cs.AI · 2026-11-02 · No. 161
Artificial Intelligence, 2026-11-02.
53 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
53 entries-
01
Latent Sparse Attention: Towards Subquadratic Ultra-Long Context Attention
Ales Kubicek, Andrea Caciolai, Liangzu Peng, Sukrit Sumant, Benjamin Hoover, Fraser Greenlee, Ruairidh M. Battleday,...
cs.AI
Agentic workflows are increasingly shifting towards long-horizon tasks, such as open-ended scientific work, where models benefit from long context windows. However, at ultra-long context (above 1M tokens), full attention is prohibitively expensive. A promising approach is sparse attention, in which a dedicated indexer selects a subset of keys for the attention. Yet current methods of indexing either still have quadratic cost in context size...
-
02
ACCT: Asymmetric Cross-LLM Context Transfer
Yuzhe Liu, Haolin Tian, Tonghan Wang
cs.AI
In real-world deployments, large language model (LLM) systems are increasingly evolving from single-model invocation toward heterogeneous deployments in which different models are dynamically invoked for inference. When the same context is reused across models, however, each newly selected target model typically has to process it again, repeatedly incurring substantial computational costs. Therefore, we propose ACCT (Asymmetric Cross-LLM...
-
03
CausalWAM: Learning the Causes of Actions in World Action Models
Juntao Cheng, Jinzhou Tang, Fan Feng, Henrik I. Christensen, Yujia Zheng
cs.AI · cs.RO · stat.ML
World action models (WAMs) learn latent variables from observations and use these to both predict the evolution of the scene and to generate actions. The prediction has to be of the whole scene, whereas only a portion of the scene causes actions. WAMs fitted to demonstrations do not, in general, guarantee that they will generate actions solely from the latent causes of the demonstrated actions (the action-relevant latent variables), as the...
-
04
The Knowledge Layer Model (KLM): Evidence-Visible AI Output, Routing Diagnostics, and Negative Results
Omer Asim Ozturk, Cihan Aydiner
cs.AI · cs.CL
AI answers require more than apparent correctness: reviewers need to inspect their recorded basis. We introduce the Knowledge Layer Model (KLM), an open, implementation-neutral specification for inference records with versioned epistemic assessments, evidence relations, and explicit unknowns. SEDIM, the knowledge and evidence architecture of Nage AI OS, is a reference implementation. We reference KLM v0.3 (repository tag v0.3.0). Empirical...
-
05
Same Question, Different Answers: Auditing Persona-Dependent Variation in Six LLMs on Smoking-Cessation Advice
Artin Yousefi, Aizierjiang Aiersilan, Lorien C Abroms, David A Broniatowski
cs.AI
Hundreds of millions of people now ask large language model (LLM) chatbots for health advice, which raises a question that is simple to pose and hard to answer: does everyone get the same advice? We audit six widely deployed LLMs from four providers on smoking cessation, a domain with codified clini- cal guidance and substantial public-health stakes, by putting the same four cessation questions to twelve user personas that differ in life...
-
06
TradeWar: A Benchmark for Execution-Grounded Trade Negotiation with Adaptive LLM Agents
Xiangyu Kong, Ruirui Yang, Xia Hou
cs.AI
Multi-turn negotiation remains a challenging problem for large language model (LLM) agents. While LLMs can conduct natural-language dialogue, existing benchmarks predominantly assess only agreement rates, overlooking whether negotiated commitments actually create value once executed. To address this gap, we introduce TradeWar, a multi-country simulation benchmark that translates negotiation dialogues into concrete tariff and trade-share...
-
07
DAMI: Dual-Axis Memory Initialization for Enhanced Long-Context Retrieval in Gated Linear Attention
Zhangchi Feng, Harry Jiang, Yangyifei Luo, Ray Zhang, Richong Zhang
cs.AI · cs.CL
Linear attention scales linearly with sequence length, but its finite-state memory can limit long-context retrieval. In gated linear recurrences, memory retention depends on state decay, which is shaped jointly by gate parameters A_log and dt_bias and by input activations. In controlled Gated DeltaNet (GDN) experiments, both parameters remain highly correlated with their initial values after training, highlighting the importance of...
