cs.AI · 2026-11-03 · No. 162
Artificial Intelligence, 2026-11-03.
46 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
46 entries-
01
From Natural Language to Exact Cover: A Neuro-Symbolic Approach to Zebra Puzzles
Paulius Skaisgiris, Thomas Pammer, Veronika Semmelrock, Mykyta Ielanskyi, Maximilian Heisinger, Erich Kobler
cs.AI
Chain-of-Thought (CoT) generation has substantially improved the performance of Large Language Models (LLMs) on complex reasoning tasks, including code generation, data analysis, and exam-style question answering. Despite these advances, purely neural LLMs continue to struggle with elementary logical reasoning problems and lack the determinism, soundness, and reliability characteristic of symbolic reasoning systems. Conversely, classical...
-
02
WebHarbor: Docking Real Websites for Evolving GUI Agent Environments
Zhaoyang Wang, Qianhui Wu, Boyu Gou, Demi Wang, Jiacheng Zhang, Peichun Hua, Qize Li, Shi Qiu, Yifan Jiang, Yifan...
cs.AI · cs.CL · cs.LG
GUI web agents require realistic and interactive environments that remain stable during both evaluation and training. Live website evaluation suffers from changing content, access restrictions, and limited coverage of authenticated workflows, while existing synthetic environments for training often lack functional depth and visual fidelity. We propose WebHarbor, a suite of 153 executable and dockerized website environments that faithfully...
-
03
Strategist: Evolving Reasoning with Agents
Taiming Lu, Qi Xu, Zhigang Hua, Zhuang Liu
cs.AI · cs.CL
A model is only half of an AI agent system. The other half is the inference strategy: the reasoning procedure that turns model calls into a response. Today that second half is written by hand, and the experience of building one strategy never carries to the next. We introduce Strategist, a meta-agent that evolves inference strategies across tasks. Each strategy is written as a blueprint,executable code that other strategies can reuse, and...
-
04
DiabAgent: Toward Agentic Physiological Control
Chengxi Li, Shaoxuan Li, Deyao Hong, Qingle Liu, Yi Huang, Puheng Bian, Minzhi Xu, Lanyue Zhang, Mingze Sun, Xin Li,...
cs.AI · cs.CL
As pretraining scales, medical language models have advanced rapidly in clinical question answering. Their ability to achieve effective physiological control through sustained intervention still lacks systematic quantitative evaluation. Type 1 diabetes provides a concrete setting: impaired insulin secretion creates dependence on exogenous insulin, with dosing continually adjusted using information about meals, exercise, illness, and glucose...
-
05
Four Bridges: Measuring Deception Propensity in a Multi-Agent Game
Raphael Casey, Michael Simeone, Alberto Tosato, Florian Ernst, Kemal El Moujahid, James Tamplin, Tommaso Tosato
cs.AI · cs.MA
AI agents are increasingly deployed in settings where they interact and coordinate with other agents, yet honesty is mostly measured in single-turn, single-agent benchmarks that pressure the model to deceive. We study deception that emerges in multi-agent interaction without any instruction to deceive. We introduce Kradle, a platform for evaluating AI models, and Four Bridges, an information asymmetry game in which four agents distribute...
-
06
FedReady: Bounded Agents for Federation Formation
Ziyue Xu, Holger R. Roth, Chester Chen, Peter Cnudde
cs.AI · cs.MA
Federated learning (FL) runtimes standardize aggregation and deployment, but each new study still requires federation formation: selecting task-eligible sites and preparing their local data and task code for federated training or analysis. This preparation recurs when the target changes, while raw records and site-private mappings are excluded from cross-site FL messages. We present FedReady, a system that performs federation formation with...
-
07
An Agentic Framework for Automated Power System Studies and Grid Connection Assessment
MaoXun Huang, Kshitij Kapoor, Eli Louise
cs.AI
Connecting new generation and demand to the grid depends on two scarce skills: checking applications against a large, changing body of regulation, and running the network studies that decide where and how a project connects. We present Grid Agents, an AI system that brings both together, and the methodology we use to evaluate it. The Grid Ontology is its knowledge system. It represents the regulation, standards and engineering knowledge that...
