Artificial Intelligence
LearnActCoder: Role-Aware Error Memory for Adaptive Clinical Coding Agents
Meysam Ghaffari, Bhaskar Sen, Nasim Sabetpour et al. (+3 more)
Clinical coding
agents repeatedly encounter the same failure modes, including unsupported codes, missed documented conditions, specificity errors, and procedure-coding convention mismatches. We introduce Learn-Then-Act, an inference-time adaptation framework that converts errors from a small labeled LEARN batch into a structured Mistake Knowledge Database (MistakeKDB). False-negative lessons are routed to a recall-oriented Coder, while false-positive lessons are routed to a precision-oriented Judge. We instantiate the framework in LearnActCoder, a Coder-Judge clinical coding pipeline with lookup-table grounding where available. On 150 matched MIMIC-III notes, structured MistakeKDB improves CPT F1 by 5.9 percentage points, while raw-example and reflection-style
memories remain near the no-
memory baseline; the ICD-9 improvement is not significant. On a matched MIMIC-IV cohort,
memory shifts ICD-10 coding toward higher precision at a recall cost, leaving F1 statistically unchanged. Applying the same
memory to 1,000 held-out MIMIC-III notes maintains a stable ICD operating point, providing scale/stability evidence. Overall, the results are consistent with structured, feedback-derived error
memory being useful for adapting clinical coding behavior across cases without weight updates or changes to the underlying workflow. Absolute CPT/HCPCS performance remains low, and the system is evaluated retrospectively rather than in clinical deployment.
Read the full abstract ▾
All authors Meysam Ghaffari, Bhaskar Sen, Nasim Sabetpour, Nina Fatehi, Animesh Agarwal, Carlos Morato
Artificial Intelligence · Cross-listed from cs.LG
Learn Your Own Thoughts: Abstract Token Curriculum
Khashayar Gatmiry, Avrajit Ghosh, Parsa Mirtaheri et al. (+4 more)
Large
Language Models (LLMs) have achieved remarkable
reasoning capabilities by utilizing chain-of-thought (CoT) as a scratchpad for intermediate stages of thinking. However, CoT techniques require explicit supervision on thinking
tokens, which requires rich, task-specific data. In this work, we propose Abstract
Token Curriculum (ATC), a novel curriculum learning framework that elicits effective continuous intermediate representations without direct supervision or manual scratchpad design. ATC gradually increases problem complexity through a sequence of distributions, training the model to develop internal abstract “thoughts” in the continuous representation space. This paper provides both theoretical and experimental evidence for the benefits of ATC and its advantages over previous methods for training continuous thoughts. Theoretically, we show that for learning parity functions with single-layer softmax
attention using ATC,
attention naturally focuses on the CoT
tokens in the context that provide the “easiest path” to predicting the next
token. Experimentally, we show ATC's effectiveness on graph reachability and arithmetic learning tasks.
Read the full abstract ▾
All authors Khashayar Gatmiry, Avrajit Ghosh, Parsa Mirtaheri, Jason D. Lee, Nika Haghtalab, Emmanuel Abbe, Peter Bartlett
Artificial Intelligence · Cross-listed from cs.CR
SoK: Trading Agents or Market Crashers? Dissecting Robustness and Security Failures in Academic Financial LLM Trading Schemes
Mengxiao Wang and Nitesh Saxena
Large
language model (LLM)
agents already trade with real capital, yet
agent-security research has mostly treated them as generic
agents. Trading changes the threat: a compromised
agent's orders move prices that other participants act on, and an attacker who profits from a crash can trigger the shock that a non-robust
agent mishandles. We present FARSIGHT (Financial
Agent Robustness and Security Investigation and Global Holistic Taxonomy), a systematization that rates trading
agents on robustness to
market stress and on security against source manipulation,
agent compromise, and
agents acting as attackers. It also checks paper-level ratings against released code. Across 15 academic schemes, none earns full credit on any robustness metric, no paper describes a way to halt trading without waiting for LLM inference, and none combines source provenance with cross-source corroboration. In the code of the 7 open-source schemes, no release enforces a stop-loss or position limit outside the LLM, 4 lack a component that their paper or documentation describes, and 2 run model-written code on the host. The same gaps appear beyond finance. Restating FARSIGHT as a domain-independent threat model, we map them onto
agents in healthcare, law, software, and crypto. We then trace how compromised
agents spread harm, as worms and as cascades that need no further compromise. At published injection rates per hop, a channel read by ten
agents lets one compromised
agent start an outbreak. We derive 14 open problems and urge deployers to corroborate sources, keep interrupts that bypass the model, and enforce loss limits outside it.
