cs.AI · 2026-11-11 · No. 170

Artificial Intelligence, 2026-11-11.

42 new papers in cs.AI. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

42 entries
  1. 01

    Contrastive Discovery: Open-Ended Scientific Discovery over Competing Explanations

    Ziang Liu, James J. Kim, Yijia Dai, Jennifer J. Sun

    cs.AI · cs.CL · cs.LG

    LLM agents are increasingly used for open-ended, data-driven scientific discovery, yet most of them evaluate hypotheses pointwise, testing an empirical claim $h$ only against its complement $\neg h$. When evidence rejects $h$, the agent learns that one explanation is unlikely but not which alternative the evidence supports. To recover that alternative, we introduce Contrastive Discovery, which replaces the single hypothesis with a contrast...

    arxiv.org/abs/2611.14514 · PDF

  2. 02

    Comparative Analysis of Agent Evaluation Frameworks: Stability, Detection, and Discovery in Enterprise Analytics Agents

    Howard Zhang, Chuck Arvin, Logan Brown, Mihir Bhatia, Neelu Choudhary, Lily Miao

    cs.AI · cs.CL · cs.LG · cs.SE

    Deploying LLM-based analytics agents in enterprise settings requires evaluation frameworks that can reliably detect failures across complex, multi-tool workflows. We present a three-phase comparative study of three evaluation frameworks, each representing a distinct evaluation paradigm (trace-based LLM judging, text-only LLM judging with red-teaming, and deterministic heuristics), applied to two analytics agents in a controlled research...

    arxiv.org/abs/2611.14493 · PDF

  3. 03

    ReTrace: Distilling Tool-Using Agents into Planner-Free Workflows

    Kaiyuan Hou, Yang Ping Kuo, Indranil Bhattacharya, Rohith Nama, Arushi Gupta, Carlos D. Castillo, Prathap...

    cs.AI · cs.LG · cs.MA

    Business process automation runs the same Standard Operating Procedure (SOP) again and again on new inputs. Large Language Model (LLM) agents can follow an SOP written in natural language, but they call an LLM to choose every step of every run, which adds latency and cost at scale. We present ReTrace, which turns an SOP and a few logged agent runs into a reusable workflow in which code, not an LLM, selects the next step. The agent's...

    arxiv.org/abs/2611.14492 · PDF

  4. 04

    Re-Search: Dissecting LLM Ideation Through a Two-Player Questioning Game

    Muhan Gao, Hangxiao Zhu, Xinqi Su, Yu Zhang, Daniel Khashabi, Kuan-Hao Huang

    cs.AI

    Research ideation is iterative: researchers refine their ideas step by step based on feedback. Yet existing evaluations obscure this search process, making it difficult to understand how LLMs explore the space of research ideas and what limits their progress. We introduce Re-Search, which adapts the format of Twenty Questions to research ideation: given only the research problem of a published paper, a model must rediscover the paper's core...

    arxiv.org/abs/2611.14487 · PDF

  5. 05

    Evaluating LLM-Generated World Models for Neuro-Symbolic Reasoning

    Souhaila Djaffal, Amna Jamal, Gagana Madhugiri Devaraja, Anidipta Pal, Jobst Heitzig

    cs.AI

    Formal world models can support planning, verification, and safety reasoning, but constructing them from open-ended natural-language situations is difficult, particularly in multi-agent settings where several formalizations may be plausible. We study whether five LLMs can generate such world models as partially observable stochastic games and whether mechanical validity is sufficient to establish that the resulting model faithfully represents...

    arxiv.org/abs/2611.14419 · PDF

  6. 06

    Precision on Demand: Escalating Weight Bits at Uncertain Decoding Steps in a Small Local Model