-
08
Grading the Unannotated: Insights from the WorkRB Skill Extraction Challenge at RecSys-HR 2026
Warre Veys, Luis Gasco, Jens-Joris Decorte
cs.AI
Skill extraction benchmarks score models against a few human-annotated positives and treat every other skill in the vocabulary as equally wrong. At the scale of ESCO (13,939 skills) this binary view can reward models that rank the annotated positive high for the wrong reason, and hides semantically nonsensical predictions. The WorkRB Challenge at RecSys-HR 2026 replaces it with graded relevance: every candidate skill in a model's ranking...
-
09
Can AI Do Formal Demography? Why Vaccinating the Oldest Saves Both the Most Lives and the Most Years of Life
Joshua R. Goldstein, Kenneth W. Wachter
cs.AI · q-bio.PE
Can AI contribute to formal demography? We report an experiment in which an AI model, Claude, was asked to explain and then simplify the proof of an earlier result: that vaccinating the oldest against COVID-19 saves both the most lives and the most years of life, because the years saved per person treated rise with age. The model proposed a new proof that is shorter, more intuitive, and somewhat more general than the original, built from a...
-
10
Online Label-Free Gradient Matching for Continual Language Model Training
Sajjad Pakdamansavoji, Mohammad Reza Rezaei, Ilija Subasic, Pedro Garzon, Radu Paradovschi, Zhao Chen
cs.AI · cs.CL
Language models in customer-facing products must be continually updated, since the data they serve shifts over time. As retraining on the full accumulated data is impractical, each update should instead run on a small set of examples carrying the training signal of all data seen so far. The strongest current methods build this set by gradient matching, which synthesizes examples whose training gradients match those of the full data. However,...
-
11
Playing Dumb: How a Chess Transformer Simulates Users Across Skill Levels
Difan Jiao, George Eilender, Zhenwei Tang, Ashton Anderson
cs.AI · cs.LG
Generative models increasingly simulate users at different skill levels in education and AI evaluation. Yet it remains unclear whether lower-skill behavior reflects less internal knowledge or a different use of retained knowledge. This distinction is difficult to study in natural language, where proficiency and relevant knowledge are hard to measure. In this work, we study Maia-2, a chess transformer that predicts human moves conditioned on...
-
12
Optimize the Harness, Not the Model: Fitting a Minimal Agent to a Self-Hostable LLM for Investigative Analysis
Shai Nahum Gefen, Vered Chassida, Dmitry Basin, Guy Feigenblat
cs.AI · cs.CL · cs.MA
Government intelligence teams need LLM agents that can analyze large, messy evidence collections, but security and cost constraints often rule out hosted frontier models and broad, hard-to-audit tool surfaces. We report CLEO: Constrained Loop for Environment Optimization, a method for fitting a minimal agent harness to a fixed, self-hostable LLM. Given an expert-validated dataset, CLEO admits only the tools, guardrails, memory policies, and...
-
13
DeliverBench: Benchmarking AI Agents on Delivering Realistic Multi-Stage Professional Projects
Yumou Liu, Mingju Chen, Zhoufutu Wen, Qianyu Yang, Zijie Wang, Yeqian Liu, Chenghao Yang, Tiliang Duan, Qiyu Cai,...
cs.AI
LLM agents are judged by what they deliver, and in professional work what gets delivered is a project, not a task. A project pays off only if the whole package holds, and one weak part can limit the value of the rest. Yet existing benchmarks mostly test agents on one task at a time, leaving a gap between the capability we measure and the outcome that makes agents useful. To address this gap, we introduce DeliverBench, which tests whether...