Read the full abstract ▾
Artificial Intelligence
FINSKILLOPS: A Self-Evolving Multi-Agent System for SEC Filing QA
Yanzhang Ma, Zhenghan Tai, Hanwei Wu et al. (+25 more)
Financial QA systems are typically improved before deployment through better
retrieval, prompting, or
agent coordination, leaving their reliability behavior fixed thereafter. In practice, new SEC-filing questions repeatedly expose heterogeneous errors in period, entity, evidence use, and calculation. Existing self-improvement methods can turn failures into new behaviors, but offer limited control over where a correction should apply or which previously correct answers it may break. We therefore frame post-deployment improvement as controlled behavioral maintenance: recurring failures should become scoped skill patches, and each patch should earn deployment with- out introducing regressions. We instantiate this view in FINSKILLOPS, a multi-
agent system for SEC filing QA. FINSKILLOPS derives reusable skills from evidence-grounded, typed failure diagnoses and governs them through targeted validation, protected-case regression checks, negative controls, and versioned replacement or retirement. Across six financial QA
benchmarks, a single frozen skill registry achieves the highest verdict-weighted correctness and reference consistency among the evaluated systems. Evolved skills raise correctness from 3.70 to 4.55 on our enhanced
benchmark. In a separate 12-round operational study, only six of 33 proposed skills are promoted, while the monitoring non-correct rate falls from 20.0% to 12.5%. These results establish controlled skill scope, admission, and lifecycle management as the foundation for reliable self-improvement.
Read the full abstract ▾
All authors Yanzhang Ma, Zhenghan Tai, Hanwei Wu, Sizhe Guan, Jianliang Lei, Hailin He, Chaolong Jiang, Jijun Chi, Tung Sum Thomas Kwok, Bohuai Xiao, Jingrui Tian, Xinlu Wu, Xingao Zhan, Peng Lu, Muzhi Li, Yihong Wu, Liheng Ma, Sicheng Lyu, Tianshuo Yan, Junhao Zhu, Yaqian Xu, Lei Ding, Yufei Cui, Ziquan Liu, Boyu Han, Hengli Liu, Ling Zhou, Xinyu Wang
Artificial Intelligence
When2Think: Learning When and How Much to Reason
Jaejun Shim, HyunJin Kim, Young Jin Kim et al. (+1 more)
Large
Reasoning Models (LRMs) often overthink easy problems and underthink hard ones, leading to inefficient computation allocation. Existing methods regulate generated computation or select between direct answering and explicit
reasoning, but do not jointly control whether}to reason and how much computation to allocate within
reasoning. We call the resulting difficulty-dependent loss in accuracy under computation reduction the efficiency tax. We propose When2Think, an RLVR-based post-training framework for instance-adaptive computation allocation. Its core mechanism, Instance-level Difficulty-Aware Control (IDAC), uses cached reference statistics of success and
token cost to modulate a correctness-gated efficiency bonus based on generated
token count. Importance sampling supports exploration of Think and NoThink, while Batch-Wise Standardization constructs standardized advantages for critic-free optimization. The framework requires neither a learned reward model nor a learned critic, and offline reference caching avoids online reference-model queries during policy updates. On AIME24, When2Think improves Pass@3 by 10.0 percentage points while reducing
token usage by 27.9% relative to the backbone.