    Mohammed Nayeem Khan, Logesh L, Aliyas Ahmad Misri

    cs.AI

    Local decoding usually fixes one weight precision for the whole generation. We study a different allocation: store 8-bit weights, decode with their top 4 bits, and redo a step at 8 bits only when the low-precision output distribution looks uncertain (entropy above a threshold or a small top-two margin). Quantization is simulated, the model is Qwen3-0.6B, and the benchmark is GSM8K. Cost is counted in weight bytes read per token. On 36724...

    arxiv.org/abs/2611.14418 · PDF

  7. 07

    Bits or permutations? Spending a fixed inference budget on weight precision or on option-order averaging in small local language models

    Mohammed Nayeem Khan, Logesh L, Aliyas Ahmad Misri

    cs.AI · cs.CL

    Local language models can save memory by storing weights in fewer bits, and they can reduce sensitivity to the order of answer options by averaging a few reorderings. We ask whether the first makes the second worse, and which is the cheaper way to spend a fixed budget. On Qwen3-0.6B and Qwen3-1.7B with simulated round-to-nearest weight quantization (8, 6, 4 and 3 bits, fp16 reference), read from the logits of the letters A to D on ARC-Easy,...

    arxiv.org/abs/2611.14413 · PDF

  8. 08

    An Energy-Based Perspective on Machine Learning

    Bo Dai, Yilun Du

    cs.AI · cs.LG

    Energy-based models (EBMs) define a distribution through a scalar energy, $p_θ(x)\propto\exp(-E_θ(x))$, and are usually presented as one model family among many. This tutorial has a broader goal: beyond introducing EBMs, it uses them as a single lens that connects the different aspects of machine learning. Any EBM is specified by three choices, the energy, which determines what the model represents; the inference procedure, which samples from...

    arxiv.org/abs/2611.14383 · PDF

  9. 09

    Cognitive Mapping of Learning by Thinking Mechanisms in Large Language Models

    Dong Han, Jin Zhang, Kunyue Yang

    cs.AI

    Large language models (LLMs) increasingly exhibit capabilities that resemble human Learning by Thinking (LbT), the acquisition of new insight through internal processes such as explanation and reasoning, without new external input. A systematic account of the cognitive mechanisms behind these capabilities, and of their limits, remains underdeveloped. This paper proposes a Cognitive LbT Framework that maps four mechanisms (Reflective...

    arxiv.org/abs/2611.14382 · PDF

  10. 10

    CLADE: Category-Level Answering from Deficient Evidence in Retrieval-Augmented Language Models

    S M Rayeed, Charles V. Stewart, Yao Ma

    cs.AI

    Retrieval-augmented systems often retrieve passages that are accurate and relevant but state the answer at a coarser level of granularity than the question requires. For example, a question may ask which specific disease a drug treats (familial hyperlipidemia), while the retrieved passage mentions the broader disease family (hyperlipidemia). Prior work on context sufficiency treats such coarse passages simply as insufficient. We argue that...

    arxiv.org/abs/2611.14355 · PDF

  11. 11

    When Should Agents Remember? Falsification-Gated Self-Evolution for LLM Agents

    Runxuan Tang, Haoyu Gao, Yuyan Ding, Junyi Yao, Zihao Zheng, Zecheng Sheng, Liwei Hou

    cs.AI · cs.LG

    LLM agents increasingly operate in long-horizon, verifier-rich environments, but current self-improvement mechanisms often write episode-derived lessons directly into memory, making local success an unreliable signal for reusable and safe knowledge. This paper addresses the core question of when an experience-derived behavioral update should be admitted into persistent agent state. We propose Falsification-Gated Self-Evolution (FGSE), a...

    arxiv.org/abs/2611.14326 · PDF

  12. 12

    Don't Just Trust Your Memory: Evidence-Linked Memory Reduces Memory-Induced Degradation in LLM Agents

    Yukyeong Lee, Yumin Choi, Jinheon Baek, Sung Ju Hwang

    cs.AI · cs.MA

    External memory enables LLM agents to improve from experience by distilling trajectories of past tasks into concise lessons for new tasks. However, memory can also lead to memory-induced degradation, where an agent fails on tasks it would solve without memory, often because it follows a lesson that is incorrect, or misapplies or misreads a valid one. This is because lessons are inferred from trajectories labeled only with task success or...

