Scaling Mathematical Proof Supervision from Structured Textbooks
Youqing Fang, Zhouqi Hua, Yinhao Tang, Yuzhe Gu, Lingkai Kong, Bin Liu, Weiming Zhang, Kai Chen 等 10 位作者
AI 速览：将2,118本大学数学教科书转化为约38万条保留章节顺序与命题-证明结构的证明监督记录，并研究课程学习与规模规律。
Mathematical supervision for language models is typically flattened into isolated problem-solution pairs, discarding the curricular organization and evidential structure of the original sources. We introduce TOME-Math (Textbook-Oriented Mathematical Evidence), a large-scale corpus that converts 2,118 textbooks spanning the core areas of university-level mathematics subjects into approximately 380K structured proof-supervision records while preserving chapter order, proposition-proof links, dependency references, and source provenance. Leveraging these structural signals, we explore curriculum learning across multiple mathematical subjects and characterize scaling patterns with supervision volume and source breadth. At full scale, fine-tuning on TOME-Math raises the unweighted mean score across our held-out evaluations and established public benchmarks by 16.7 percentage points over the base model, while exceeding all three public instruction-data baselines evaluated in aggregate. Our findings highlight structured textbooks as both a scalable source of mathematical supervision and an empirical framework for studying the impact of data organization on mathematical reasoning. We will release the corpus to facilitate further research on structured mathematical supervision.
Zero-shot object navigation requires an agent to reason about where a target may be found while retaining evidence from previous observations. We present HGWM, a hierarchical graph-guided world model that combines a category-conditioned room--anchor prior with persistent spatial-semantic memory. A coarse stage uses a vision-language model to score candidate headings, while a fine stage explicitly compares observed objects and relations with the goal prior. Phase-dependent fusion integrates these signals with a language-model recommendation to guide local navigation. HGWM achieves 62.6\% success rate (SR) and 31.5\% success weighted by path length (SPL) on HM3D v0.1, improving over WMNav by 4.5 and 0.3 percentage points, respectively. On MP3D, it achieves 46.8\% SR and 17.9\% SPL, with gains of 1.4 and 0.7 points. On HM3D v0.2, the full model reaches 74.4\% SR and 31.9\% SPL; removing individual components reduces SR by 0.9--2.3 points and SPL by 0.6--1.5 points. These results support the use of relational priors and persistent graph memory for target-directed search.
Large language models are typically adapted to a task either by placing knowledge in the input context, which keeps it external and re-encodes it on every call, or by fine-tuning, which internalizes it but demands a costly round of optimization per task. We aim to internalize the knowledge carried by a context directly into model parameters, without per-task optimization and without keeping the context in the input at inference time. To this end, we propose CLIK, a context-conditioned parameter generator that maps a given context to LoRA parameters for internalizing knowledge in a single forward pass through a Transformer encoder with cross-attention, requiring no test-time gradient updates. Once the generated LoRA is inserted into a frozen base model, the model answers downstream queries from the query alone, having internalized the context into its weights rather than re-reading it. Because the adapter depends only on the context, it is generated once and reused for every query on the same document, so the cost of reading that document is amortized across queries. On document question answering, CLIK substantially improves over the no-context base model and outperforms existing hypernetwork-based generators, while remaining behind a base model that reads the context directly, and it carries over to multi-turn dialogue without any multi-turn-specific training. Analysis further shows that the context-dependent part of the generated adapter concentrates in a compact and specific substructure.
