cs.AI · 2026-09-23 · No. 122
Artificial Intelligence, 2026-09-23.
45 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
45 entries-
01
CliffCompaction: Cost-Efficient Compaction for Long-Horizon Coding Agents
Trang Nguyen, Eulrang Cho, Bingqing Chen, Tim Dettmers
cs.AI · cs.LG · cs.SE
Agents often work on complex problems that require millions of tokens of context, which necessitates compacting across sessions due to limited context windows. We develop CliffCompaction, an autocompaction technique that reduces cost by up to 50% under a bounded context while maintaining or improving performance on Terminal-Bench and achieving new levels of efficiency for test-time scaling and state-of-the-art results on KernelBench. The...
-
02
SWE-Serve: Benchmarking Agentic Engineering For Production Inference Serving
Jennifer Williams, Dave Farris, Jeff Farris, Jiantao Jiao
cs.AI · cs.SE
We introduce SWE-Serve, a benchmark for evaluating agents on production inference engineering tasks. Implementing an inference feature can require coordinating multiple changes across the serving stack, including model support, runtime execution, and public APIs. Existing benchmarks provide limited coverage of production inference engineering: repository-level software engineering benchmarks do not target inference, while general...
-
03
Grow the Harness, Not the Context: From Strategy-Free Scaffolds to Reusable Specialist Agents
Laizhen Li, Jiarui Li, Juanjuan Zhao, Kejiang Ye, Ye Li, Cheng-zhong Xu, Xitong Gao
cs.AI · cs.SE
Large language model (LLM) agents often handle streams of related tasks, yet standard harnesses repeatedly ask the model to reconstruct the same control decisions inside each task's context. We study whether task feedback can instead turn recurring control into reusable executable code, while reserving LLM calls for task-specific semantic reasoning. We introduce Growing Harness, a failure-guided training paradigm that learns the agent harness...
-
04
Type-Safe Is Not Error-Free: A Constrained Decision Head Follows the Option Name, Not the Rubric Bound to It
Yu Sun, Junhao Xu
cs.AI
Typed decision models are built for settings where model outputs are consumed directly by software. Instead of generating free-form text, they return a decision over a predefined set of options. By construction, every output conforms to the required schema. Yet this guarantee does not tell us whether the model interprets the options as intended. We study Jev and two Jev-like models with open weights by changing how option names are assigned...
-
05
The Delegation Blind Spot: Auditing Product Decisions from Agent Choices
Shivam Gupta
cs.AI · cs.LG
Successful agent execution need not identify which future product improvement its user would value. We present a decision-specific audit that maps a declared observation channel and product-value contrast to compatible intervals and witness populations. Its foundations are established identification and decision theory; the contribution is an executable measurement workflow and a controlled study of its limits. A frozen experiment makes 4,800...
-
06
Quantum-Aided Active Device Detection in Energy-Harvesting Symbiotic Radio Networks
Remon Polus, Deemah Tashman, Soumaya Cherkaoui
cs.AI
Massive connectivity in next-generation networks demands energy- and spectrum-efficient solutions for large-scale Internet of Things (IoT) deployments. Symbiotic radio (SR) enables passive IoT devices to communicate by backscattering existing cellular transmissions. A key challenge in uplink SR is active device detection (ADD), which directly affects decoding reliability, interference management, and system throughput. We propose an...
-
07
Neutral-Atom-based Quantum Optimization for Resource Allocation in NOMA Networks
Patatchona Keyela, Remon Polus, Soumaya Cherkaoui, Ola Ahmad
cs.AI · cs.IT
In wireless communication networks, many resource optimization problems are nondeterministic polynomial-time hard (NP-hard) due to their combinatorial nature and high computational complexity. Recently, neutral-atom-based quantum computing has emerged as a promising platform for efficiently solving such problems by leveraging quantum superposition and entanglement. However, its application to wireless communication optimization problems...
-
08
JEV-as-a-Judge: Accept When Confident, Escalate When Unsure
Yubo Li, Yidi Miao, Ramayya Krishnan, Rema Padman
cs.AI
LLM-as-a-judge enables evaluation across diverse tasks, but inference cost and confidence reliability become critical at scale. We study whether a decision-only judge can provide an economical first pass and identify when stronger evaluation is needed. Comparing jev-as-a-judge with sixteen generative and reward-model judges, with blinded human adjudication, we find it within three percentage points of a state-of-the-art LLM judge, our...