    arxiv.org/abs/2611.14320 · PDF

  13. 13

    Multimodal Abstention That Preserves Acquired Correct Answers

    Jinyuan Zhang

    cs.AI · cs.CV · cs.LG

    Adding abstention to a task-adapted multimodal model can discard correct answers, including capabilities acquired during adaptation. We formulate abstention repair as maximizing correct abstention on unanswerable questions under a budget on newly lost correct answers. We propose ReFrain (Regression-Free Abstention), which combines a linear probe on first-token logits, threshold calibration on held-out image clusters, and a deterministic veto...

    arxiv.org/abs/2611.14311 · PDF

  14. 14

    LM-SimBench: A Unified Framework, Dataset, and Benchmark for Large Language Model Training Simulation

    Yu Dong, Hong Li, Qiang Sun, Xu Zhou, Jinbiao Huo, Qixiu Cheng, Zhiyuan Liu

    cs.AI

    Evaluating candidate parallelization strategies through distributed training runs makes strategy selection prohibitively expensive at scale. Performance simulation offers a lower cost alternative, yet controlled comparisons among existing simulators remain difficult because they differ in the training stages they model and the workloads on which they are evaluated. We introduce LM-SimBench, a unified framework, profiling dataset, and...

    arxiv.org/abs/2611.14285 · PDF

  15. 15

    Recurrent Modular Structure in Spiking Neural Network Reinforcement Learning

    Vikram Ramavarapu, Himanshu Udupi, Ashish Gautam

    cs.AI · cs.LG · cs.NE

    Biological neural circuits are both modular and recurrent, with dense communities sparsely linked to one another. Spiking neural networks (SNNs) for reinforcement learning are usually feed-forward, and it is unclear how to obtain functional modules in a recurrent SNN or what they buy. In this work, we introduce a class of spiking networks, called Community Recurrent SNNs (CoRe SNNs): recurrent networks partitioned into communities with fixed...

    arxiv.org/abs/2611.14262 · PDF

  16. 16

    A Cross-Scenario Survey and Analysis of Self-Evolving Multimodal Agents

    Jingjing Jiang

    cs.AI

    Recent work shows that multimodal agents increasingly self-improve without recurring human annotation. However, each self-improvement mechanism is designed and evaluated within a single scenario, leaving its preconditions unverified under cross-scenario transfer. This survey investigates the structural source of asymmetric mechanism transfer across four scenarios: multimodal reasoning, multimodal generation, GUI and Web navigation, and...

    arxiv.org/abs/2611.14256 · PDF

  17. 17

    Personalized Affective Perception via Continual Learning in Human-Agent Negotiation

    Mehmet Onur Keskin, Berk Buzcu, Nikhil Churamani, Reyhan Aydogan, Hatice Gunes, Catholijn Jonker

    cs.AI · cs.HC · cs.LG · cs.MA · cs.RO

    Self-interested intelligent agents that negotiate with humans should interpret nonverbal expressions and adapt their behavior accordingly. However, generic facial-affect models degrade across individuals and contexts, creating a generalization gap. We introduce an affect-adaptive negotiation strategy that incorporates Continual Learning with Imagination for Facial Expression Recognition (CLIFER) to personalize valence-arousal perception in...

    arxiv.org/abs/2611.14247 · PDF

  18. 18

    Breakdown of Autoregressive Multi-Step Reasoning Under Concentrated vs. Diffuse Attention Head Dropout

    Karol Struniawski

    cs.AI · cs.CL

    During extended wakefulness, mammalian neocortical networks experience localized periods of transient neuronal silence termed off-states. Here, we examine how analogous spatiotemporally concentrated disruptions affect sequential reasoning in autoregressive Large Language Models (LLMs). Evaluating 250 paired derivations on the GSM8K benchmark across two 8B models (Qwen3-8B and LLaMA-3.1-8B-Instruct), we contrast clustered bursts of attention...