-
14
LAND: Learning an Adaptive Number of Draws for Bayesian Best-of-N Selection
Koen Oostermeijer, Teryn Jones
cs.AI
Best-of-N decoding improves generation quality by sampling multiple candidates and selecting the best, but it allocates equal compute to sources regardless of how much they benefit from additional sampling: the expected benefit is small for sources with low-variance score distributions and potentially much larger for those with high-variance distributions. To address this shortcoming, we propose LAND (Learning an Adaptive Number of Draws),...
-
15
Can We Stop the Backtest Yet? Anytime-Valid Promotion Tests for Adaptive Financial Research Agents
Eric Benhamou, Jean-Jacques Ohana, Beatrice Guez, Ethan Setrouk, Chamyl Saadi, Thomas Jacquot
cs.AI · q-fin.ST
Financial research agents can generate and monitor trading rules faster than a human can document the resulting selection process. Candidates appear at data-dependent times, weak rules are abandoned, and promising ones are watched until they cross a reporting threshold. We introduce PROMOTE, a protocol that assigns every candidate predictable testing wealth at birth and accumulates a cost-aware e-process only from subsequent returns. If...
-
16
Same Outputs, Different Scores: Auditing the Unchecked Graders of Multimodal LLM Benchmarks
Ahmad Jarjis Hasan, Jonathan Lwowski
cs.AI · cs.CL · cs.CV
Every multimodal-LLM multiple-choice benchmark ends with a scoring rule that converts a model's response, often free-form text rather than a clean option letter, into a right/wrong verdict, buried in its code. Unlike the dataset, this rule is chosen without justification and left unexamined, yet it sets the published number. We reproduce the official scorers of eight peer-reviewed benchmarks on five open vision-language models (VLMs) that fit...
-
17
Mixed-Methods Exploration of Sociotechnical Factors to Improve Adoption of Crime-Reporting Apps in Urban Communities
Olalekan David-Banjo, Chinazunwa Uwaoma, Paul Witman
cs.AI · cs.CY
Crime-reporting mobile applications can enhance community safety and engagement in urban areas, yet their adoption remains low, partly because developers prioritize technological features over residents' social realities. This study used an exploratory sequential mixed-methods design to identify and validate the sociotechnical factors that drive adoption. Two focus groups and an analysis of 660 app reviews revealed that users' initial sense...
-
18
The SIMPLE Law for Energy Cost of LLM Inference
Hiari Pizzini Cavagna, Andrea Proia, Daniele Cesarini, Zeynep Kiziltan, Andrea Bartolini
cs.AI · cs.LG · cs.PF
Generative AI is billed per token, yet tokens are not equally expensive. Each token enters the KV-cache and raises the cost of those that follow, so energy grows non-linearly along a sequence whose tokens look identical. No analytical model states what a token costs, and the most accurate SOTA model is a fit, not a law: it absorbs architecture into fitted coefficients, requiring per-LLM fitting. We derive closed-form expressions of the...
-
19
From FAIR to AI-FAIR Metadata-First Infrastructure for AI-Enabled Science
Elizabeth G. Campolongo, Eric R. Sokol, Marty Downs, Gina Glenne, Gregory E. Maurer, Sydne Record, Dustin R....
cs.AI · cs.DB · cs.HC · cs.IR · q-bio.QM
Artificial intelligence (AI) technologies and their capabilities have advanced rapidly over the past few years, leading to widespread interest and adoption in the biological and ecological sciences. However, the data infrastructure and computational resources that provide the foundation for AI workflows in ecology and biodiversity science remain fragmented. Moreover, the flow of value remains largely unidirectional: data move from collectors,...
-
20
Top-$k$ Retrieval Leaves Memory Value Undetermined
Arman Behnam
cs.AI
A memory-augmented agent must decide which memories to keep, merge and retrieve, and its only evidence of their value is its retrieval log: the memories it retrieved in each episode and whether it succeeded. Existing methods assign every memory a value from this log, even when the log cannot separate one memory's contribution from another's. We treat the log as an experiment that nobody designed and ask which memory values it determines. Two...