-
08
ID2Pattern: Pretraining Generalizable Identity Behavior Patterns for Transaction Risk Foundation Models
Ze Zhao, Haoyu Jiang, Weiyu Han, Ruobing Zuo, Xiao Tan, Shuai Chen, Tianyi Zhang
cs.AI
Large-scale behavioral pretraining offers a promising route to generalizable representations in online payment systems. However, high-cardinality identity fields such as card, device, and account IDs, though rich in behavioral signals, remain underexploited. Their continually growing vocabularies and limited semantic meaning make existing vocabulary-based and semantics-based encodings ill-suited. Their generalizable signal lies not in...
-
09
When Does Test-Time Search Help World Action Models? An Empirical Audit of Candidate Selection and Simulator Integrity
Jun Liu, Dajie Sun, Zhenglun Kong, Zhenjiang Fan, Peiyan Dong, Fan Yang, Wenbin Zhangg, Geng Yuan, Xue Lin, Yanzhi...
cs.AI
World-action models increasingly apply test-time scaling, spending extra inference computation on candidate selection and adaptive allocation to improve control. Such gains are credible only when candidates carry exploitable signal, nominal compute savings become real speedup, and evaluation stays reliable. We audit all three on Cosmos Policy and RoboCasa with a premise-first, pre-registered methodology. On clean data, a learned value...
-
10
Prune Gradually, Adapt Sparsely: Efficient Pruning of Large Language Models at Extreme Sparsity
Jean Lucien Randrianantenaina, Hung Nguyen, Nasib Ullah, Jinbin Zhang, Nilesh Gupta, Inderjit S. Dhillon, Rohit Babbar
cs.AI
Weight pruning can reduce the storage and inference cost of large language models (LLMs), but preserving quality at high sparsity levels remains challenging. Existing methods face a quality-cost trade-off in this regime. One-shot pruning is cheap but degrades sharply as sparsity increases, even when followed by post-pruning recovery. A growing line of work instead optimizes the mask directly from the dense model under the end-to-end...
-
11
Optimizing Stochastic Policy Geometry for Few-Step Flow Reinforcement Learning
Zhuguanyu Wu, Congjia Chen, Ruihao Gong, Yang Yong, Shiqiao Gu, Yi Xu, Xianglong Liu
cs.AI · cs.LG
Few-step flow models generate samples through a handful of large denoising transitions. Applying GRPO to such models requires introducing stochasticity into the denoising transitions, and when a single transition spans a wide range of noise levels, the choice of the resulting stochastic policy becomes a major factor in optimization. Recent constructions constrain the policy to preserve the target flow coefficients, but this constraint admits...
-
12
Sensorium: An Open-Source Multimodal Data Collection and Curation Library for Embodied Surgical AI
Lorenzo Mazza, Ariel Rodriguez, Stefanie Speidel
cs.AI · cs.RO
Embodied surgical AI requires reliable multimodal data, yet surgical data collection remains costly, difficult to repeat, and strongly dependent on the hardware setup. We present Sensorium, an open-source Python library for recording, processing, annotating, and curating multimodal surgical data from configurable robot and sensor streams using the Robot Operating System (ROS) and ROS2 middleware. The library combines operator-facing data...
-
13
Structure-Aware Skill Retrieval and Arbitration for Optimization Modeling
Anran Liu, Benzhao Hou, Zongsheng Cao, Daichao Wang, Lang Chen, Shitong Chen
cs.AI
Large Language Models (LLMs) can turn natural-language optimization tasks into solver-checked answers, but current agents remain brittle under narrative rewrites and often store reusable experience at the instance level. We introduce \textsc{ArchOR}, an archetype-centric skill agent that builds on \textsc{OptSkills} by adding two retrieval-focused modules. \emph{Centroid-Aware Representation Learning} (CARL) refines the ordering of cached...
-
14
ReX-GG: a LLM Ensemble Pipeline for Relation-extraction and Graph Generation
Giacomo Magnifico, Eduard Barbu
cs.AI
Current LLM ensemble frameworks focus on multi-step setups with additional modules for answer ranking, often opting for token and span analysis rather than structured outputs, leading to heavyweight architectures with potential fail states along the pipeline. Faster, lighter solutions are more vulnerable to hallucination propagation and can lack output control in more complex pipelines. This paper proposes a customisable, lightweight ensemble...