    arxiv.org/abs/2611.14209 · PDF

  19. 19

    Joint Quantization and Dynamic Partitioning for Context-Aware Edge Vision Transformers

    Zhu Jiaqi, Jain Prakriti, Katare Dewant, Kumar Saurabh

    cs.AI

    Deploying vision transformer models across connected and automated vehicles (CAVs) requires joint management of computation and Vehicle-to-Vehicle (V2V) communication. Static split-inference methods use fixed partition points and cannot adapt to time-varying link bandwidth, processing load, and concurrent multi-stream traffic. This paper proposes an edge orchestration framework that jointly selects model partition points, per-layer...

    arxiv.org/abs/2611.14196 · PDF

  20. 20

    An Augmented Lagrangian Approach to Lifted Bellman Linear Programming

    Jongchan Park, Hyukjun Yang, Narim Jeong, Donghwan Lee

    cs.AI

    Temporal-difference critics regress onto a bootstrapped target and usually need a target network. Lifted Bellman Linear Programming (LBLP) instead expresses the in-sample optimal values of offline RL as the solution to a linear program over the dataset. Its neural solver ALBUM relaxes the constraints into hinge penalties with fixed coefficients, and its guarantees are conditions on coefficients chosen in advance. We solve the same program...

    arxiv.org/abs/2611.14183 · PDF

  21. 21

    Cross-Border Fulfillment Center Selection via Doubly Robust Estimation and Linear Programming

    Kriti Mahajan, Patrick Bloebaum

    cs.AI

    We introduce the cross-border (XB) fulfillment center (FC) Selection Model: a multi-stage optimization framework combining forecasting, doubly robust estimation, and linear programming to select optimal source FCs. For each source-destination shipping arc, the objective is to choose a subset of source-country FCs that minimize delivery time and cost while maximizing profit and shipped units under a fixed domestic network. We evaluate the...

    arxiv.org/abs/2611.14174 · PDF

  22. 22

    BARS: Budget-Aware Sequential Sampling with Refusal for Majority Identification under Unknown Distributions

    Shenxi Liu, Yiwei Li, Mingyang Zhao, Yuhang Tian, Kan Li

    cs.AI

    Repeated sampling with majority selection is an effective means of enforcing self-consistency in large language models. Recently, a variant has also been introduced that terminates early to save costs when the output distribution is favorable. But it still cannot yield a correct confidence estimate from the answer distribution. For this issue, we formalize this as majority identification under an unknown distribution with a budget and a...

    arxiv.org/abs/2611.14171 · PDF

  23. 23

    Hx2Dx: From Anamnesis to Diagnosis - A Multimodal Arena for Conversational Clinical Reasoning in LLMs

    Federico Ravenda, Mirko Cesarini, Daniele Montagnani, Volodymyr Karpenko, Antonietta Mira, Andrea Raballo

    cs.AI

    Large language models (LLMs) achieve expert-level diagnostic accuracy in static evaluations, where the model receives a curated vignette or case report that already condenses the diagnostically relevant findings. Such evaluations measure inference over already selected evidence; the evaluations do not account for the inquiry used to obtain it. In clinical practice, however, diagnosis is an iterative process of inquiry. Clinicians take the...

    arxiv.org/abs/2611.14122 · PDF

  24. 24

    Personalized Memory Rubrics: Learning What to Remember per User via Rubric-Guided Credit Assignment

    Yupeng Han, Kai Zhang, Shuochen Liu, Ze Liu, Xianquan Wang, Zhihong Pan, Xiangyu Zhao, Qi Liu, Enhong Chen

    cs.AI

    Long-horizon personalized agents maintain an evolving memory by continuously deciding what to add, modify, or discard. However, learning an optimal update policy remains challenging. Conventional training relies solely on terminal question-answering accuracy, yielding a coarse feedback signal that treats all intermediate updates identically. Furthermore, update utility is inherently user-specific, as identical memory actions may yield...