Zhefan Rao, Meng Chu, Xuan Billy Zhang, Jingfan Chen, Guohao Cai, Runyi Li, Shiyi Du, Xu Huang 等 92 位作者
World Models (WMs) can support Multimodal Agents (MAs) through simulated experience, while Agent trajectories can inform World Model refinement. Evaluating this interaction requires separate evidence about action selection and state evolution. We introduce Dual Exam, which tests Agents under fixed environment response mechanisms and World Models under fixed action interventions across physical, digital, social, and scientific domains. The Agent track compares 10 configurations on 1,088 items in 15 reporting categories. The World Model track contains 400 cases across eight scenarios; 15 configurations have full coverage and one covers six scenarios. GPT 6 Astra leads the case-weighted Agent Index at 31.3, and GPT-Image-2 leads the full-coverage WM Overall at 21.7. These scores use different tasks and metrics and are not directly comparable. A 150-case pilot of one coupled pairing records zero task successes and motivates component-level diagnosis. Results reveal uneven task performance and failures to preserve task-relevant state. Their value for predicting coupled success or sustained reciprocal learning remains to be established.
Visual generation requires both high-level semantic knowledge and fine-grained pixel details. We propose a learning paradigm that assigns these roles to autoregressive pretraining for knowledge acquisition and diffusion post-training for high-fidelity rendering. Within this framework, we study the objective, representation, and scaling of knowledge acquisition and rendering. Controlled comparisons identify autoregression as the stronger pretraining objective for downstream rendering, improving both learning efficiency and final generation quality. We further find that AR-only generation quality does not necessarily correlate with final performance; semantic quality matters more. This motivates a purely semantic tokenizer trained with language supervision alone, without an image decoder or reconstruction loss. We establish compute-optimal scaling laws for knowledge acquisition and rendering, and find that autoregressive pretraining lowers the fitted asymptotic rendering loss compared with pixel diffusion models trained from scratch. Guided by the laws, we train a 3B-parameter text-to-image model with only 6,600 H100 GPU-hours, achieving 86 on GenEval and 87 on DPG-Bench and validating the proposed paradigm at scale.
Jinhao Tan, Jam Kabeer Ali Khan, Bruno C. d. S. Oliveira
First-class environments expose runtime environments as ordinary values and support a substitution-free, environment-based operational semantics. They also support applications such as first-class modules, dynamic composition of environment fragments, and sandboxing via local environments. Existing environment-based calculi, however, are mostly studied in a simply typed setting and stop short of System F and polymorphism. We present $F_E$, a polymorphic calculus with first-class environments that conservatively extends System F with a small-step environment semantics. $F_E$ eliminates all forms of substitution in System F. Term and type abstractions evaluate to closures, boxes run code under local environments, and box types expose the local typing assumptions of both. Manifest types, together with a two-sided type equivalence, play a dual role: they model type-level instantiation, and enable transparent type components in environments and modules. We prove type soundness, normalization, decidability, and standard properties of type equivalence, and conservativity over System F. The metatheory of $F_E$ is based on instantiation lemmas rather than substitution lemmas. This foundation supports polymorphic first-class modules with dynamic composition and sandboxing. We study $F_E$ in two forms. Our main presentation is an explicit, type-passing calculus that follows conventional System F. We also develop an implicitly-typed variant aligned with the semantics of polymorphic functional languages. All metatheory is mechanized in the Rocq theorem prover.