Read the full abstract ▾
All authors Jaejun Shim, HyunJin Kim, Young Jin Kim, JinYeong Bak
Artificial Intelligence · Cross-listed from cs.IR
Self-Evolving Search Index
Sangam Lee, Wonjae Lee, Sunghwan Kim et al. (+5 more)
Information
retrieval is increasingly important as LLM
agents tackle complex tasks involving diverse information needs. Because
retrieval relies on an index that represents each document through index keys,
retrieval quality depends heavily on how effectively these keys expose the knowledge contained in each document. However, effective index representations vary across
retrieval environments, making it difficult for any fixed optimization strategy to perform consistently. Yet evolving an index to its
retrieval environment remains largely human-driven, requiring humans to diagnose
retrieval failures, refine the optimization strategy, and reprocess the index accordingly. We propose SELF-INDEX, a framework that enables an index to self-evolve without human intervention. Its Optimizer autonomously diagnoses
retrieval shortfalls, selectively revises the responsible index keys, and validates each revision before updating the index. Beyond reacting to observed
retrieval demands, SELF-INDEX proactively explores additional demands through a Query Simulator, allowing the index to evolve beyond the queries already available for optimization. Across diverse corpora and retrievers, SELF-INDEX consistently improves
retrieval performance while outperforming existing index optimization methods. We further show that these benefits extend to downstream applications, improving the effectiveness and efficiency of search
agents and helping
agent memory systems retrieve useful past interactions.
Read the full abstract ▾
All authors Sangam Lee, Wonjae Lee, Sunghwan Kim, Deogyong Kim, Jaehoon Kim, Daye Nam, SeongKu Kang, Dongha Lee
Artificial Intelligence
Replan, Repair, or Edit? A Unified Empirical Evaluation of Travel Agents for Itinerary Revision under Resource Disruptions
Xiaofei Yuan, Yan Zhang, Shaobo Qiao et al. (+7 more)
Travel-planning
agents generate itineraries that may become infeasible after acceptance because of flight cancellations, hotel unavailability, or attraction closures. Revising these itineraries involves full replanning, classical plan repair, and LLM-based travel-
agent revision, whose differing task formulations and evaluation protocols hinder comparison. We conduct a systematic empirical study using two TREK-derived
benchmark sets: 500 single-disruption cases, including feasible and infeasible instances, and 200 feasible simultaneous compound-disruption cases. We compare LLM-Z3 full replanning, IPyHOPPER hierarchical repair, and an iTIMO local-revision adapter across effectiveness, plan stability, and computational cost. LLM-Z3 with Gemini achieved the highest observed compound-disruption success. IPyHOPPER nearly matched that configuration's single-disruption overall success, while preserving substantially more of the accepted itinerary on successful repairs. Successful hierarchical and local repairs made fewer edits and retained more accepted commitments than full replanning. Computational profiles differed: IPyHOPPER used no LLM inference, the evaluated LLM-Z3 adapter used compact one-call inference, and the iTIMO adapter consumed substantially more
tokens. The study provides practical guidelines for balancing feasibility recovery, commitment preservation, and computational cost within evaluated settings.