    arxiv.org/abs/2611.14017 · PDF

  25. 25

    Understanding Mixture-of-Experts Language Models Beyond Expert Boundaries

    Zhenhong Zhou, Mao Zheng, Mingyang Song, Qiankun Li, Kun Wang, Junfeng Fang

    cs.AI · cs.CL

    In Mixture-of-Experts (MoE) models, the nature of expert specialization remains controversial. Reports of domain-associated expert preferences contrast with analyses attributing routing primarily to token identity or syntactic patterns. To clarify these differing accounts, we look beyond expert-level routing to investigate the neuron-level organization of domain-specialized computation using Routing-Aware Magnitude Profiling (RAMP), a measure...

    arxiv.org/abs/2611.13975 · PDF

  26. 26

    TreeAgent: Structure-Aware Memory Agent for Processing Long Hierarchical Data

    Wei Gu, Weiwei Qi, Jiajun Tang, Tianhang Zheng, Bo Chen, Zhibo Zhang, Jinfei Liu, Kui Ren

    cs.AI

    Practical Web applications increasingly require agents to interpret long conversations or documents. For inputs exceeding the context windows of large language models (LLMs), memory agents process segments sequentially and retain past information in bounded memory. However, they typically divide inputs into flat token segments without preserving structure or hierarchy, causing three limitations for structured data such as API responses or...

    arxiv.org/abs/2611.13946 · PDF

  27. 27

    Beyond Proxy Metrics: MLLMs as Human Surrogates for Explainable AI Evaluation

    Eoin M. Kenny, Salim I. Amoukou, Tom Bewley

    cs.AI

    Explainable AI (XAI) has expanded into a broad and impactful research area, but the fundamental question of how best to evaluate explanation techniques has proven frustratingly elusive. Methodologies typically revolve around either proxy metrics which tell us little about the utility of an explanation, or human evaluation which---while generally considered the gold standard---is expensive, difficult to scale, and challenging to reproduce. In...

    arxiv.org/abs/2611.13926 · PDF

  28. 28

    From Counterfactual Edits to Human Narratives: LLM-Driven Interpretations for Recommender System Explanations

    Vojtech Cahlik, Amir Reza Mohammadi, Rodrigo Alves, Pavel Kordik, Eva Zangerle

    cs.AI · cs.IR

    Recommender systems increasingly influence what users discover and consume online, yet the decision logic behind their outputs often remains opaque. Counterfactual explanation (CFX) methods provide an effective way to show which changes to a user's interaction history would alter a recommendation. In recommendation settings, however, CFXs often require many edits, producing long, low-level lists that are hard for users to interpret. Moreover,...

    arxiv.org/abs/2611.13914 · PDF

  29. 29

    Taxonomy-Agnostic Neurosymbolic Grounding of Robot Kinematics

    Bastien Dussard, Aur{é}lie Clodic, Guillaume Sarthou

    cs.AI · cs.RO

    While symbolic reasoning for task allocation requires grounding a robot's physical capabilities, standard Unified Robot Description Format (URDF) files provide only low-level kinematics without the formal semantic context needed for reasoning. We present URDF2Ontology, an automated, taxonomy-agnostic neurosymbolic framework that transforms raw URDF files into populated, grounded OWL ontologies. It leverages a Large Language Model (LLM) for...

    arxiv.org/abs/2611.13850 · PDF

  30. 30

    Ceci n'est pas une pipe -- Toward a Symbolic Solver for the Abstraction and Reasoning Corpus Using Evolutionary Computation