-
21
ScienceCUA: Resource-to-Skill Construction and Execution-Guided Skill Evolution for Scientific Computer Use Agents
Daiqiang Li, Jingyi Peng, Rui Hu, Jia Li, Xuyang Liu, Guanren Qiao, Yujia Xiang, Qiuzhuang Sun, Zhiping Xu, Mingrui Luo
cs.AI
Computer-use agents for scientific software require application-specific expertise. Much of this expertise is documented in human-authored software manuals and web pages. However, turning these resources into executable, reusable skills remains challenging due to mismatches between documented and deployed software versions and differences in scope between documentation coverage and task requirements. We introduce ScienceCUA, a two-stage...
-
22
Axion 1.0: Open Agent Foundation Models, Simplified
Yuqi Jia, Yunjie Tian, Jiayu Zheng, Yijun Liang, Jingchen Sun, Mengyu Zhao, Di Fu
cs.AI
We introduce Axion 1.0, a fully open agent foundation model that combines strong and broad agentic capabilities with a remarkably simple training recipe. Axion 1.0 is trained in only three stages: two lightweight supervised fine-tuning stages followed by reinforcement learning, without dedicated mid-training, direct preference optimization (DPO), or on-policy distillation (OPD). The first SFT stage develops strong self-contained reasoning...
-
23
Auto-Research Agent on MSA Organization to Improve Protein-Protein Complex Structure Prediction
Zilu Zhang, Jing Bao, Lifeng Qiao, Sheng Xu, Qiantai Feng, Siqi Sun, Yang Yang
cs.AI
Protein-complex structure prediction with AlphaFold 3 depends on MSA content, depth, and cross-chain pairing. Current pipelines apply uniform recipes, typically maximizing depth and pairing by species, yet even whether cross-chain pairing helps AF3 remains contested. We show that the value of both depth and pairing is strongly target-dependent, so no single recipe is optimal across interfaces. We introduce an autonomous agent that treats a...
-
24
CoworkOS:Scaling Agent Coworkers for Real-world Automation
Jiajie Jin, Guanting Dong, Chengjun Pan, Xin Deng, Zhuohui Sheng, Guoqiang Wang, Tao Gui, Yutao Zhu, Yujia Chen,...
cs.AI · cs.CL
Rapid advances in cowork agents are shifting human-AI collaboration toward real-world automation, delivering software, designs, and other artifacts. However, such productivity work demands both high-quality delivery on complex productivity tasks and continued monitoring and decision-making over long horizons, a combination that remains an open challenge. We introduce CoworkOS, a general-purpose harness for long-horizon work that separates...
-
25
Toward Knowledge-Centric AI: Discovering, Internalizing, and Using Explicit Knowledge Across Agents and Generations
Yisen Gao, Haoyu Huang, Zhongwei Xie, Yufei Li, Hong Ting Tsang, Boyi Zhang, Qiao Xiao, Tianshi Zheng, Jiaxin Bai,...
cs.AI
Knowledge is how understanding accumulates across people and generations: durable records that outlive their producers and that others can check, combine, teach, and correct. AI agents are now built and run by many independent users and organizations, and each agent is upgraded, replaced, or retired within months. Yet what an agent learns stays trapped in model parameters, a transient context window, or a system-specific memory store that is...
-
26
CUA-Master: Scaling Computer-use Agents through Open-World Recursive Improvements
Xinlei Yu, Gen Li, Ji Zhao, Zhangquan Chen, Congcong Wang, Shuai Dong, Zelin Peng, Yuqi Xu, Hongrui Wu, Kaiwen Tuo,...
cs.AI
Despite recent advances in CUAs, their development remains constrained by the limited diversity, controllability, and reliability of interaction data. Moreover, conventional optimization pipelines lack iterative feedback, while existing recursive improvement approaches often rely on self-generated experiences, limiting ability expansion and yielding diminishing returns. To address these challenges, we introduce CUA-Master, a nested...
