cs.AI · 2026-09-22 · No. 121
Artificial Intelligence, 2026-09-22.
41 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
41 entries-
01
Harness-Zero: Harness Distillation via Agent-as-Harness
Haoran Ye, Yuxing Lu, Haonan Dong, Zhaochen Su, Guojie Song
cs.AI · cs.CL · cs.NE
Agent harnesses, the external systems that mediate model-environment interaction, can substantially improve agent performance, but their gains remain tied to the harness at deployment. Because the best harness varies across domains, instances, and models, a general-purpose agent must either settle for a suboptimal shared harness or route among an ever-growing set of specialized ones. We therefore study agent harness distillation: using a...
-
02
Emergent Collusion in Long-Horizon LLM Agent Interaction
Xinrui Shi, Yanzhe Zhang, Diyi Yang
cs.AI · cs.CL
LLM agents are increasingly deployed in collaborative settings, yet long-term interaction may give rise to undesirable coordination. We study the emergence of collusion in a long-horizon multi-agent environment: two agents repeatedly complete individual tasks, share task logs, verify each other's work, and receive rewards. We introduce realistic constraints that make compliance with the verification protocol incompatible with reward...
-
03
Et Tu, Brute? Economic Misalignment in Personal AI Agents
Aman Priyanshu, Supriti Vijay, Brian Jabarian, Niloofar Mireshghallah
cs.AI
Personal AI agents make recommendations and take actions on people's behalf in high-stakes economic contexts, e.g., buying a flight, choosing health insurance, or selecting a graduate program. The agent is given access to the user's personal context, e.g., their email inbox and a structured profile of personal attributes, with the intention of making an optimal, personalized decision for the user. We show that by simply providing this...
-
04
BackTrend: Evaluating Scientific Weak-Signal Prediction via Backward Reconstruction
Xiao Zhou, Yilun Zhao, Owen Jiang, Tiansheng Hu, Cai Xu, Manasi Patwardhan, Arman Cohan
cs.AI
Scientific weak signals are early, low-visibility research directions that later become central to mature scientific topics, yet existing resources such as trend tracking, citation forecasting, and foresight reports rarely provide validated reference sets that link concrete early precursors to later paradigms. We introduce BackTrend, a retrospective benchmark in which, given a mature target topic and a temporal evidence constraint, systems...
-
05
A Global Comparison of Schemas, Transparency, and Interoperability in Public-Sector AI Registers and Inventories
Dipto Das, Shion Guha
cs.AI · cs.CY · cs.HC
Artificial intelligence (AI) registers and inventories aim to make governmental AI visible, but their institutional scope, schemas, and reporting practices construct different representations of public-sector AI. We compare 8,368 records from country-specific and transnational inventories covering 72 countries. Across 23 harmonized fields, registers shared a descriptive core but rarely requested information about appeals, risks, legal bases,...
-
06
Pinocchio: Fast Uncertainty Estimates for Black-Box Language Models
Kevin David Hayes, Arka Pal, Haosong Zhang, Tom Goldstein, Micah Goldblum
cs.AI
In high-stakes decision-making applications of large language models (LLMs), practitioners require not only accurate LLMs but also uncertainty estimates for their predictions. Existing approaches to uncertainty estimation for LLMs require access to log-probabilities output by the model or require fine-tuning access. However, many industrial LLM products use closed-source API models, and many such API models like GPT do not return...
-
07
Partner-Specific Affective Precision in Social Active Inference
Harshil Shah, Andrew Pashea
cs.AI
In multi-agent social settings, model reliability varies across relationships. Beyond inferring what others will do, an agent must calibrate how confidently those inferences should guide policy selection for each relationship. An agent may maintain a well-validated model of one partner, a fragile model of another, and a model under revision for a third; collapsing these into a single confidence estimate loses information relevant to policy...
-
08
Extracting Arguments, Not Just Classifying Them: Instruction-Tuned LLMs for Generative Component Detection
Sofiane Elguendouze, Erwan Hain, Elena Cabrio, Serena Villata
cs.AI · cs.CL
Argumentative component detection (ACD) is a core subtask of Argument(ation) Mining (AM) and one of its most challenging aspects, as it requires jointly delimiting argumentative spans and classifying them into components such as claims and premises. While research on this subtask remains relatively limited compared to other AM tasks, most existing approaches formulate it as a simplified sequence labeling problem, component classification, or...