Xi Chen, Chongjian Ge, Yiran Xu, Yiqun Mei, Henrik I. Christensen, Hao Tan, Ziwen Chen, Hanwen Jiang
As autonomous research systems become more capable, benchmarks must both evaluate their performance and support meaningful research progress. We introduce Auto-Research Arena, a multi-target benchmark for evaluating autonomous research systems and discovering ideas in language modeling. Arena supports diverse research objectives within a shared experimental environment by separating admissibility from improvement: model quality and resource constraints determine whether a result qualifies, while the selected target measures progress among admissible results. We instantiate Arena in language model pretraining with nine targets spanning model, data, training, and inference efficiency, and evaluate seven research harnesses using two foundation models. Arena clearly differentiates existing harnesses across research objectives, with several sophisticated methods outperformed by our simple sequential search baseline, indicating substantial headroom in current auto-research systems. Beyond evaluation, Arena reveals a substantially broader frontier of model and system ideas aligned with active research directions. Reusing these discoveries in a new quality-driven search yields lower training loss under matched data and FLOPs and lower held-out BPB at the same model size. Together, Arena provides a common framework for benchmarking autonomous research and expanding its scope in language modeling. The code is available at https://github.com/Auto-Research-Arena/auto-research-arena
Zipeng Ling, Shuliang Liu, Seonil Son, Shenghong Fu, Yuehao Tang, Yao Wan, Xuming Hu
Large language models (LLMs) have become increasingly used for various tasks, often coupled with Chain-of-Thought (CoT) prompting to boost accuracy. Recent work has shown that high label-prediction accuracy does not guarantee correct intermediate reasoning, and the causes of *reasoning flaws* vary from sample to sample, yet existing remedies either focus on a single domain or assume that one flaw type applies uniformly across samples. A simple mitigation method is to provide the model with the correct answer, but we show that this yields no consistent improvement in reasoning quality. This indicates that the problem cannot be fixed by LLMs' awareness of answers, and must instead be addressed through the *structure* of reasoning. Motivated by this, we propose CRAFT (Consensus Reasoning knowledge graph Aggregation for Flaw-aware Trace synthesis), which aggregates the consensus components shared across multiple candidate reasoning traces to synthesize improved ones. CRAFT consistently improves label-prediction accuracy on both logical and mathematical reasoning benchmarks, outperforming most baselines, while its post-processed traces achieve higher quality under fine-grained benchmark evaluation.
Large Language Models (LLMs) are increasingly trained to abstain from answering questions they are unsure about. However, this ability is often misapplied: in real-world applications, user prompts sometimes contain elements of uncertainty, which lead LLMs to abstain even on problems they are capable of solving. We argue that LLM abstention is not only an expression of genuine uncertainty; it can also be an artifact largely shaped by prompts. We name this phenomenon *Abstention Inflation*. We add "Unknown" as an extra option for LLMs to choose from; experiments show serious accuracy drops on True/False Questions (TFQs). Replacing "Unknown" with an unrelated random word produces a similar effect. We argue that LLMs are trained to imitate the surface pattern of abstention, rather than to express genuine uncertainty. Based on ten experimental settings, we support four claims that form a progressive argument: **(C1)** *Abstention Inflation* can be triggered by the presence of an extra option, not by genuine uncertainty; **(C2)** it makes the models deny they can answer, even when they can; **(C3)** it is a later-layer output override, as the reasoning traces and mid-layer representations preserve correct answers; **(C4)** it is not stochastic noise: it results from various factors, emerges through instruction tuning, is boosted by problems' higher difficulty, and can be mitigated at larger model sizes.
Chenglong Ma, Yuanfeng Ji, Junzhi Ning, Jiyao Liu, Yujie Wei, Shaohao Rui, Chaoyang Zhang, Wenjie Li 等 21 位作者
Multimodal medical AI requires a common visual interface for encoding heterogeneous imaging evidence for patient condition modeling. However, existing medical visual tokenizers are often tied to a specific dimension and imaging modality, forcing multimodal systems to rely on fragmented and poorly reusable representations. We introduce MedVTok, a general-purpose visual tokenizer that maps 2D images and 3D volumes from diverse imaging modalities into a unified token space. Building such a tokenizer poses two key challenges: preserving anatomical structure across dimensions and capturing clinical semantics across modalities. To this end, MedVTok introduces (i) slice differential regularization, which explicitly models inter-slice anatomical coherence missing in previous per-pixel/per-voxel supervision, and (ii) multi-expert representation alignment, which integrates knowledge from multiple medical expert encoders while retaining modality-specific complementary knowledge. Trained on 28M images and 70K volumes across 9 imaging modalities, MedVTok supports classification, retrieval, segmentation, synthesis, visual question answering, and medical report generation through a single tokenizer. Across 24 benchmarks, MedVTok achieves state-of-the-art performance, demonstrating a scalable token interface that unifies medical image dimension, modality, and task usage.