-
27
ComplianceAtlas: A Taxonomy-Driven Agentic AI Framework for Automated AI Act Gap Analysis and Remediation
Ilias Driouich, Hongliu Cao, Eoin Thomas, Yannick Devaux, Agnes Brodelle
cs.AI
Assessing regulatory compliance for high-risk AI systems requires systematic identification of technical gaps such as missing controls, in- adequate processes, or shallow evaluation of practices. Compliance officers typically admin- ister structured questionnaires collecting evi- dence of current practices, where organizations respond with descriptions of their existing pro- cesses, technical capabilities, and architectural choices. However,...
-
28
From Local Skills to Long-Horizon Web Tasks: Progressive Skill Exploration for LLM Web Agents
Xueyang Feng, Xiaohe Bo, Xu Chen, Quanyu Dai, Feng Wen
cs.AI
Large language models (LLMs) are driving autonomous agents toward real-world environments, with the Web emerging as one of the most representative interaction scenarios. However, training Web agents with naive exploration remains challenging: successful trajectories are rare, and the sparse terminal rewards make it difficult for agents to obtain useful feedback from failed trajectories. Inspired by skill acquisition theory, we propose...
-
29
LUCA: A Synthetic World for Experimental Reasoning
Anna Gogleva, Thomas Charman, Martin Balla, Karl Gemayel
cs.AI
An experimental agent can succeed for the wrong reasons. Evaluations, however, often focus on the outcome, not the experiments, evidence, and inferences that produced it. We introduce LUCA, a configurable synthetic world for evaluating this process under fully known ground truth. Agents learn unknown regulatory systems through budgeted experimentation, then predict unseen interventions, diagnose hidden faults, and attempt rescues. This setup...
-
30
A Fine-Grained Hierarchy and Benchmark for State Tracking in Language Models
Jackson Petty, William Merrill, Ashish Sabharwal
cs.AI
Theoretical limitations of transformers on state tracking---the ability to track information about entities or variables over long contexts---have motivated new recurrent language modeling (LM) architectures such as Gated DeltaNet (GDN). These architectures have, in particular, been benchmarked against the $S_5$ word problem, a theoretically hard state-tracking task that captures abilities such as code evaluation under arbitrary variable...
-
31
Avatar Intelligence: Amplifying Human Agency Through Persistent Personal Agents
Zheng Wu, Xinbei Ma, Yao Yao, Zhaoyuan Huang, Haowen Hu, Yijie Lu, Taolei Wang, Yifei Yang, Wuyue Xiong, Pengzhou...
cs.AI · cs.CL
Personal AI agents are increasingly capable of handling long-horizon tasks across applications, yet users often need to invest substantial effort in specifying goals, resolving ambiguity, and verifying outcomes. We argue that progress should be measured by how effectively agents amplify human agency: enabling people to pursue their goals with less routine supervision while retaining control over consequential decisions. We advocate Avatar...
-
32
Towards a Trustworthy and Governable Internet of Agentics: An Architectural Perspective on Protocols, Systems, and Services
Haoyi Xiong, Yi Liu, Jiang Bian, Peng Diao, Bin Zhu, Tingting Hu, Yi Wang, Sumi Helal
cs.AI · cs.DC
Large language model applications are increasingly being organized as tool-using and multi-agent workflows rather than as isolated chat interfaces. This perspective paper examines the architectural problem that follows from that shift: agents may reason, invoke tools, and delegate work, but dependable deployment still requires interoperability across frameworks, runtimes, data boundaries, and organizational control domains. We study this...
-
33
Networked AI: Architecture, Theory, and Applications
Liang Song, Jiayue Jin, Peng Sun, Di Li, Yang Liu, Athanassios Skodras, Dimitris Ampeliotis, Yong Yuan, Amit Dvir,...
cs.AI · cs.NI
Recent advances in Artificial Intelligence (AI), particularly large-scale deep learning, have been driven by monolithic or offline training on massive curated datasets. While successful, these approaches face structural limitations: escalating data and computational demands, limited online adaptability, and a lack of system-level intelligence in open, non-stationary environments. This paper presents Networked AI - a networked intelligent...