-
09
MedRSI: Recursive Self-Improvement for Medical Agents via Clinically Aligned Self-Evolution
Junde Wu, Jiayuan Zhu, Minghao Hu, Fenglin Liu, Jiazhen Pan
cs.AI
Medical agents increasingly combine general reasoning models with specialized clinical tools, yet their capabilities remain largely fixed by what clinicians and engineers design before deployment. Recursive self-improvement (RSI) offers a different paradigm in which agents learn from their own failures and autonomously expand their capabilities, but directly applying RSI to medicine introduces fundamental safety challenges. We introduce...
-
10
GRUET: Quantifying Uncertainty of Agentic Reasoning-and-Acting Processes
Shuang Liang, Xin-Yu Hu, Shao-Qun Zhang
cs.AI
Agents have attracted considerably increasing attention due to the power of executing both Reasoning and Acting (ReAct) in open and dynamic environments. The ReAct process typically exhibits a multi-turn trajectory in which one drives Large Language Models (LLMs) to generate both reasoning chains and task-specific actions in an interleaved manner. However, agents often suffer from significant uncertainty, where identical tasks yield divergent...
-
11
Convex AI Compositionality and the Governance of AI System Populations
Andrea Ferrario
cs.AI · cs.CY
AI governance increasingly requires providers and public authorities to reason about multiple AI instantiations, alternative versions, and deployment configurations of multiple AI systems. Yet current regulation remains predominantly single-system-centric, acknowledging such multiplicity only sparsely without treating collections of related AI systems as governance objects. This creates an AI population governance problem: determining which...
-
12
Construting Reverse Thinking: Developing Large Language Models' Reverse Thingking Ability
Xin Liu, Yunhai Li, Chunfu Jia, Ziliang Chen, Jisen Song
cs.AI
When facing complex problems, humans tend to try various ideas for different issues. Human thinking patterns exhibit remarkable flexibility in adapting to diverse scenarios. GPT-o1, GPT-o3, and DeepSeek-R1 adopt long chain-of-thought models to address complex problems by increasing reasoning depth, which default to a forward reasoning mode. We conducted statistical analysis on the accuracy of different mathematical problem datasets on models...
-
13
Epi-Logic: A Conceptual Framework for Epistemic Runtime Control, Schema Validity Checking, and Controlled Accommodation in Autonomous AI Agents
Boris Wetzk
cs.AI
Autonomous AI agents are increasingly deployed in areas where wrong decisions are hard to reverse. This paper examines schema mismatch: the condition in which an agent operates within an interpretive frame that no longer applies to the current context. Outputs produced under such a mismatch can appear internally consistent, linguistically plausible, and largely factually correct; output-quality metrics alone therefore capture the underlying...
-
14
World State Generator
Sungheon Jeong, Sanggeon Yun, Ryozo Masukawa, Haleh Alimohamadi, Mahdi Imani, Mohsen Imani
cs.AI
Language agents solve complex tasks through plans and actions. A single step the world refuses puts the goal out of reach, and what the agent does next decides the task. Prompted planners fail at exactly this point, rewriting the refused step in new words, meeting the same refusal, and burning the attempt budget without moving. They fail because the plan was never tied to the world, so a refusal has nothing in the plan to attach to. A world...
-
15
TimeLitmus: A Diagnostic Benchmark for Cross-Modal Understanding and Explanation Faithfulness in Event-Conditioned Time-Series Prediction
Jie Gong, Maowei Jiang, Zhiwei Liu, Yankai Chen, Guojun Xiong, Xue Liu, Min Peng, Qianqian Xie, Sophia Ananiadou
cs.AI
Large language models (LLMs) are increasingly used to make predictions from numerical time-series histories and textual events. Yet accuracy alone cannot reveal whether correct answers reflect effective integration of the two inputs or instead arise from event polarity, unimodal priors, or superficial cues. Likewise, plausible explanations may rationalize predictions without faithfully reflecting the evidence that drives model behavior. We...
-
16
Beyond Endpoint Performance: Process-Level Evaluation of Self-Evolving Agents
Hongqiang Lin, Chao Liu, Xiaofan Bai, Xuan Jin, Yuhong Li, Nenggan Zheng, Xipeng Cao
cs.AI
Self-evolving agents convert interaction feedback into persistent artifacts, such as memories or skills, which in turn guide subsequent decisions. As these artifacts are iteratively updated throughout an experience stream, the capabilities they support may evolve. Consequently, endpoint performance alone offers an incomplete view of self-evolution. Process-level evaluation is therefore essential to identify when a target capability emerges...