Large Language Models (LLMs) have shown remarkable capabilities across tasks, but they still struggle with complex reasoning that requires integrating scattered knowledge. Graph Retrieval-Augmented Generation (GraphRAG) addresses this challenge by organizing fragment knowledge as graphs, while recent Graph Foundation Models (GFMs) further improve GraphRAG with graph-native retrieval and reasoning capabilities. However, existing GraphRAG methods usually adopt decoupled retrieve-then-generate pipelines, which create objective misalignment between retrieval and reasoning, and training GFM retrievers typically depends on expensive human annotations. To address these limitations, we propose \ourmethod, a unified end-to-end GraphRAG framework that tightly couples a GFM retriever with an LLM generator. Given a query, the GFM retriever first reasons over the graph to score and retrieve relevant document nodes. These node embeddings are then passed through a fully differentiable graph bridge, which projects them into soft-weighted graph prefixes according to retrieval scores and combines them with raw document texts to form graph-augmented prompts. In this way, structural information is injected directly into LLM generation, while the final answer loss can be back-propagated through the bridge to jointly optimize retrieval and reasoning. To stabilize training and reduce reliance on costly annotations, we further introduce a semantic-guided distillation module that provides auxiliary supervision using pseudo-labels derived from query-document semantic similarities. Extensive experiments on three multi-hop QA datasets and three out-of-domain GraphRAG benchmarks show that \ourmethod consistently outperforms strong baseline methods and generalizes well, which demonstrates the effectiveness of end-to-end GraphRAG with tightly integrated GFM retrieval and LLM reasoning.
Karen Zhou University of Chicago, Chenhao Tan University of Chicago
Checklists have emerged as a popular approach for interpretable and fine-grained evaluation, particularly with LLM-as-a-Judge. Beyond evaluation, these structured criteria can serve as signals for model alignment, reinforcement learning, and self-correction. To support these use cases, we present AutoChecklist, an open-source library that unifies checklist-based evaluation into composable pipelines. At its core is a taxonomy of five checklist generation abstractions, each encoding a distinct strategy for deriving evaluation criteria. A modular \textit{Generator $\rightarrow$ Refiner $\rightarrow$ Scorer} pipeline connects any generator with a unified scorer, and new configurations can be registered via prompt templates alone. The library ships with ten built-in pipelines implementing published approaches and supports multiple LLM providers (OpenAI, OpenRouter, vLLM). Beyond the Python API, the library includes a CLI for off-the-shelf evaluation and a web interface for interactive exploration. Validation experiments confirm that these checklist methods significantly align with human preferences and quality ratings, and a case study on ICLR peer review rebuttals demonstrates flexible domain adaptation. AutoChecklist is publicly available at https://github.com/ChicagoHAI/AutoChecklist.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations) · 2026 · 正式发表
Yinghao Tang State key laboratory of CAD&CG, Zhejiang University, Yupeng Xie, Yingchaojie Feng, Tingfeng Lan, Wei Chen Zhejiang University
Interactive articles help readers engage with complex ideas through exploration, yet creating them remains costly, requiring both domain expertise and web development skills. Recent LLM-based agents can automate content creation, but naively applying them yields uncontrollable and unverifiable outputs. We present Vividoc, a human-agent collaborative system that generates interactive educational documents from a single topic input. Vividoc introduces a multi-agent pipeline (Planner, Executor, Evaluator) and the Document Specification (DocSpec), a human-readable intermediate representation that decomposes each interactive visualization into State, Render, Transition, and Constraint components. The DocSpec enables educators to review and refine generation plans before code is produced, bridging the gap between pedagogical intent and executable output. We collect a dataset of 101 real-world interactive documents across 11 domains and conduct a user study showing that ViviDoc produces documents comparable in quality to human-authored ones. Our demo is available at https://vividoc.vercel.app/ and a video demonstration at https://www.youtube.com/watch?v=rJrnPJLyHUI.