-
34
PRIME: Predictive Routing of Interventions by Modeling Effects for Scientific Ideation
Fengxian Ji, Xie Yu, Zhexuan Cui, Yuke Li, Zirui Song, Fan Zhang, Qian Jiang, Jingpu Yang, Xiuying Chen, Preslav...
cs.AI
Feedback-driven iteration is widely used to improve LLM-generated scientific ideas, but existing systems either leave revision decisions implicit in generation, align revisions with feedback-localized weaknesses, or restrict action selection to system-specific operations. This is problematic because problems, hypotheses, and solutions are interdependent: the location where a weakness manifests does not itself determine the revision scope that...
-
35
BLPO: Beyond-Local Policy Optimization for Long-Horizon LLM Agents
Xuanren Chen, Chongyang Tao, Wenpeng Hu, Yong Wang, Bo Deng, Xinlei Zheng, Shuai Ma
cs.AI
Long-horizon tasks require large language model (LLM) agents to coordinate interdependent actions, a capability central to automating complex workflows. Stepwise group-based reinforcement learning provides finer credit than trajectory-level supervision, but reliable comparisons must account for differences in interaction history. Enforcing this consistency within the limited rollouts of each task can leave insufficient support for estimating...
-
36
CAREFUL-Bench: Effect-Aware, Judge-Free Evaluation of Multi-Turn LLM Function Calling
Alexander Kovalenko, Artem Redchych
cs.AI · cs.SE
The multi-turn checker of the Berkeley Function Calling Leaderboard (BFCL) evaluates final state correctness but ignores the effects of intermediate calls: extra calls are free, function documentation does not describe side effects, and the scripted user never responds to proposals. Consequently, models asking for confirmation before destructive actions are penalized; 260 of 734 reference turns in the base category perform destructive actions...
-
37
Action Verification through Conjecture and Refutation for Language Model Agents
Minhyeon Oh, Chiyeong Heo, Geonwoo Noh, Hoyoung Kim, Jangwon Son, Jungseul Ok
cs.AI · cs.CL · cs.LG
Language model agents increasingly act on users' behalf by manipulating external environments through tools, often from high-level instructions that leave critical task- and environment-specific context unstated. To prevent resulting misaligned actions, recent work verifies proposed actions before execution, largely by establishing whether the conditions supporting them hold. We argue that this confirmation-oriented view leaves a fundamental...
-
38
Why Tabular Foundation Models Excel on Relational Data They Have Never Seen
Linjie Xu, Yiqun Hu, Jixiang He, David Wipf
cs.AI · cs.DB · cs.LG
Given a relational database (RDB) storing heterogeneous tabular information, how can we predict missing (or future) values in some target column of interest? As candidate targets are numerous in enterprise settings, it is preferable to avoid learning a new model from scratch each time there is a new prediction task. Frozen foundation models (FMs) based on in-context learning (ICL) and RDB-specific pre-training provide a viable solution, but...
-
39
User Attributes and Political Ideology Shape LLM Receptiveness in Online Political Debates
Akram Elbouanani, Yousra Taleb, Gianluca Demartini, Adrian Popescu
cs.AI · cs.CL
Online political discussions increasingly involve AI-mediated participation, as users invoke LLMs to assess contested claims, arbitrate disputes, and respond to opposing viewpoints. As these systems become participants in online exchanges, they may alter which speakers and argumentative strategies receive validation within the discussion. We study this interactional dimension by reconstructing 5,376 Debate.org debates as LLM conversations and...
-
40
What makes a theorem interesting? Operationalizing interestingness for open-ended exploration
Silvère Gangloff
cs.AI
An agent that explores, whether it generates conjectures or research ideas, must decide which of them are worth keeping. This judgment of interestingness is usually delegated to a hand-picked proxy or to a language model, neither of which is known to correspond to what humans actually value. I study it for mathematical theorems, by observing which results mathematicians single out in formal libraries and in papers. I model each way of...