    Luca Favole, Giorgio Mongardi, Giovanni Squillero, Alberto Tonda

    cs.AI

    The Abstraction and Reasoning Corpus (ARC) is a benchmark designed to assess the capability of Artificial Intelligence (AI) systems to generalize starting from a few samples, a task humans excel at. The ARC-AGI contests held since 2020 have been the focus of intense competition, with participants proposing approaches ranging from traditional symbolic AI to Transformer architectures. Despite a long history of successes, evolutionary algorithms...

    arxiv.org/abs/2611.13831 · PDF

  31. 31

    Integrating Action Prefix Prediction and Alignment Across Modalities for Multimodal Reinforcement Learning

    Sijie Xu, Francisco Cruz

    cs.AI

    Learning representations from multimodal observations is difficult in reinforcement learning with limited interaction data. Multimodal Joint Predictive Representation combines multimodal latent prediction with contrastive learning across modalities, but its recursive rollout depends on earlier predictions and its pairwise alignment focuses on correspondence between modalities. We propose Improved Predictive Representation, which combines...

    arxiv.org/abs/2611.13782 · PDF

  32. 32

    Toward Autonomous RTL and Synthesis Optimization: Benchmarking and Self-Improving Agents

    Wenji Fang, Yao Lu, Jinghua Wang, Zhiyao Xie

    cs.AI · cs.AR

    Recent advances in large language models (LLMs) and autonomous agents are creating new opportunities for hardware design optimization. This paper examines three connected directions toward autonomous RTL and synthesis optimization: (1) Realistic benchmarking. We discuss reference-based and open-ended RTL optimization benchmarks that evaluate optimization opportunities under realistic EDA workflows. (2) Tool-grounded RTL optimization. We...

    arxiv.org/abs/2611.13713 · PDF

  33. 33

    Broad-Persistent Advising in Interactive Reinforcement Learning via Latent State Encoding

    Zhuoran Liang, Francisco Cruz

    cs.AI

    Deep Interactive Reinforcement Learning (Deep IntRL) accelerates reinforcement learning training by incorporating external advice. However, conventional Deep IntRL uses each piece of advice only in the current step and discards it after a single interaction. Persistent Advising and Broad-Persistent Advising (BPA) extend this process by storing advice in persistent memory and reusing it in similar states through state generalisation based on...

    arxiv.org/abs/2611.13712 · PDF

  34. 34

    AutoManifold: Agentic Design of Data Visualisation Algorithms via Manifold Embedding

    Burak Susam, Ruiyuan Kang, Tingting Mu

    cs.AI

    Manifold embedding for data visualisation is dominated by a small set of hand-designed state-of-the-art (SOTA) algorithms. Their design targets are fixed at development time, resulting in inflexible algorithmic behaviour that cannot be readily steered towards user-specified structural priorities. Hand-designing new embedding algorithms to address user priority requires highly specialised expertise and is time consuming. To address autonomous...

    arxiv.org/abs/2611.13710 · PDF

  35. 35

    Agentic AI Meets Formal Verification in the Era of Agentic Hardware Development

    Wenji Fang, Yuchao Wu, Jing Wang, Zhiyao Xie

    cs.AI · cs.AR

    As AI agents become increasingly capable of generating and optimizing hardware circuits, ensuring the correctness of AI-generated designs becomes more important. Meanwhile, advances in AI lower the barriers to developing and applying formal methods, creating new opportunities to automate and improve hardware verification. This invited paper presents an overview of the methodologies and applications of hardware formal methods in the AI era....

    arxiv.org/abs/2611.13705 · PDF

  36. 36

    SeqFold: Timestamp-Addressable Compressed States for User Action Sequence Backbones

    Mianwei Zhou, Duo Zhang, Henry Tsai, Yuqi Zheng, Jian Li, Juexin Lin, Sujay Khandagale, Vijay Rajaram, Dong Jiao, Tao Cheng

    cs.AI · cs.SI

    Existing sequential user modeling methods mainly focus on improving the backbone encoder or learning task-specific user representations for a single prediction objective. We instead study how to export the multi-layer user states of a frozen long-history backbone as compact, timestamp-addressable representations for downstream training backfill and serving. In this setting, the user state at a given timestamp summarizes the user's actions...