-
09
REFLEX with Jev for Efficient Selective Control in LLM Agents
Tiantong Wu, Wei Yang Bryan Lim
cs.AI
LLM agents often use generative models for bounded decisions, raising the question of when these decisions can be handled more efficiently without reducing task success. We study REFLEX, an agent architecture that uses Jev as a fast, typed decision layer and calls a strong LLM when confidence is low, or generation is required. On a frozen 100-task benchmark, REFLEX achieves 95% success with 72.7% fewer strong-model calls than a strong-only...
-
10
Reproducible AI Requires Reproducible Randomness
Anthony Bertrand, Tom Schmitt, Engelbert Mephu Nguifo, David Hill
cs.AI
Pseudorandom number generators (PRNGs) constitute indispensable computational tools across multiple scientific domains, including Monte Carlo simulations, stochastic computing, and artificial intelligence (AI). The reproducibility of such applications critically depends on the ability of PRNG implementations to generate identical sequences across software environments when initialized from the same internal state. These algorithms enable the...
-
11
Recursive self-improvement of AI research agents
Dhruv Srikanth, Bingchen Zhao, Dixing Xu, Yuxiang Wu, Zhengyao Jiang
cs.AI · cs.LG · cs.SE
AI agents are beginning to automate research and development across the AI stack, from improving training efficiency to optimizing inference. A natural next step is to improve the research efficiency of the agents themselves. When an AI research agent's own code is the object of optimization, each accepted rewrite becomes the agent that the next round edits. We refer to this loop as recursive self-improvement. Its significance lies in a...
-
12
The Source of Disturbance Matters: External, Internal, and Control-Generated Noise in Adaptive Regulation
Veronique Ziegler
cs.AI · eess.SY · nlin.AO
Adaptive regulation can itself perturb the state it is intended to stabilize. In replicated simulations of an adaptive agent, we compare external disturbance, persistent internally generated disturbance, and control-generated disturbance under regulation-first and disturbance-first ordering. Persistent internal disturbance produces the largest exposure and regulatory burden within the tested parameter grid. When positive controller updates...
-
13
Reliability Theory for AI Control
Grant Molnar
cs.AI · math.OC
Reliability theory gives a mature language for layered systems, but its formal tools are not yet standard in frontier AI control. We apply them to Google DeepMind's defenses against rogue deployment. The same control stack can have cubic, quadratic, or linear rare-failure suppression depending on its failure domains. Birnbaum importance identifies which component improvements buy the most nominal reliability, while prevention changes the...
-
14
Dual-Frontier: When Can an Agent Trust Its World Model?
Huatai Zhu, Qiang Chen, Ziqian Kou, Wenhao Li, Fei Wang, Yichao Cao, Xiu Su, Yi Chen
cs.AI
Learned world models are becoming essential to general-purpose agents: by predicting action consequences, they support planning and decision-making while reducing reliance on costly trial and error. This reliance creates a fundamental ambiguity: when a world-model-guided decision fails, the trajectory alone may not reveal whether the agent's decision rule or the world model caused the loss. We formalize this failure-attribution problem as a...
-
15
EADC: Evaluation of Advanced and Deep-level Compliance in Large Language Models
Yan Zhang, Ruien Li, Yaoyao Peng, Wanxin Ren, Yijia Zhang, Wusheng Zhang, Guangwen Yang
cs.AI
Large Language Models (LLMs) have been used in various industries. However, ensuring their compliance with complex laws and regulatory frameworks remains a great challenge. Existing evaluation paradigms mainly rely on static benchmarks that suffer from three severe limitations: First, the compliance rules being used do not comply with the requirements of Artificial Intelligence (AI) laws and regulations; Second, they only handle apparent,...
-
16
FIRE: Failure-Informed Runtime Engineering for Reliable Language-Model Agents
Nikita Agarwal, Nivedit Jain
cs.AI · cs.CL · cs.SE
Language-model agents often reach a working solution and then fail to consistently deliver it. We study runtime policies: targeted natural-language instructions and action denials applied by the agent harness at states that preceded observed failures, without changing model weights or the user prompt. With this, keeping capability constant, we observe a meaningful unlock in delivered reliability. Across the complete 87-task Terminal-Bench 2.1...