-
41
Bridging Low-Level Image Fusion and High-Level Semantic Understanding
Guangyuan Dong, Lingdong Shen, Xudong Zhang, Haodong Jing, Haoyu Wang, Zihao Li, Zonghao Ying, Ziyu Song, Shenghao...
cs.AI · cs.IR
Remote sensing image fusion and semantic interpretation are usually optimized separately, so reconstruction quality need not preserve downstream retrieval utility. We propose LANCE, which uses structured language as an explicit, indexable semantic state. A frozen vision-language model maps the input to a closed-vocabulary text record; a language-conditioned generator fuses the imagery; and a dense verifier with a differentiable continuous...
-
42
JABER: Sequential Quality Control for Human-AI Data Annotation under Shared Bias
Fengxu Yang, Minghui Liwang, Yang Lu, Bo Han, Xianbin Wang, Seyyedali Hosseinalipour
cs.AI
High-quality annotations are essential for training and evaluating artificial intelligence (AI) systems. Quality control (QC) often acquires additional human or AI judgments before accepting a label. Nevertheless, shared biases can cause correlated judgments, leading conventional methods to mistake repeated agreement for independent evidence of correctness. To address this challenge, we propose JABER (Joint Alias-Preserving Belief for...
-
43
Integrating Domain Adaptation and Retrieval-Augmented Generation for Saline-Alkali Land Reclamation Planning
Zuguang He, Congcong Zheng, Wanyue Chen, Wenya Zhou, Zaijin Yang, Long Long, Yucheng Zhang, Shuqin Gao
cs.AI
Reclamation of saline-alkali land requires management plans that account for soil and water conditions, treatment evidence, and financial constraints. This study develops Wenyao, an agricultural decision-support system integrating domain adaptation with retrieval-augmented generation. A bilingual corpus of 8,664 research papers was processed using a 110-indicator schema to construct SA-Bench, comprising 4,860 paper-level planning instances. A...
-
44
Value-Conditioned Proposal Acquisition for Test-Time Reasoning
Zeyan Li, Jianfeng Xu
cs.AI
Sampling and selection spend test-time compute inside a candidate pool, but they cannot recover a correct answer that never enters it. We introduce ValueFormation, a test-time policy that decides after each primary-model draw whether to stop, continue sampling, or acquire one proposal from a heterogeneous reasoning specialist. The three actions are compared on one cost-regularized value scale learned from vote-state features; the calibration...
-
45
TLAPS-Bench: Formally Proving Correctness of Real-World System Specifications with TLA+ Proof System
Qian Cheng, Ruize Tang, Saad Mohammad Rafid Pial, Zhizhen Cathy Cai, Yiming Su, Jackson Clark, Munim Thahmid,...
cs.AI · cs.DC · cs.LO · cs.SE
TLAPS-Bench is a benchmark and execution harness for constructing machine-checked proofs for real-world system specifications in TLA+ with agentic AI. Proving correctness of complex system specifications requires discovering inductive invariants, reasoning about intricate state transitions, and decomposing proofs into tractable obligations. TLAPS-Bench provides a proof harness that supports iterative proof development atop the TLA+ Proof...
-
46
SpecOPD: Branch-Parallel On-Policy Distillation for Speculative Decoding
Tianyu Liu, Jun Zhang, Wenjie Huang, Yuhao Shen, Tianqi Xu, Xinyue Hao, Hongyaoxing Gu, Xuyang Liu, Baolin Zhang,...
cs.AI
Speculative decoding (SD) accelerates large language model inference by reducing the sequential cost of token-by-token generation. Advanced SD methods reduce proposal cost with parallel drafters that predict entire blocks in one forward pass, but overall speedup still depends on acceptance length. On-policy distillation (OPD) can push well-trained drafters beyond acceptance-length plateaus, yet conventional pipelines collect supervision...
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.