Read the full abstract ▾
All authors Xiaofei Yuan, Yan Zhang, Shaobo Qiao, Huangleshuai He, Leyan Ni, Mingchen Ju, Lujia Yang, Sijia Xu, Yifu Tang, Zhengyi Yang
Artificial Intelligence
ScientistTwo: Pioneering the Human Knowledge Frontier with Autonomous AI
Jaehyun Nam, Jinsung Yoon, Yanzhou Pan et al. (+4 more)
Scientific discovery is defined by the ability to identify the boundaries of existing knowledge and venture into unexplored territory. The ultimate
vision for AI in science is problem-driven autonomous research: given a fundamental challenge by a human expert, the AI independently navigates the scientific landscape, uncovers theoretical and empirical bottlenecks, and systematically expands the frontier of knowledge. In this paper, we introduce ScientistTwo, a fully autonomous multi-
agent framework designed to realize this
vision. Specifically, ScientistTwo takes an initial problem as input, establishes state-of-the-art baselines, formulates novel hypotheses, and coordinates specialized
agents to orchestrate an end-to-end discovery cycle without human intervention. Moreover, the framework rigorously conducts experiments using diverse
datasets and metrics, refines methodologies through automated ablation studies, and validates research findings via a closed-loop simulated peer-review rebuttal engine. To evaluate ScientistTwo's capabilities against the highest standards of human scientific achievement, we
benchmark it across papers accepted at top-tier conferences such as ICLR, ICML, and NeurIPS. As a result, ScientistTwo autonomously generates expert-level, publishable papers and fully verified, executable codebases. Its solutions consistently outperform human state-of-the-art models, and achieve higher average review ratings than human-authored papers under automated AI review
agents. These results show that ScientistTwo is not merely an assistive tool but an autonomous scientific pioneer capable of pushing the frontiers of human discovery. Project website: https://scientist-two.github.io/
Read the full abstract ▾
All authors Jaehyun Nam, Jinsung Yoon, Yanzhou Pan, Yubo Wang, Rui Meng, Parthasarathy Ranganathan, Tomas Pfister
Artificial Intelligence
Reach or Solve? Deep Diving into Agentic RL Gains with Checkpoint Handoffs
Xuan Liu and Jingbin Qian
Reinforcement learning (RL) is widely used to improve
language-model
agents, and its gains are usually measured by final task success. However, an
agent's earlier actions shape the states in which its later decisions are made, so final task success conflates the ability to reach useful states with the ability to complete the task once there. Comparing
agents only on the states each one reaches does not separate the two, since each
agent is then scored on states selected by its own actions. To address this conflation, we introduce checkpoint handoff, an evaluation protocol that decouples reaching from completing without retraining. One checkpoint acts as a reacher up to a handoff point, and another continues as the solver from the same replayed history. In detail, (1) Reach measures how often a reacher arrives at states that a replayable environment verifies to be a fixed number of actions from success, and (2) Solve measures how often a solver completes the task from identical cloned copies of those states. Crossing supervised fine-tuning (SFT) and RL checkpoints in both roles across two
benchmarks and two independently released training pipelines, we find that the gain from switching the solver from SFT to RL is consistently larger when RL is the reacher, at all three model scales on TravelPlanner and on both ALFWorld splits. Further analyses on ALFWorld show that RL improves both Reach and Solve. The solver gain is larger under an RL reacher because RL reaches solvable states more often, and separately measured Reach and Solve gaps recover most of this difference. Because handoff only requires replaying one checkpoint's history under another, agentic RL evaluations can report arrival and completion alongside final success.
Read the full abstract ▾
Artificial Intelligence
From Intent to Action: Benchmarking LLM Safety in Vehicle Voice Command Authorization
Diba Afroze, Xingli Zhang, Yazhou Tu et al. (+1 more)
Large
language models (LLMs) are increasingly integrated into vehicle voice assistants. But linking natural-
language requests to vehicle functions creates a safety-critical authorization problem. Before executing a command, the system must choose whether to execute, refuse, clarify, require confirmation, defer to manual control, trigger an emergency response, or make no tool call. To our knowledge, prior evaluations do not isolate this pre-action decision across speaker role, authentication status, vehicle state, and tool availability. We introduce a 202-scenario
benchmark with Reference Decisions under a seven-class taxonomy. We evaluate two local open-weight models and three API-based LLMs using Decision
Alignment and safety-specific error metrics.
Alignment ranges from 40.1% for Llama 3.2 3B to 89.1% for Gemini 3.1 Pro Preview. The API-based models score between 83.2% and 89.1%, with no statistically significant differences among them. Even these models produce two to three False Executes among 161 non-execution scenarios, and persistent errors remain in confirmation and manual-control decisions. A controlled Llama 3.2 3B ablation increases
alignment to 40.1% under the structured authorization policy, versus 28.2-29.2% under schema-only and generic-safety baselines, but it does not eliminate False Executes. Structured LLM decisions are therefore insufficient as a standalone safety mechanism, and deployment requires an independent enforcement layer that verifies tool permissions and vehicle-state constraints before invoking any vehicle function.