-
17
DUMA-Bench: A Dual-Control Multi-Agent Benchmark for Evaluating LLM Agent Security
Ivan Aleksandrov, German Kochnev, Sabrina Sadiekh, Yaroslav Rogoza
cs.AI
LLM-based agents increasingly operate in environments where they interact with users, tools, and external systems. Yet most security evaluations assume passive users and static control, ignoring the interactive dynamics that shape real agent behavior. We introduce \textbf{DUMA-Bench}, a benchmark and evaluation protocol for measuring agent security under \emph{dual-control} interaction, where both the agent and the user can influence the...
-
18
Custom Named Entity Recognition and Topic Classification for Global Health Publications
Genis Skura, Antoine Geissbühler, Jean-Luc Falcone
cs.AI · cs.CL
How should natural language processing models be selected and adapted for global health literature in environments where annotated data and computational resources are limited? This thesis investigates these challenges through experiments on semantic tag discovery, named entity recognition (NER), and multi-label topic classification. First, skip-gram word2vec models trained on progressively larger specialized corpora are compared with...
-
19
Ascent: An Agentic System over the Model Context Protocol for Real-World Clinical Data Analysis
Angelo Ziletti, Leonardo D'Ambrosi, Melanie Tuchardt, Tim Kondziella
cs.AI · cs.IR
Answering epidemiological questions from real-world clinical data requires medical coding, schema-aware SQL, and validation of implicit choices about populations, denominators, and time. We present Ascent, an agentic system that exposes medical coding, question answering, and cohort analysis through a shared Model Context Protocol tool surface for standardized and native schemas. We introduce EpiTrap, a dataset testing whether systems avoid...
-
20
The Endless Exam: Mathematical Constructions from Today's Models toward Superintelligence
Muhan Zhang
cs.AI · math.HO
We introduce the Endless Exam, a benchmark for measuring mathematical progress from today's models toward artificial superintelligence through fourteen parameterised construction families. Each submitted object is checked automatically for validity and assigned a relative quality score against a published frontier or construction baseline, without capping improvements at $1$. The families draw on open mathematical problems for long-term...
-
21
Not All Task Vectors Need Equal Rank: Energy-Proportional Allocation for Model Merging
Hyunjoong Cho, Jinhyeok Jang
cs.AI · cs.CV · cs.LG
Model merging aims to combine multiple fine-tuned models derived from a common pretrained model into a single multi-task model without additional joint training. Recent spectral merging methods improve over simple weight averaging by exploiting low-rank structures of task-specific updates, but they commonly assign the same rank capacity to every task. This uniform allocation ignores that task vectors can have heterogeneous spectral...
-
22
Fathom-Vaidya: Advancing Medical Reasoning with Rubric-Based Rewards
Kalash Shah, Kunal Singh, Snehan J, Shreyas Singh
cs.AI · cs.CL · cs.LG
Deploying Large Language Models (LLMs) in healthcare requires robust performance across two complementary dimensions - diagnostic reasoning: the convergent, evidence-driven task of inferring a patient's condition from clinical data to produce a diagnosis, and clinical healthcare reasoning: the broader, navigational judgment required to communicate, plan, and adapt across multi-turn clinical interactions where a single correct answer may not...
-
23
Predicting Postprandial Glycemic Response from Meal Images, Clinical Variables, and Gut Microbiome Information
Varvara Kondratyeva, Kamilia Zaripova, Nassir Navab, Azade Farshad
cs.AI
Predicting postprandial glycemic response (PPGR) is fundamental to personalized nutrition and type 2 diabetes management, yet existing approaches typically rely on manually reported dietary intake, limiting their scalability in free-living settings. We propose a multimodal framework that replaces manual dietary logging with image-derived macronutrient estimates and integrates them with clinical variables and gut microbiome information for...
-
24
VLM-in-Sandbox: Visual Workspaces for Agentic Visual Reasoning
Hexiong Yang, Mingrui Chen, Jie Cao, Ran He
cs.AI
Sandboxed computer environments support multi-step reasoning with tools, executable programs, and persistent files, yet their extension from language models to vision-language models (VLMs) introduces a distinct state-management problem. Visual reasoning produces intermediate image-valued evidence---crops, masks, overlays, zoomed regions, and analytic renderings---that must remain addressable without accumulating unboundedly in multimodal...
-
25
Few-Shot Demonstrations Elicit the Use of In-Context World Representations in LLMs
Kohsei Matsutani, Gouki Minegishi, Core Francisco Park, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo
cs.AI
Large language models (LLMs), when acting as agents, are expected to take observed data in context, infer the latent state space underlying the world, and leverage it for downstream prediction. However, prior work demonstrated that LLMs struggle to use representations learned in context on a graph tracking task, where the model needs to construct a representation of the graph governing data generation process and use it for subsequent...