-
15
Using Machine Learning to Measure Self-Efficacy Belief Through Learners' Interaction Traces in Technology-Enhanced Learning
Maeva Somny, Linda Chouati, Marie Lefevre
cs.AI
Self-efficacy beliefs play a critical role in learners' performance, academic choices, and, more broadly, in their future career trajectories. As Technology-Enhanced Learning (TEL) environments have demonstrated strong potential for supporting both performance and motivation, investigating self-efficacy within such environments is of particular interest, especially for implementing remedial practices as early as possible to support learners'...
-
16
Automated Keyword Generation Using LLMs in a High-Volume Data Virtualization Service
Saiful Khan, Yiwen Xing, Joyraj Chakraborty, Afrah Farea, Philip Beaucamp, Samuel Jackson, Min Chen
cs.AI
In modern data infrastructure, a data virtualization service (DVS) allows users to create many versions of source datasets for different processing tasks. For example, a multivariate or multi-modality dataset can be used for different machine learning tasks (e.g., classification, detection, segmentation, forecasting, and so on). Data selection, participation, integration, and preprocessing in different tasks result in many virtual datasets...
-
17
Fuzzy selective state model for forecasting the dynamics of consumer preferences
P. A. Golovinski, A. A. Drobyshev, A. O. Shatalova
cs.AI
We consider forecasting the dynamics of consumer preferences of retail chain customers. A customer's preference is described by a triangular fuzzy number. The evolution of the preference over time is governed by a Mamba-type selective state space model whose hidden state is a triangular number, with computations carried out in M.G.~Matveev's two-component algebra of fuzzy numbers. The recurrence parameters are computed from crisp features,...
-
18
Learning to Interact and Direct: Co-Evolving Video Director Agents
Yingzhao Jian, Zhongan Wang, Yuxuan Hou, Hehe Fan
cs.AI
Video director agents orchestrate multistage production to realize users' creative visions. Emerging research on their self-evolution advances screenplay planning effectively. However, the mutual reinforcement between directing and user interaction remains largely overlooked. Improved interaction clarifies user intent and informs workflow refinement, while more reliable execution shifts collaboration from troubleshooting to creative...
-
19
Dynamical Memory Transformer: Selective Recurrent Memories with Constant Cost Attention
Yannis Bendi-Ouis, Xavier Hinaut
cs.AI
Transformers retain an explicit history of the sequence, allowing attention to directly retrieve past representations. However, the size of the KV-Cache and the cost of a new token increase with the context length. State Space Models compress the past into a fixed-size recurrent state, at the cost of reduced addressability. We present the Dynamical Memory Transformer (DMT), a hybrid architecture that separates sequence encoding from...
-
20
ReuScope: Auditing Data Reuse and Evaluation Sensitivity in Capsule Vision 2024
Eunseob Choi, Kyeonghun Kim, Hyuk-Jae Lee, Nam-Joon Kim
cs.AI · cs.CV
We develop ReuScope, a protocol for auditing data reuse and evaluation sensitivity, using Capsule Vision 2024 as a case study. It combines measurements of data relationships with two comparisons: changing the evaluation population while holding predictions fixed, and changing training data while holding evaluation fixed. Byte-identical files cross the public training-validation boundary, and all 41 Kvasir-Capsule recordings that contribute...
-
21
RECAST: REconstruction of Chain-of-Thought via Auditable Structured Traces
Qi Wang, Kang Xu, Chengcheng Wan, Jiangtao Wang
cs.AI
Large closed-source reasoning models expose only their final answers. The intermediate reasoning that produces those answers is hidden behind API surfaces, tool-call policies, and safety filters. Existing chain-of-thought (CoT) extraction methods assume a side channel: a visible reasoning field, a scratchpad carried through tool calls, or a signed/encrypted reasoning block. We reproduce three representative state-of-the-art extraction methods...
-
22
Whose Values, Which Contexts, and What Signals? Grounding Cultural Value Alignment with Re3Culture
Jing Yao, Hyunjin Hwang, Weihua Zheng, Bryan Chen Zhengyu Tan, Jia Wang Peh, Dylan Raharja, JinYeong Bak, Roy Ka-Wei...
cs.AI
Cultural value alignment requires not only model optimization but also a well-specified target grounded in real-human evidence. Yet how such targets should be grounded in human data remains largely unexplored, raising three fundamental questions: (1) whose values should be represented? (2) where should cultural values be observed? and (3) what signals reveal underlying values? We investigate these questions through Re3Culture, a large-scale...
