines across multiple benchmarks and subject categories (e.g., \emph{Animal}, \emph{Object}), achieving up to 6.4-point gains in textual alignment and 5.9-point gains in subject preservation.

cs.CV

版本更新 · v2arXiv:2502.05564Google Research

TabICL: A Tabular Foundation Model for In-Context Learning on Large Data

Jingang Qu, David Holzmüller, Gaël Varoquaux, Marine Le Morvan

原文摘要

The long-standing dominance of gradient-boosted decision trees on tabular data is currently challenged by tabular foundation models using In-Context Learning (ICL): setting the training data as context for the test data and predicting in a single forward pass without parameter updates. While TabPFNv2 foundation model excels on tables with up to 10K samples, its alternating column- and row-wise attentions make handling large training sets computationally prohibitive. So, can ICL be effectively scaled and deliver a benefit for larger tables? We introduce TabICL, a tabular foundation model for classification, pretrained on synthetic datasets with up to 60K samples and capable of handling 500K samples on affordable resources. This is enabled by a novel two-stage architecture: a column-then-row attention mechanism to build fixed-dimensional embeddings of rows, followed by a transformer for efficient ICL. Across 200 classification datasets from the TALENT benchmark, TabICL is on par with TabPFNv2 while being systematically faster (up to 10 times), and significantly outperforms all other approaches. On 53 datasets with over 10K samples, TabICL surpasses both TabPFNv2 and CatBoost, demonstrating the potential of ICL for large data. Pretraining code, inference code, and pre-trained models are available at https://github.com/soda-inria/tabicl.

cs.LG · cs.AI