Read the full abstract ▾
All authors Diba Afroze, Xingli Zhang, Yazhou Tu, Xiali Hei
Artificial Intelligence · Cross-listed from cs.HC
DataCanvas-EDU: An Agentic Framework for Instructor-Guided Synthetic Data Generation in Business Analytics Education
Bang An, Maria Hamdani and Joseph Fox
Business analytics education requires diverse
datasets to support different learning objectives, student backgrounds, and analytical tasks. Real-world data can be difficult to obtain and offer limited flexibility for adapting a case to a particular course. Even when suitable data are available, instructors must investigate the patterns, verify the results, and prepare assignments and reference solutions, requiring substantial time and effort. The use of large
language models (LLMs) introduces an additional concern about training data contamination. Widely used public
datasets often have extensive tutorials and worked analyses that models may have encountered during training. Students may therefore receive explanations drawn from existing analyses without practicing how to investigate unfamiliar data in collaboration with AI. This paper presents DataCanvas-EDU, an agentic framework for instructor-guided synthetic data generation in business analytics education. Instructors specify teaching goals and intended patterns through conversation, while an AI
agent writes generation code, checks the resulting data, and prepares assignments, reference analyses, and rubrics. Four phases, Plan, Create, Verify / Test Analysis, and Evaluate, organize the process and support instructor review and revision. The framework is intended to simplify case preparation while creating opportunities for students to investigate newly designed patterns with AI. We illustrate the approach with WindowDash, a food delivery case containing 15,000 orders and nine designed patterns. DataCanvas-EDU is packaged as a reusable AI
Agent Skill for compatible
agent environments, with the package and installation instructions available at https://github.com/BANG23333/datacanvas-edu
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Semantic Layer Induction from Raw Telemetry via Hierarchical LLM and RAG Abstraction
Yuanzhe Jia and Ali Anaissi
Modern applications generate massive volumes of raw telemetry data, but translating those noisy, heterogeneous event streams into actionable business insights remains a fundamental challenge. Data engineers and analysts expend substantial effort reconciling semantic discrepancies, hand-crafting parsing logics, and maintaining fragile mappings between raw data and business KPIs. In this paper, we present an end-to-end framework that fully automates the construction of a business semantic layer from application raw logs. Our approach introduces a two-stage semantic abstraction: first, high-level business features are identified via LLM inference augmented with domain-specific industry knowledge; second, fine-grained business nodes are derived through a structured pipeline comprising data refinement, hybrid
retrieval, multi-stage filtering, semantic clustering, and canonical naming. Evaluation on production-scale telemetry demonstrates that our system improves human-assessed semantic quality from 50 to 80+ on a 100-point scale, reduces maintenance effort by 80%, filters out 74% of noise, and achieves 0.87 Cohen's kappa via an integrated LLM-as-Judge evaluation, enabling continuous, scalable quality assurance. Overall, our work distinguishes itself from prior work by addressing the novel problem of business semantic layer induction from raw telemetry, operating without labeled training data or manual rule engineering.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
TacSushi: Tactile-Grounded World-Action Modeling for Dexterous Sushi Manipulation
Haodi Hu, Kaen Kogashi and Toshiaki Koike-Akino
Dexterous food manipulation requires control under deformation, occlusion, and uncertain contact. We present TacSushi, a tactile-grounded, Cosmos3-based world-action policy that learns from recorded future consequences while acting on current observations. The backbone encodes current RGB,
language, and hand state, and feature-wise gated fusion incorporates fingertip tactile features into the action representation. During training, a decoder conditioned on demonstrated action chunks predicts logged future visual observations, task progress, relative contact risk, and tactile summaries; this decoder is removed at deployment. Failed trials provide consequence supervision, but their actions are excluded from imitation. We train TacSushi on 340 successful and 50 failed real-
robot trials and compare six methods in 600 separate rollouts across three in-distribution tasks and two out-of-distribution ingredient variants. To assess food quality beyond a single
geometric threshold, we score terminal outcomes using an anchored visual-quality protocol that equally weights five human ratings and three
vision-
language-model ratings per rollout. Full TacSushi achieves 68.3% average in-distribution success and 37.5% out-of-distribution success, compared with 36.7%/10.0% without future-consequence supervision and 25.0%/17.5% with direct tactile concatenation in place of gated fusion. These comparisons support complementary benefits of feature-wise gated tactile fusion and training-only predictive supervision.