-
23
Clinical-Protocol-Aware Cyber Resilience for Connected Clinical Technologies Under AI-Enabled Adversarial Conditions
Pranav Patel, Siva Kannathasan, Prerak Patel, Jigar Patel, Vansh Patel, Sheel Patel
cs.AI · cs.CE · cs.ET · cs.NI · eess.SY
Healthcare increasingly relies on connected medical devices, clinical information systems, cloud services, and distributed-care technologies, creating cybersecurity risks across clinical workflows. AI-enabled capabilities can accelerate vulnerability discovery and attack-path analysis, increasing the need to limit compromise propagation. This paper proposes a clinical-protocol-aware cyber-resilience framework based on bounded clinical...
-
24
Multimodal In-Context Learning with Explicit Rule Induction
Yuquan Li, Xinyang Jiang, Yuhao Xue, Cairong Zhao
cs.AI
A central challenge in multimodal in-context learning (MICL) arises from tasks that are ill-defined without context and require uncovering the underlying rules from demonstrations. Existing methods predominantly treat MICL as direct input-output mapping, overlooking the importance of explicitly inducing and reasoning over such rules, limiting both performance and interpretability. We propose ERIM, Explicit Rule-Induction for Multimodal...
-
25
Advancing Clinical Trial Outcome Prediction with Domain-Specific Large Language Models
Burak Bakkar, Hana Moalla, Mohamed Salem Jedidi, Haifa Ben Messaoud, Nicolas Lopez Carranza
cs.AI
Clinical trial failures are a major barrier to efficient drug development, incurring substantial costs and delaying patient access to effective therapies. Structured approaches such as the Hierarchical Interaction Network (HINT) predict trial outcomes by explicitly modelling interactions between drugs, diseases and protocols, but make limited use of the free text in trial registrations. We evaluate two domain-specific language models, BioBERT...
-
26
TSBPO: Tree-Structured Branching for Policy Optimization in Interactive Language Agents
Rui Yu, Chong Mu, Jinchuan Zhang
cs.AI · cs.CL · cs.LG
Training interactive language agents from terminal outcomes poses three coupled problems: which task and state continuations to sample, how to assign delayed feedback to decisions, and how to aggregate token losses for multi-token actions. We present TSBPO, a tree-structured sampling-to-update paradigm that addresses these problems within one training loop. A likelihood-fitted Root/Branch allocator uses retained task and state evidence to...
-
27
Radial Kernel Attention for Long-Range Modeling in Polymer Machine Learning Force Fields
Wenbo Fu, Chenghui Mao, Chengwen Hu, Haifeng Lv, Zhou Lv
cs.AI
We introduce Radial Kernel Attention (RKA) for long-range modeling in polymer machine learning force fields. Local neighbor graphs constrain communication across polymer chains and their surrounding environments, while explicit all-pair attention incurs quadratic cost. RKA maps atomic distances from the cluster centroid to learned radial features and combines their overlap with content-dependent queries and keys. Factorized aggregation and...
-
28
Breaking Information Islands in Sparse Tuning via Small-World Connectivity
Xianchao Guan, Zijun Xiong, Yifeng Wang, Yubo Cui, Yaowei Wang, Guo-Sen Xie, Xin Li, Zheng Zhang
cs.AI
Sparse tuning is widely used to adapt large language models due to its parameter efficiency. However, its effectiveness depends not only on the number of trainable parameters, but also on the feature-interaction topology of the sparse update's structural support. Limited or uneven connectivity in this support may isolate subsets of feature dimensions, forming information islands that restrict direct task-specific interactions through the...
-
29
Risk-Sensitive Mission Planning for Multi-Target On-Orbit Inspection via Distributional Reinforcement Learning
Adam Abdin
cs.AI · math.OC
Multi-target on-orbit servicing missions require planning tools that can adapt to evolving operational conditions while accounting for the outcome variability inherent to safety-critical spaceflight. This paper presents an adaptive planning approach for multi-target servicing campaigns in low Earth orbit and applies it to inspection missions flown by a low-thrust servicer. The approach is based on Distributional Reinforcement Learning, which...
-
30
Chance-Constrained Inspection Viewpoint Sequencing for On-Orbit Servicing via Safe Reinforcement Learning
Chloé Carer, Adam Abdin
cs.AI · math.OC
Autonomous inspection of a target spacecraft is typically the initial step in on-orbit servicing. Planning close-proximity observation viewpoints involves a complex combinatorial problem constrained by coverage, fuel, and safety considerations. This paper models the viewpoint selection as a Constrained Markov Decision Process (CMDP) and applies Proximal Policy Optimization with Lagrangian relaxation to solve it. The system combines a...