    arxiv.org/abs/2611.13704 · PDF

  37. 37

    Topological Dynamics Under Non-Stationary Supervision: Persistent Homology of Neural Network Weight Evolution

    Mitra Varun

    cs.AI

    We investigate how the persistent topology of neuron- weight point clouds evolves under stable and non-stationary supervision. An identical multilayer perceptron is trained on Fashion-MNIST with correct labels, a fixed random permutation of the training-label vector, or a fresh permutation every epoch. Five paired seeds share initialisation and minibatch order, yielding 15 models trained for 100 epochs. Raw and row-normalised incoming weight...

    arxiv.org/abs/2611.13701 · PDF

  38. 38

    A computational framework for understanding embodied plans

    Aalap D. Shah, Basil Saeed, Joshua B. Tenenbaum, Tobias Gerstenberg, Hyowon Gweon, Ilker Yildirim

    cs.AI · cs.HC · cs.RO

    Reasoning about people's plans and goals based on their actions is fundamental to human social interaction and essential for cooperative, embodied artificial intelligence. Formalizing this capacity in naturalistic, embodied settings has been a longstanding challenge. Here, we present GenEA, a novel agent representation capable of reasoning over multi-step, long-horizon embodied plans. At the heart of GenEA lies a multilevel state-space that...

    arxiv.org/abs/2611.13669 · PDF

  39. 39

    Benchmarking LLM Next-Step Recommendations with Knowledge Space Theory

    Peter Steiner, Jan Hochweber

    cs.AI

    Selecting an LLM for next-step recommendation requires benchmarks that reflect the intended educational task and domain. We present a benchmarking method that uses Knowledge Space Theory (KST) as a formal evaluation reference. Given a task catalogue and an existing prerequisite relation, the method derives admissible knowledge states and the complete set of immediate next steps for each state. Recommendations generated by a model under a...

    arxiv.org/abs/2611.13667 · PDF

  40. 40

    DrugCoding: A Scientific Programming Agent for Drug Discovery

    Junwei Hu, Zhuohao Lin, Kun Li, Hengnan Zhang

    cs.AI · cs.MA

    Drug discovery involves multiple interconnected research stages, including molecular design, property prediction, and virtual screening. These processes are characterized by complex workflows, interdependent computational tasks, and diverse specialized tools, placing substantial demands on the coordination of scientific models and computational resources. However, existing large language model (LLM)-based scientific agents still face...

    arxiv.org/abs/2611.13651 · PDF

  41. 41

    Megrez: A Knowledge-Guided Agent for Formal Mathematics over MK Set Theory

    Tiancheng Xu, Wensheng Yu

    cs.AI

    General-purpose coding agents equipped with proof-assistant tools have shown strong performance on standalone competition problems, yet cumulative textbook formalization inside a low-resource mathematical library still faces three obstacles: aligning textbook concepts with library declarations, keeping long-horizon search synchronized with live proof states, and integrating locally verified proofs reliably into a growing codebase. We present...

    arxiv.org/abs/2611.13613 · PDF

  42. 42

    Earth Embeddings in Environmental Remote Sensing

    Yuchi Ma, Jiaqi Yang, Mengyu Liang, Ivan Higuera-Mendieta, Caleb Robinson, Anthony Ortiz, Min Chen, David B. Lobell,...

    cs.AI

    Earth observations from satellite platforms have profoundly transformed research and applications across numerous domains. However, uneven observation coverage and frequent data gaps continue to limit their ability to capture Earth's surface dynamics. Moreover, processing multi-modal Earth observations requires substantial computational resources and sophisticated data harmonization frameworks, which may not be readily accessible to many...

    arxiv.org/abs/2611.13612 · PDF

This edition is part of The Daily Abstract — cs.AI archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.