-
26
LADDER: Graph-Guided Diffusion Language Models for Efficient Multi-Hop Reasoning
Senlei Zhang, Linhao Luo, Qian-Wen Zhang, Siyu An, Junnan Dong, Shuhao Zhang, Xing Sun
cs.AI
Graph Retrieval-Augmented Generation (GraphRAG) has remarkably enhanced large language models on complex reasoning by leveraging structured entity topologies. However, existing frameworks heavily rely on standard autoregressive language models where the nature of inherent sequential generation severely hinders overall inference efficiency. Inspired by Diffusion Language Models (DLMs) that offer massive parallelism via continuous...
-
27
Brain-Token Learning: Microstate-Based Tokenization and Multi-Scale Interaction for Long-Horizon EEG Sequence Modeling
Weishan Ye, Yue Pan, Li Zhang, Gan Huang, Zhen Liang
cs.AI
Electroencephalography (EEG) provides a non-invasive window into dynamic brain activity, yet modeling long-horizon EEG sequences remains challenging due to their high temporal complexity, substantial variability across subjects, and the lack of biologically meaningful sequence representations. Existing tokenization strategies, such as fixed-window and patch-based representations, discretize EEG signals according to artificial temporal...
-
28
When and How Should an Agent Clarify? CIGAsk: Teaching LLMs to Clarify via Counterfactual Information Gain
Yunxiang Li, Xixin Wu, Helen Meng
cs.AI
Instruction-tuned LLMs faced with underspecified queries often commit to a single interpretation rather than ask for clarification, producing confidently wrong answers. In our experiments, prompting alone is insufficient: models either ask for clarification on every query or ask vague questions that fail to recover the missing information. Addressing this failure requires learning two coupled skills: when to ask rather than answer and how to...
-
29
How Many Pixels Is a Digit Worth? Place-Aware Coordinate Entropy for GUI Agent Confidence Estimation
Yunxiang Li, Xixin Wu, Helen Meng
cs.AI
GUI agents predict click coordinates as digit-token sequences, but standard text-LLM confidence estimation methods rank correct clicks from wrong ones only weakly. GUI-specific alternatives use K samples or new supervision, but still leave room for improvement. We trace part of this to place-value asymmetry: bounding-box correctness often makes higher-place digits more important than lower-place digits, so uniform aggregation weakens the...
-
30
Unsupervised Brain Anomaly Detection as a Bayesian Inverse Problem with Diffusion Prior
Hugues Roy, Reuben Dorent, Ninon Burgos
cs.AI · cs.CV
Unsupervised anomaly detection (UAD) aims to localize abnormal regions in medical scans without pixel-level annotations. A typical strategy seeks to reconstruct a pseudo-healthy image that preserves subject-specific anatomy. Recently, diffusion models have been proposed to perform UAD. However, these methods rely on heuristic noise schedules or synthetic corruptions to balance subject-specificity and anomaly removal. In this work, we propose...
-
31
Taming CoT Obfuscation in VLMs: From Mechanistic Evidence to Activation Enforcement
Xutao Mao, Jianing Zhu, Jinman Zhao, Tongliang Liu, Xiaowen Chu, Cong Wang, Bo Han
cs.AI
Reinforcement learning (RL) improves reasoning in vision-language models (VLMs) but can induce chain-of-thought (CoT) obfuscation: an operational, non-intentional outcome where task reward or accuracy rises while traces become less grounded and monitorable. Prior work largely documents this decay behaviorally, leaving its representation-level correlates and actionable controls unclear. We find that template- and ground-associated activations...
-
32
Recovering Lost Details: Multi-Scale Frequency Compensation for Long-Term Time Series Forecasting
Runmin Zou, Siyi Xie, Yaohui Huang, Yun Wang
cs.AI
Long-term time series forecasting has made significant progress by leveraging multi-scale information to capture hierarchical temporal patterns and model long-range dependencies. However, temporal downsampling in existing multi-scale methods inevitably smooths detailed temporal fluctuations, and this information loss is further aggravated by their emphasis on dominant trends across scales, resulting in insufficiently expressive...
-
33
SKstars at SHROOM: Visions Agreement-Guided Ensembling of Zero-Shot and LoRA-Adapted Vision--Language Models
Ali Athar, Imran Ahsan, Joon-Yong Jung
cs.AI · cs.CV
This paper describes the SKstars submission to SHROOM-Visions 2026, a shared task on fine-grained hallucination detection in large vision-language model outputs. The task requires systems to identify hallucinated character spans, assign hallucination categories, and provide confidence estimates for their predictions. Our approach combines zero-shot predictions from Qwen2.5-VL-72B-Instruct with those of a LoRA-adapted Qwen2.5-VL-7B-Instruct...