-
31
What Should LLMs Forget: Reinforcement Unlearning of Knowledge Associations
Wutong Xu, Yun Qu, Haiyan Feng, Qi Wang, Xiangyang Ji
cs.AI
Large language models (LLMs) acquire extensive factual knowledge during pre-training, which may include sensitive, private, or copyrighted information, motivating the development of unlearning methods that selectively remove specific knowledge while preserving general capabilities. However, existing approaches typically optimize entire responses without explicitly identifying the knowledge to be forgotten, resulting in coarse and uncontrolled...
-
32
Real Computation or Merely Naming? A Pre-Registered Mechanism Audit of 25 Cognitive-Architecture Modules in an LLM-Based Agent System
Peter Chen, Ni Zhang, Ying Xu, Siyuan Zhang
cs.AI
Agent systems built on local large language models are increasingly marketed through the vocabulary of cognitive architecture: modules named global workspace, theory of mind, causal reasoning, or active inference are listed as features, and the presence of the name is taken as the presence of the mechanism. We ask the prior question -- does the named computation actually happen -- and contribute a transferable verification method for the...
-
33
Patch-Based Deep Kernel Learning for Data Assimilation and Bias Correction with Extremely Sparse Observations
Emanuele Mele, Angelo Coluccia, Massimo Cafaro, Italo Epicoco, Paola Nassisi
cs.AI
Data Assimilation (DA) reconstructs the state of a spatio-temporal system by combining sensor observations with the output of a numerical model. Since model states are high-dimensional while observations cover only a small fraction of the domain, DA is a challenging large-scale estimation problem, central to weather forecasting and oceanography. Classical variational methods such as 3D-Var rely on a hand-crafted background error covariance...
-
34
Connectivity-Aware Client Selection in Decentralized Federated Learning
Usevalad Milasheuski, Monica Nicoli, Stefano Savazzi
cs.AI
Decentralized federated learning (DFL) has emerged as a scalable alternative to centralized federated learning, removing the single point of failure and communication bottleneck at the server. However, most existing decentralized approaches rely on full-neighborhood broadcasting, where each client transmits its model update to all of its neighbors in each communication round. While effective, this results in significant communication overhead...
-
35
Verify--Backtrack Loop: Structured Precondition Recovery for Long-Horizon Language Agents
Mingyang Liu, Qingcan Kang, Shixiong Kai, Tao Zhong, Mingxuan Yuan, Xin Li, Linqi Song
cs.AI
Language agents increasingly tackle long-horizon tasks in interactive environments, where actions often depend on latent preconditions. The core difficulty is not trajectory length but recovery: when a prerequisite is missing or an earlier decomposition fails, trying another plausible action rarely helps. ReAct and later reflection or adaptive-planning methods support local correction, but express recovery as free-form text, with no explicit...
-
36
Specification-Guided Generation for Large Language Models
Alessandro Previti, Konstantinos Vandikas, Mario Alviano, Mats Carlsson, Albin Larsson Forsberg, Alexandros Nikou,...
cs.AI
Large language models (LLMs) can generate structured outputs, but existing constrained-decoding methods mainly enforce syntax and cannot directly enforce satisfaction of a formal specification. We introduce a neuro-symbolic, specification-guided decoding framework that combines LLM generation with symbolic reasoning. At each step, the framework refines the decoding grammar by filtering out values that cannot be extended to an output...
-
37
Multi-Test Nation Bias Benchmarking of LLMs with Explicit Unbiased Baselines
Jonghyeon Choi, Yeonjun Choi, Beakcheol Jang
cs.AI
While prior work has highlighted that systematic nation-level bias in large language models (LLMs) can pose operational risks for international relations (IR) applications, many existing evaluations still lack a clearly specified unbiased reference (ground truth), limiting fully quantitative and cross-setting measurement. Using an expanded corpus of 722 official UN Security Council (UNSC) records, we measure nation-level bias with five...