-
17
Canonical locks that encode part-whole hierarchies
Rajat Modi, Yogesh Singh Rawat
cs.AI
One of the challenges in representational learning is how to encode part-whole hierarchies in a neural net. Prior works rely on flattening tree-like structures into string-like sequences and training a sequence-to-sequence model via autoregression. While such a representation works for parse-trees in NLP, it is not entirely clear how to make it work for images. Thus, we propose a geometric primitive called canonical locks. The key idea is...
-
18
CQ4OE: A benchmark for assessing LLM-assisted ontology generation from competency questions
Jiayi Li, Ziyuan Wang, Daniel Garijo, María Poveda-Villalón
cs.AI
Ontology generation from Competency Questions (CQs) is a central yet labor-intensive phase of Ontology Engineering. While large language models (LLMs) offer promising automation capabilities, current evaluations remain fragmented. Task formulations are heterogeneous, gold standards often lack fine-grained CQ provenance, metrics conflate lexical overlap with structural and logical adequacy, and reference ontologies are not always explicitly...
-
19
VideoX-Qwen: Data-Centric Instruction-Based Video Editing
JJiahang Li, Dingbao Shao, Xinyu Chen, Song Wu, Jiang Lin, Duo Li, Yuhang Liu, Jiaxin Hu, Shengrong Gu, Ying Tai, Zili Yi
cs.AI · cs.GR
Progress in general-purpose video editing depends on constructing large-scale paired supervision and effectively adapting video-generation backbones to instruction-driven editing. Unlike video generation, video editing must execute a requested transformation while preserving unrelated subjects, scene structure, motion, and temporal continuity. We present VideoX-Qwen, an integrated data-construction and model-training framework for general...
-
20
CausalLoss-Fin: Attributing Financial-Agent Loss to Decisions and Infrastructure Faults
Abhishek Sharma
cs.AI
When an agent handling a payment exception loses money, the agent-step attribution methods this paper compares against will name one of its actions. They will do so even when a settlement message was dropped and the agent never had a chance: they intervene on agent actions and do not expose infrastructure faults as intervenable variables, so every dollar they explain is charged to a decision. We take a benchmark whose fault process is...
-
21
AgenticSizing: A Large Language Model-based Multi-Agent Framework for Analog Circuit Sizing
Yijia Hao, Pratibha Verma, Dongxu Guo, Cristian Sestito, Michael O'Boyle, Christos-Savvas Bouganis, Themis Prodromakis
cs.AI · cs.AR
Analog circuit sizing remains a challenging and time-consuming task due to the large design space, strong performance trade-offs, and increasing circuit complexity in scaled technologies. Although recent large language model (LLM)-based methods show promise in improving sample efficiency and interpretability, existing approaches often lack explicit circuit-topology understanding and are mainly evaluated on relatively simple analog building...
-
22
Prediction Is Not Detection: Evaluating Pre-Recognition Claims in Longitudinal Clinical AI
Jing Yang, Long R. Jiao, Xiujun Cai, Zongjiu Zhang
cs.AI
Clinically useful early detection requires validated pre-recognition lead time. Yet event-based evaluations of longitudinal clinical AI can treat recognition-mediated care-process signals as shortcuts and recognition-dependent endpoints as reference standards, inflating apparent performance and lead time while undermining cross-center transport. Such results may serve prognosis without establishing detection before recognition. We define an...
-
23
Optimizing the Score, Losing Sight of the Task: Reward Hacking Across Weights, Selection, and Prompts
Vansh Wahi
cs.AI
A higher evaluation score does not always mean a better language model system. When optimization exploits an evaluator's mistakes, measured progress can conceal unchanged or deteriorating task performance. This failure can arise through parameter updates, selection among generated outputs, or revisions to persistent prompts. We develop a comparative framework for reward hacking across these three optimization substrates: weights, selection,...