-
34
LIMIT: Less Is More for Instruction Tuning in Text-to-SQL
Haoyuan Ma, Hengwei Liu, Linjuan Wu, Yongliang Shen, Weiming Lu
cs.AI
Large language models have achieved remarkable progress on Text-to-SQL through reasoning-enhanced fine-tuning, yet existing approaches predominantly rely on massive instruction corpora under the assumption that scale drives performance. We challenge this paradigm by investigating a fundamental question: what is the minimal data requirement for effective Text-to-SQL instruction tuning? We propose LIMIT(Less Is More for Instruction Tuning in...
-
35
CREDO: Variance-Guided Rubric Evolution for Replay-Corrected Credit Assignment
Xuchun Hu
cs.AI
Long-horizon language agents receive sparse terminal feedback, while intermediate rubrics provide structured but potentially misspecified assessments of progress. In resettable training environments, counterfactual continuation rollouts can measure local credit, but exhaustive replay is costly. We propose Credo, a framework that couples evolving semantic rubrics with selective, execution-based credit correction. A frozen judge maps visible...
-
36
APEXA: Execution-Integrity Enforcement for Multi-Agent LLM Automation of Synchrotron Data Reduction
Pawan K. Tripathi, Hemant Sharma, Andrew Chuang, Mathew J. Cherukara
cs.AI
Synchrotron data reduction, detector calibration followed by azimuthal integration of terabyte-scale diffraction series, is a multi-step, expert-bound bottleneck that increasingly limits the science rate of user facilities. LLM agents promise to collapse it, but driving a real pipeline with a stochastic model creates a failure mode chat benchmarks cannot see: an agent can report a calibration that was never computed. Correctness here is a...
-
37
Self-Healing Harness for Runtime Oversight of Agent Self-Modification
Sina Tayebati, Divake Kumar, Nastaran Darabi, Ranganath Krishnan, Amit Ranjan Trivedi
cs.AI
LLM agents can change their own future behavior, raising a basic control question of which self-generated changes should be allowed to persist. We formulate this as admission control for self-modification. The agent may propose changes to its operating instructions, while an external runtime gate controls persistence. We implement this principle as a model-agnostic self-healing harness that runs a Detect, Notice, Heal, Validate loop around an...
-
38
EDGEGEN: Improving Tool-Calling Agents Beyond Happy Paths with Synthetic Edge Case Generation
Harshavardhan Abichandani, Penny Chong, Jiyuan Shen, Gunraj Singh, Ashutosh Hathidara, Marcus Duigan Xing Yu, Jane...
cs.AI
Tool-calling LLM agents are increasingly deployed in enterprise applications. However, effective evaluation and optimization require high-quality, diverse task datasets that are often difficult to obtain due to privacy and other constraints. Existing synthetic task generation methods often produce generic tasks that ignore an agent's underlying state or database and fail to reflect real-world usage diversity. We propose EdgeGen, a synthetic...
-
39
When More Evidence Hurts: Publication-Bias Drift and Principled Stopping for Biomedical Causal Search
Fred Sun, Shangqi Guo
cs.AI · cs.IR
Automated biomedical evidence synthesis depends on retrieving published studies, but the biomedical literature is systematically skewed toward positive findings. Deeper retrieval can therefore make a system \emph{more} likely to falsely infer benefit when the true effect is null. We formalise this phenomenon as \emph{evidence drift} and prove that, under a standard publication-bias model, the false-positive probability on null-effect queries...
-
40
DocMIDE: Learning Multi-Hop Implicit Derivation in Visually Rich Documents
Jeremy Cerwin Wang, Wai Kit Wong, Jeff Kai Tai Tang
cs.AI
Real-world document processing systems rely on rigid, predefined schemas, yet critical target fields often lack direct visual counterparts on the page. Extracting these implicit values requires multi-hop derivation, such as aggregating sub-categories or reasoning over visual marks. While existing methods handle explicit text spans or simple implicit queries, they fail at multi-hop visual reasoning even after standard fine-tuning: models...
-
41
Incremental Consistency Execution for Autonomous Intelligent Systems
Cheng Li, Jiexiong Liu, Yixuan Chen, Ziheng Huang
cs.AI
Long-horizon autonomous intelligent systems rely on heterogeneous components such as large language models, databases, external APIs, and rule engines, while their external states continuously change during execution. Re-executing the entire workflow after every change introduces substantial redundant computation. This paper proposes an incremental consistency execution method based on task fact contracts, field-level dependency masks, and...
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.