尚无 AI 解读，展示原文摘要
cs.CL · cs.MA
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations) · 2026 · 正式发表
Zihao Tang, Xin Yu, Ziyu Xiao, Zengxuan Wen Microsoft, Zelin Li Microsoft, Jiaxi Zhou, Hualei Wang Center for Excellence in Brain Science and Intelligence Technology (Institute of Neuroscience), Chinese Academy of Sciences and University of Chinese Academy of Sciences, Haohua Wang 等 12 位作者
AI Memory, specifically how models organizes and retrieves historical messages, becomes increasingly valuable to Large Language Models (LLMs), yet existing methods (RAG and Graph-RAG) primarily retrieve memory through similarity-based mechanisms. While efficient, such System-1-style retrieval struggles with scenarios that require global reasoning or comprehensive coverage of all relevant information. In this work, We propose Mnemis, a novel memory framework that integrates System-1 similarity search with a complementary System-2 mechanism, termed Global Selection. Mnemis organizes memory into a base graph for similarity retrieval and a hierarchical graph that enables top-down, deliberate traversal over semantic hierarchies. By combining the complementary strength from both retrieval routes, Mnemis retrieves memory items that are both semantically and structurally relevant. Mnemis achieves state-of-the-art performance across all compared methods on long-term memory benchmarks, scoring 93.9 on LoCoMo and 91.6 on LongMemEval-S using GPT-4.1-mini.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Yinghao Tang State key laboratory of CAD&CG, Zhejiang University, Xueding Liu University of Electronic Science and Technology of China, Boyuan Zhang, Tingfeng Lan, Yupeng Xie, Jiale Lao, Yiyao Wang, Haoxuan Li Zhejiang University 等 16 位作者
Infographics are composite visual artifacts that combine data visualizations with textual and illustrative elements to communicate information. While recent text-to-image (T2I) models can generate aesthetically appealing images, their reliability in generating infographics remains unclear. Generated infographics may appear correct at first glance but contain easily overlooked issues, such as distorted data encoding or incorrect textual content. We present IGenBench, the first benchmark for evaluating the reliability of text-to-infographic generation, comprising 600 curated test cases spanning 30 infographic types. We design an automated evaluation framework that decomposes reliability verification into atomic yes/no questions based on a taxonomy of 10 question types. We employ multimodal large language models (MLLMs) to verify each question, yielding question-level accuracy (Q-ACC) and infographic-level accuracy (I-ACC). We comprehensively evaluate 10 state-of-the-art T2I models on IGenBench. Our systematic analysis reveals key insights for future model development: (i) a three-tier performance hierarchy with the top model achieving Q-ACC of 0.90 but I-ACC of only 0.49; (ii) data-related dimensions emerging as universal bottlenecks (e.g., Data Completeness: 0.21); and (iii) the challenge of achieving end-to-end correctness across all models.
尚无 AI 解读，展示原文摘要
cs.CL · cs.CV
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Zhong-Zhi Li, Xiao Liang, Zihao Tang, Lei Ji, Peijie Wang, Haotian Xu, Xing W, Haizhen Huang 等 14 位作者
Large Language Models (LLMs) have recently achieved remarkable progress on complex reasoning tasks by leveraging extended Chain-of-Thought (CoT) techniques. These reasoning processes can be roughly categorized into System-1 (fast and intuitive) and System-2 (slow and deliberate) paradigms. However, excessive reliance on lengthy System-2-style reasoning during inference can produce extremely long outputs, thereby reducing efficiency. In this work, we propose Thinking Length Data Re-weighting (TLDR), that does not rely on sophisticated data annotations or interpolation between multiple models. We continuously balance the weights between the model’s System-1 and System-2 data to eliminate redundant reasoning processes while preserving the model’s reasoning capability. We validate our method across multiple base models, including Deepseek-R1-Distilled Qwen models, as well as on a diverse benchmarks with varying difficulty levels. Our method significantly reduces the number of output tokens by nearly 40% while maintaining the accuracy of the reasoning.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Mingxuan Li, Hanchen Li, Chenhao Tan University of Chicago