-
38
EvoMCP: Co-evolving MCP agents and training data
Xuanang Gao, Kepeng Lin, Xinyan Shi, Yong Deng, Shuheng Shen, Changhua Meng, Xiaofeng Wu, Jie Yang, Wei Liu
cs.AI
Supervised fine-tuning of Model Context Protocol (MCP) agents is typically conducted on a static data distribution, which fails to adapt to the student's evolving capabilities and leaves newly exposed weaknesses insufficiently addressed. To address these challenges, we propose \method, an agent--data mutual evolution framework that enables MCP agents to improve through a closed loop of task evolution, trajectory evolution, and supervised...
-
39
Evidence-Guided Recovery for AI Agents with Ambiguous Tool Outcomes and Partial Execution
Genliang Zhu, Xiaobo Chen, Ziyuan Wang, Chu Wang
cs.AI
Tool timeouts can leave AI agents facing ambiguous tool outcomes and partial execution: an action may have failed, committed or remained in flight while other workflow steps have already completed. We formulate evidence-guided task recovery over approved obligations, provider capabilities and states compatible with public evidence. A shared admissibility check handles key expiry, authorization timing, dependencies and residual effects; a...
-
40
CryoAtlas: A Large Curated Dataset and Unified Benchmark for Cryo-EM Atomic Model Building
Mingrui Li, Minzhang Li, Weichen Qin, Yufan Xie, Zhangzhi Xiong, Sixian Shen, Jiakai Zhang, Yuan Pei, Jingyi Yu
cs.AI
Deep learning has accelerated automated atomic model building from cryo-EM maps, yet progress remains limited by the lack of large, high-quality datasets and standardized evaluation benchmarks. We address this gap by introducing CryoAtlas, a rigorously curated dataset and unified benchmark for density-guided atomic model building of protein chains. By integrating and filtering EMDB and PDB entries (up to March 2026), CryoAtlas provides 17,809...
-
41
scAnyOmics: Foundation-Model Distillation for Any-to-Any Completion of Multi-omics Virtual Cells
Zhaoqi Song, Ye Du, Yusuke Iwasawa, Yutaka Matsuo, Qian Niu
cs.AI
Recent advances in single-cell technologies have enabled the profiling of multiple molecular modalities, including transcriptomics, proteomics, and chromatin accessibility, providing a more comprehensive understanding of cellular states. However, integrating heterogeneous modalities and predicting missing molecular information remain challenging, particularly when paired measurements are limited. Here, we introduce scAnyOmics, a generative...
-
42
Cross-Interface Authorization for AI Computer-Use Agents
Genliang Zhu, Chu Wang
cs.AI
Computer-use agents act through graphical interfaces, command lines, APIs, scripts, and Model Context Protocol servers. A policy decision can be interface-invariant while its executable authorization is not: another route can bypass mediation, alter a security-relevant default, or commit after the authorized state has changed. We present a profile-bounded protocol for a fixed, versioned computer-use deployment. It enumerates effect-bearing...
-
43
Online Evidence-Containment Prediction over Text Spans under Distinct Queries
Xiang Liu, Haochen Ding
cs.AI
Evidence-grounded NLP systems often verify nested text regions sequentially, so verifying one region constrains others. We formalize this as Online Evidence-Containment Prediction (OECP): each candidate is predicted before exact verification and queried at most once. Span containment is exactly a triangular 2D product order, making OECP distinct-query online isotonic regression. With multiple admissible targets, worst-case regret is...
-
44
Ask on Demand: Targeted Peer Communication for Parallel Agentic Systems
Haofu Yang, Hongyang Yin, Ran Bi, Faguo Wu, Peng Xue, Feng Zhou, Han Zhang
cs.AI
Parallel LLM agents tackle complex tasks by exploring multiple trajectories, yet useful discoveries remain isolated in individual execution histories. Existing sharing methods often select or summarize information before other agents' needs become clear, potentially overlooking details that become important later. We propose Ask on Demand (AOD), a communication framework that enables agents to seek targeted peer assistance when specific...
-
45
From the Zoo to the BULLPEN: Sample-Efficient LLM Profiling via Multi-Channel Model Embeddings
Russell Ro, Qiming Cui, Reza Abbasi-Asl
cs.AI · cs.LG
Choosing among the hundreds of thousands of available large language models (LLMs) requires a thorough understanding of each candidate model's properties. In practice, each property is measured by its own benchmark suite, so profiling a model on many properties means paying for many separate evaluations. To address this, model embeddings compress each model into a fixed-length vector from which many properties can be predicted. Existing...