-
24
When Are Aggregate Agent Traces Diagnosable? Traffic-Governed Interpretation and Calibrated Abstention
Peiying Zhu, Sidi Chang
cs.AI
Runtime traces can appear transparent, but a closed-loop policy determines which states are visited and which failures become visible. We study a simulated hotel-pricing agent mapping time, inventory, and market state to discrete price actions under varying demand regimes. A fault may leave no aggregate trace when the policy rarely visits affected cells. We treat entry into aggregate-only fault interpretation as a diagnosability decision...
-
25
The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks
Wenbo Pan, Zhichao Liu, Shujie Liu, Jingying Zeng, Chin-Yew Lin, Xianfeng Tang, Yan Lu, Qi He, Xiaohua Jia
cs.AI
LLM agents increasingly work on long-horizon tasks, and the decisions they make along the way, such as which hypothesis to test or which implementation to build on, determine the outcome of the whole run. Making these decisions well is becoming a key capability for both engineering and research agents. We refer to the ability to make good long-horizon decisions as the taste of an agent. While existing benchmarks measure the end-to-end success...
-
26
Towards Omni-dimensional GUI Agent Navigation with Masked Trajectory Prediction
Yan Zhang, Pei Fu, Daiqing Wu, Huawen Shen, Ruoceng Zhang, Shaojie Zhang, Jiahui Yang, Yu Zhou, Can Ma, Zhenbo Luo, Jian Luan
cs.AI
Graphical User Interface (GUI) Agents autonomously interact with software to fulfill user requests, where GUI navigation stands out as the most critical and challenging capability. Mastering this capability demands a complex synergy of step-wise decision-making, state-action alignment, and long-horizon planning. While directly mixing these corresponding navigation tasks seems intuitive to simultaneously acquire these skills, such a direct...
-
27
Neurosymbolic Action Model Learning under Partial Observability
Adem Kikaj, Lennert De Smet, Giuseppe Marra, Luc De Raedt
cs.AI
AI planning studies how an agent can reach a goal by executing a sequence of actions. To plan correctly, the agent needs an action model describing when each action can be executed and how it changes the world. Constructing such models by hand requires domain expertise, and can be costly and error-prone. Action models can instead be learned from available data using existing neurosymbolic approaches, but they currently assume access to...
-
28
The Limits of Simulated Societies: How Post-Training and Survey Fine-Tuning Erase Cross-Cultural Variance
Rojin Ziaei
cs.AI
Using large language models (LLMs) to simulate diverse human populations has the potential to transform many aspects of computational social science, yet many evaluations score the average response rather than the spread of opinion within real groups. Here, we develop a diagnostic framework that measures point accuracy alongside dispersion retention, the ratio of predicted to human standard deviation ($\dr$), on 10{,}000 respondent--question...
-
29
OmniFysics-Nano-V2 Technical Report: Understanding the Physical World Across Modalities
Yizhou Liu, Jinghang Han, Kaixiang Qiu, Qi He, Minghao Han, Yue Jiang, Xujia Chen, Wei Zou, Shunli Wang, Lihua...
cs.AI
Omni-modal models have expanded multimodal interaction across vision, audio, speech, and language. However, their training is predominantly organized around semantic descriptions and general-purpose objectives, leaving physical attributes, interaction states, and causal mechanisms only partially specified. This gap is not simply a matter of modality coverage: adding more modalities does not by itself provide the supervision needed to connect...
-
30
LingLan: An Advancing Traditional Chinese Medicine Diagnosis LLM with Multimodal Data
Zheng Chen, Zhicheng Du, Haoxuan Li, Yingshan Liang, Peiwu Qin
cs.AI
Though artificial intelligence (AI) increasingly transforms modern medicine, its integration into Traditional Chinese Medicine (TCM) has been relatively slow, primarily due to TCM's reliance on holistic, subjective diagnostic methods---namely Inspection, Auscultation and Olfaction, Inquiry, and Palpation(I-AOI-P)---which are difficult to align with quantitative, standardized medical systems. In this work, we introduce a Unification Framework...