Large language models (LLMs) have demonstrated great potential for automating the evaluation of natural language generation. Previous frameworks of LLM-as-a-judge fall short in two ways: they either use zero-shot setting without consulting any human input, which leads to low alignment, or fine-tune LLMs on labeled data, which requires a non-trivial number of samples. Moreover, previous methods often provide little reasoning behind automated evaluations. In this paper, we propose HypoEval, Hypothesis-guided Evaluation framework, which first uses a small corpus of human evaluations to generate more detailed rubrics for human judgments and then incorporates a checklist-like approach to combine LLM’s assigned scores on each decomposed dimension to acquire overall scores. With only 30 human evaluations, HypoEval achieves state-of-the-art performance in alignment with both human rankings (Spearman correlation) and human scores (Pearson correlation), on average outperforming G-Eval by 11.86% and fine-tuned Llama-3.1-8B-Instruct with at least 3 times more human evaluations by 11.95%. Furthermore, we conduct systematic studies to assess the robustness of HypoEval, highlighting its effectiveness as a reliable and interpretable automated evaluation framework.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Dezhao Tang, Meihan Liu China University of Mining Technology - Xuzhou, Yulai Tong China University of Mining Technology - Xuzhou, Guan Yuan, Qiuyan Yan China University of Mining Technology - Xuzhou
Dynamic reasoning trees can help large language models solve complex tasks by explicitly structuring intermediate decisions.However, existing approaches often rely on manually specified subproblems or predefined decomposition patterns, which limits the effectiveness of reasoning and generalization.To solve this problem, we propose SyRA, a hierarchical reasoning framework based on MFR theory that supports the construction of adaptive reasoning trees and reliable error correction within a single LLM. Specifically, SyRA focuses on reasoning-tree construction, dynamically controlling branching and expansion using MFR principles to enable informative, non-redundant subproblem decomposition. In addition, it introduces a residual backtracking mechanism for adaptive cross-layer error correction, allowing the model to revise earlier reasoning decisions based on downstream feedback.Across eight reasoning benchmarks, SyRA significantly reduces logical errors and improves reasoning accuracy, while achieving a better balance between accuracy and reasoning time than the Chain-of-Thought, Decompose–Analyze–Rethink and Tree-of-Thought. Our code and dataset are available at https://github.com/Tim798-art/SyRA/tree/main/SyRA.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Jiahao Tang Central South University, Henry Hengyuan Zhao, Lijian Wu, Zijian Zhang, Yifei Tao, Dongxing Mao Central South University, Yang Wan, Jingru Tan Central South University 等 11 位作者
We introduce Chart2Code, a new benchmark for evaluating the natural language to chart code generation capabilities of large multimodal models (LMMs). Chart2Code is explicitly designed from a user-driven perspective, capturing diverse real-world scenarios and progressively increasing task difficulty. It consists of three levels: Level 1 (Chart Reproduction) reproduces charts from a reference figure and user query; Level 2 (Chart Editing) involves complex modifications such as changing chart types or adding elements; and Level 3 (Long-Table to Chart Generation) requires models to transform long, unprocessed tables into faithful charts following user instructions. To our knowledge, this is the first hierarchical benchmark that reflects practical chart2code usage while systematically scaling task complexity. In total, Chart2Code contains 2,186 tasks across 22 chart types, paired with multi-level evaluation metrics that assess both code correctness and the visual fidelity of rendered charts. We benchmark 29 state-of-the-art (SoTA) LMMs, including both proprietary and the latest open-source models such as GPT-5.2, Qwen3-VL, InternVL3/3.5, MiMo-VL, and Seed-1.6-VL. Experimental results demonstrate that even the SoTA model GPT-5.2 averages 72.21 on code-based evaluation and only 33.41 on chart-quality assessment across the editing tasks, underscoring the difficulty of Chart2Code. We anticipate this benchmark will drive advances in multimodal reasoning and foster the development of more robust and general-purpose LMMs.