-
46
RECITE: Revising Eligibility Criteria Incorporating Textual Evidence
Russell Ro, Reza Abbasi-Asl
cs.AI
Overly restrictive eligibility criteria contribute to widespread enrollment failure in clinical trials, yet published recommendations for how specific criteria should be broadened remain disconnected from trial design at scale. We introduce RECITE (Revising Eligibility Criteria Incorporating Textual Evidence), a framework for automated discovery, extraction, and implementation of evidence-based eligibility criteria revisions. RECITE uses...
-
47
LEAP: Efficient LLM Inference Scheduling with Generalizable Length Prediction
Kwan Yan, Jialun Zhong, Yanzeng Li
cs.AI
Length-aware scheduling reduces request latency in LLM serving by prioritizing shorter requests. However, despite their large model sizes, length predictors can suffer degraded ranking performance under domain and task shifts, and adapting them can require costly retraining. Their prediction overhead can further offset the benefits of scheduling. To improve the generalization and efficiency of length-aware scheduling, we propose...
-
48
Do Transaction Prices Reflect Visual Preference? A Diagnostic Study with Multimodal Language Models
Fengxian Ji, Jingpu Yang, Fan Zhang, Junhong Liang, Qian Jiang, Yuke Li, Jinri Guo, Rongxin Zhu, Zhuohan Xie
cs.AI
Existing visual preference evaluation relies on costly human annotations or preference reward models, whereas online marketplace transaction prices are readily available and reflect real purchasing behavior, offering potential low-cost supervision. However, transaction prices conflate visual preferences with non-visual factors such as provenance, demand, and competition, making aggregate accuracy insufficient to distinguish model errors,...
-
49
Operon-S1: a fast decision controller for long-horizon biomedical agents
Genoria AI Team, Yuejie Hou, Yueyuxiao Yang, Weiting Tang, Meng Yang
cs.AI · cs.LG
Language-model agents now carry out long scientific work in biology, but their judgements about conventions, skills, errors, evidence and stopping are made inside the reasoning that does the work, where they cannot be measured, replaced or improved on their own. Here we present Operon-S1, a fast decision system, a System 1 for the agent, that separates judging from doing. A decision harness poses the agent's recurring judgements as closed...
-
50
SERIAL-7: Deriving, Realizing, and Preserving Machine-Verifiable Outputs Across Representations
Youngkyung Seo, MiHyeon Kim, Jisoo Lee, Hwijung Ryu
cs.AI · cs.CL
Large language models increasingly generate structured outputs consumed by programs and downstream systems, where semantic correctness alone does not guarantee reliable execution. We introduce SERIAL-7, a Korean-English benchmark built around an executable verification framework for machine-verifiable generation across seven representations. Using 177 validated canonical artifacts, SERIAL-7 separates semantic derivation (Derive), constrained...
-
51
Subliminal Reinforcement Learning: traits travel through a judge's scores
Keuntae Kim, Yong Suk Choi
cs.AI
Subliminal learning, the transfer of a model's trait through data with no semantic trace of it, has been shown for students trained on a teacher's text. Post-training relies on group relative policy optimization with a language-model judge, where the student learns only from its own outputs and one judge's scores. We show this suffices: a student writes invented syllables or numbers, a judge made to prefer one animal scores them, and the...
-
52
Self-Improvement with Auxiliary Rewards: Learning from Verified Traces and Evaluating Transfer
Minju Gwak, Alan Ritter
cs.AI
Answer-level rewards cannot distinguish reasoning traces with equally correct outcomes. We study whether auxiliary trajectory preferences improve small-language-model self-improvement and transfer under limited supervision. We compare confidence-based (SC) and entropy-based metrics (UID-Conj.), which combines global entropy variation and local smoothness, through online reward augmentation and offline training on correct responses. Online...
-
53
SAT-ACT: Learning CDCL Branching from Outcome-Derived Action Preferences
Zhenchao Sun, Chongyang Tao, Ping Lu, Tongkai Lu, Jianling Gao, Shuai Ma
cs.AI · cs.LG
Learning-based approaches have increasingly been explored for SAT solving, with particular attention to improving branching decisions in conflict-driven clause learning (CDCL) solvers. These approaches derive branching guidance either from static structural properties of SAT formulas or from dynamic signals obtained through solver feedback and execution traces. However, these forms of supervision provide limited evidence about state-dependent...
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.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.