-
31
TCMaster: Confidence-Aware Querying and Workload-Guided Physical Design for Multi-Source Traditional Chinese Medicine Knowledge Graphs
Zheng Chen, Yuzhu Li, Haoxuan Li, Zhongde Zhang, Lianshun Jin, Peiwu Qin
cs.AI
Multi-source knowledge graphs (KGs) need query mechanisms that expose reliability and exploit domain structure. This paper presents TCMaster, a property-graph query substrate for confidence-aware traversal and workload-guided physical design over Traditional Chinese Medicine KGs. TCMaster integrates pharmacopoeias, prescriptions, molecular databases, and LLM-extracted micro-semantics into a KG with approximately 221K entities and 723K base...
-
32
How Strongly Should Task State Influence an LLM Agent?
Chenyu Zhang, Wonbin Kweon, Jiawei Han
cs.AI · cs.CL · cs.LG
Long-horizon assigned work requires an LLM agent to track the state of a task: which steps are done, blocked, cancelled, or open to repetition. Agent systems either keep this state as text in the prompt and rely on the model to read that text, or move the state into a module that enforces it, and each system is evaluated as a whole, so no one knows how much reliability comes from the state being shown, told, or enforced. We fix the task...
-
33
Toolcompass: Guiding Tool Trialing, Not Suppressing It
Junlin Fang, Chong Zhang, Do Nguyen-Thanh, Xiaogang Xu, Zhen Fang, Sean Du
cs.AI · cs.LG
Large language model (LLM) agents must generalize from tools seen during training to unseen tools at deployment. A key challenge is tool trialing, i.e., excessive trials waste the interaction budget, whereas selective trials enable exploration of unfamiliar tools. Existing outcome-based post-training leaves wasteful trials unguided, while turn-level supervision may suppress necessary exploration. We introduce ToolCompass, a post-training...
-
34
Seeing Is Not Perceiving: When Synthetic Consumers Can and Cannot Pretest Visual Marketing
Yi-Lin Tsai, Yung-Hsiu, Lai
cs.AI · cs.CY · econ.GN
Marketers now deploy generative AI agents as synthetic consumers to pretest visual assets such as logos, packaging, and advertising at a fraction of human-panel cost. However, this procedure assumes that a model seeing a visual cue can also perceive its consumer meaning, which is largely untested. We stress-test the assumption using six canonical visual marketing experiments, varying the two levers managers control: model generation...
-
35
Testing-Driven Reliability Audit of Trajectory-Based Early Outcome Prediction for LLM Agents: Target-Specific Calibration Transfer Persists Within a Single Benchmark
YanZe Cao
cs.AI
Predicting early outcomes based on trajectory can decrease the expenses associated with agent evaluation by terminating a run once the outcome becomes sufficiently predictable, assuming that the predictor's confidence is properly calibrated. Calibration is at risk when a predictor is applied to an agent on which it was never trained, but it is not known whether such transfer failures are broad across agent systems or concentrated in specific...
-
36
Ladders of Thought: A Self-Evolving Curriculum of Progressively Simplified Reasoning Traces
Minghui Liu, Thomas Magelinski, Dehao Yuan, Qi Yu, Furong Huang
cs.AI · cs.LG
Large language models (LLMs) excel at reasoning when scaled to hundreds of billions of parameters, but small- and mid-scale models remain brittle reasoners even with knowledge distillation (KD). We present Ladders-of-Thought (LoT), a framework that improves reasoning by combining progressive question rewrites with a self-evolving curriculum. LoT automatically generates semantically faithful but easier variants of reasoning problems, organizes...
-
37
ChatT2: An Adaptive Framework for Developing a Large Language Model-Based Agent for Natural Product Domain Research
Yihan Wang, Qiandi Gao, Yihui Zhuang, Liangjun Ge, Heqian Zhang, Jiaquan Huang, Zhiwei Qin
cs.AI
Scientific investigations into microbial natural products (NPs) present significant challenges for novices, largely due to the complexity of microbial systems, biochemical diversity, technical skill requirements, and the demands of bioinformatics and data analysis processes. To address these issues, we introduce ChatT2, a large language model (LLM)-based agent that is specifically tailored to the unique characteristics of bacterial type II...
-
38
Reasoning-Preserving Fine-Tuning of Post-RL LLMs with Null-Basis LoRA
Wenzhi Fang, Nicholas Tzou, Lazar Valkov, Srinivas Chappidi
cs.AI
Reinforcement learning (RL)-based post-training has become an effective approach for eliciting reasoning capabilities in large language models (LLMs). However, adapting post-RL models to new knowledge domains or behaviors through subsequent supervised fine-tuning (SFT) can severely overwrite these capabilities. Existing approaches mitigate such forgetting through experience replay, specialized initialization, or constrained optimization using...