尚无 AI 解读，展示原文摘要
cs.CL · cs.CV
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Junjie Wang Ant Group, Zequn Xie, Dan Yang, Jie Feng, Yue Shen antgroup, Duolin Sun, Meixiu Long, Yihan Jiao 等 12 位作者
Deep Research systems based on web agents have shown strong potential in solving complex information-seeking tasks, yet their search efficiency remains underexplored. We observe that many state-of-the-art open-source web agents rely on long tool-call trajectories with cyclic reasoning loops and exploration of unproductive branches. To address this, we propose WebClipper, a framework that compresses web agent trajectories via graph-based pruning. Concretely, we model the agent’s search process as a state graph and cast trajectory optimization as a minimum-necessary Directed Acyclic Graph (DAG) mining problem, yielding pruned trajectories that preserve essential reasoning while eliminating redundant steps. Continued training on these refined trajectories enables the agent to evolve toward more efficient search patterns and reduces tool-call rounds by about 20% while improving accuracy. Furthermore, we introduce a new metric called F-AE Score to measure the model’s overall performance in balancing accuracy and efficiency. Experiments demonstrate that WebClipper compresses tool-call rounds under excellent performance, providing practical insight into balancing effectiveness and efficiency in web agent design.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
MEMENTO: Teaching LLMs to Manage Their Own Context
Vasilis Kontonis, Yuchen Zeng, Shivam Garg, Lingjiao Chen, Hao Tang, Ziyan Wang, Ahmed Awadallah, Eric Horvitz 等 10 位作者
AI 速览：通过将推理过程分块并压缩为稠密摘要（memento），让模型仅依赖摘要向前推理，从而降低上下文、KV 缓存与计算开销。
Reasoning models think in long, unstructured streams with no mechanism for compressing or organizing their own intermediate state. We introduce MEMENTO: a method that teaches models to segment reasoning into blocks, compress each block into a memento, i.e., a dense state summary, and reason forward by attending only to mementos, reducing context, KV cache, and compute. To train MEMENTO models, we release OpenMementos, a public dataset of 228K reasoning traces derived from OpenThoughts-v3, segmented and annotated with intermediate summaries. We show that a two-stage SFT recipe on OpenMementos is effective across different model families (Qwen3, Phi-4, Olmo 3) and scales (8B--32B parameters). Trained models maintain strong accuracy on math, science, and coding benchmarks while achieving ${\sim}2.5\times$ peak KV cache reduction. We extend vLLM to support our inference method, achieving ${\sim}1.75\times$ throughput improvement while also enabling us to perform RL and further improve accuracy. Finally, we identify a dual information stream: information from each reasoning block is carried both by the memento text and by the corresponding KV states, which retain implicit information from the original block. Removing this channel drops accuracy by 15\,pp on AIME24.
Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent 等 1137 位作者
In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio. The family includes two new models: (1) an updated Gemini 1.5 Pro, which exceeds the February version on the great majority of capabilities and benchmarks; (2) Gemini 1.5 Flash, a more lightweight variant designed for efficiency with minimal regression in quality. Gemini 1.5 models achieve near-perfect recall on long-context retrieval tasks across modalities, improve the state-of-the-art in long-document QA, long-video QA and long-context ASR, and match or surpass Gemini 1.0 Ultra's state-of-the-art performance across a broad set of benchmarks. Studying the limits of Gemini 1.5's long-context ability, we find continued improvement in next-token prediction and near-perfect retrieval (>99%) up to at least 10M tokens, a generational leap over existing models such as Claude 3.0 (200k) and GPT-4 Turbo (128k). Finally, we highlight real-world use cases, such as Gemini 1.5 collaborating with professionals on completing their tasks achieving 26 to 75% time savings across 10 different job categories, as well as surprising new capabilities of large language models at the frontier; when given a grammar manual for Kalamang, a language with fewer than 200 speakers worldwide, the model learns to translate English to Kalamang at a similar level to a person who learned from the same content.