-
39
ArticleMiner: Ontology-Guided Knowledge Graph Construction from Scientific Publications
Md Abrar Jahin, Craig A. Knoblock, Jay Pujara
cs.AI
Scientific papers keep much of their quantitative content in tables and supplementary files, where a number means something only through its header, caption, unit, analytical method, and the conventions of its field. Recovering the rows and columns of a table is therefore not the same as recovering the scientific fact it reports. Most semantic table-interpretation methods assume that a clean table is already available and subsequently map its...
-
40
Evaluating Coding Agents on Kernel Exploit Generation
Junyoung Jang, Gwanhyun Lee, Hwiwon Lee, Kyuheon Kim, Jongseong Kim, Jinho Jung, Lingming Zhang
cs.AI · cs.CR
Coding agents now find real vulnerabilities in production software. However, bug discovery results do not measure whether agents can construct exploit primitives. We introduce KEX-bench, a benchmark for evaluating coding agents on exploit primitive generation against real operating-system kernels. KEX-bench contains 45 task instances across 40 Linux and Windows CVEs, covering kernel address leak, instruction-pointer control, heap read, heap...
-
41
Transformer Heads Looking for Order
Jasper van Doornmalen, Alexander Kozachinskiy, Corinna Mathwieser, Tomasz Steifer, Felipe Urrutia, José Verschae,...
cs.AI · cs.LG
In this note, we show that the problem of checking, whether a sequence of bits is ordered, is not doable by 1-head 1-layer transformers but is doable by a 2-head 1-layer transformer. Unlike similar previous results, our results assume the model where transformers have an output MLP.
-
42
Gaze responses to false-positive computer-aided detection prompts during colonoscopy: a paired-video and real-time eye-tracking study
Te Luo, Yan Zhu, Peiyao Fu, Ruijie Yang, Xian Yang, Quanlin Li, Pinghong Zhou, Shuo Wang
cs.AI
False-positive computer-aided detection (CADe) prompts may divert endoscopists' attention during colonoscopy, yet the attentional impact of individual prompts remains unclear. We used event-locked eye tracking to quantify gaze attraction and attention occupation in complementary retrospective and prospective studies. In a retrospective paired-video experiment, 3 senior and 2 novice endoscopists viewed 60 colonoscopy videos with and without...
-
43
Direct Optimization of Generators for Search in Automated Theorem Proving
Adam Ousherovitch, Ambuj Tewari
cs.AI · stat.ML
Fine-tuned Large Language Models (LLMs) significantly advance Automated Theorem Proving (ATP), but are often deployed as guiding policies within tree search rather than for single-attempt generation. Recent work shows cross entropy is suboptimal for an LLM used in flat search strategies such as aggregation or filtering and that work has developed new loss functions to correct this misalignment. Extending this alignment to tree search is more...
-
44
A Behavioral Trait Leaks into Preferences: Diagnosing Trait Interference in LLM User Simulators
Chaehyun Kim, Sein Kim, Hongseok Kang, Chanyoung Park
cs.AI
LLM-based user simulators aim to bridge the offline-online gap in recommender evaluation by emulating users through injected traits, where preference attributes determine what a user engages with and a behavioral activity trait governs how long they browse. However, we show this intended trait independence collapses during simulation, causing two failures: (i) Trait Interference, where amplified activity distorts preference boundaries and...
-
45
Recovering Agentic Sovereignty: Mitigating the Consensus Paradox via Contrastive Epistemic Decoding
Dahlia Shehata, Ming Li
cs.AI
Large language models (LLMs) exhibit a parametric vulnerability to adversarial swarm consensus. To mitigate this sycophancy, we introduce Contrastive Epistemic Decoding (CED), a zero-shot inference intervention. Unlike standard Contrastive Decoding (CD) which relies on a weaker secondary model, CED utilizes a dual forward-pass on a single architecture to isolate conformity bias. By introducing a novel asymmetric, zero-bounded probability...
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.