Read the full abstract ▾
Artificial Intelligence
SIMLIFE: Pattern Understanding for Long-Horizon Human-Agent Partnership
Run Peng, Zinnia Nie, Jing Ding et al. (+7 more)
Understanding humans over long horizons requires
agents to infer not only what people need in the moment, but also how routines form, why they repeat, and when they change. We introduce SimLife, a scalable platform for simulating long-term household life with rich visual observations, ground-truth action logs, and synthetic dialogues with audio. Built on SimLife, SimLife-BP evaluates long-context pattern understanding: the ability to infer latent behavioral rules from weeks or months of everyday observations. The
benchmark contains 106 episodes averaging 15.49 hours and 38.57 in-game days, and 1,439 question-answer pairs. Each task probes direct, counterfactual, noisy, and inverse
reasoning under different levels of rule hints. Evaluating frontier models and architectures, we find that current models often achieve surface-level prediction without comprehensive rule understanding, rely on frequency-based heuristics rather than if-then
reasoning over evidence, and struggle to adapt when behavioral patterns change. These findings suggest that long-context pattern understanding remains a major bottleneck for future
embodied agents, while SimLife opens a broader space for studying
memory, personalization, adaptation, and long-horizon planning in everyday human-AI interaction.
Read the full abstract ▾
All authors Run Peng, Zinnia Nie, Jing Ding, Yinpei Dai, Yichi Zhang, Zengqing Wu, Yao Fu, Ziqiao Ma, Jiayuan Mao, Joyce Chai
Artificial Intelligence · Cross-listed from cs.SE
DeltaSelect: Affordable A/B Testing for Coding Agents
Nicholas J. Conn
Coding-
agent benchmarks are built for broad and comprehensive comparisons, not frequent development decisions. Individual runs vary, full suites are expensive, and the
benchmark harness may differ from the harness used in practice. In a resampling analysis of DeepSWE's published trials, only 19.5% of tasks (22 of 113) had a fifth-percentile Pearson correlation of at least 0.50 with full-
benchmark performance. The paper presents DeltaSelect, an open-source method that identifies tasks whose one-run results consistently track full-
benchmark performance using Pearson correlation, maps fractional verifier results to a common score using linear regression, and selects a fixed task set within a dollar budget. DeltaSelect is intended for repeated baseline-versus-candidate comparisons during development, not model rankings. In a gpt-5.6-luna low-
reasoning case study, DeltaSelect was used to revise custom skills and instructions. Across 13 evaluations, the recorded cost was USD 27.86 at rates published August 16, 2026. The adopted version cost 58.1% less than the initial version (USD 1.75 versus USD 4.18; p=0.008), while the calibrated score was higher (42.36% versus 36.46%; published-analog variance p=0.326).
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Form Over Content In Gradient-Based Data Attribution Methods
Sunwoo Kim, Seokwon Jung, Sohyung Kim et al. (+2 more)
Data attribution methods using gradient similarity are widely used to analyze and select training data for large
language models, but what gradient similarity actually measures is debated. Some interpret it as identifying task-relevant skills, while other work reports that surface form is the main factor. We resolve this debate for supervised fine-tuning examples by varying task and answer format independently. Specifically, we render
benchmarks in different answer formats, such that
datasets can share a task without a format or a format without a task. We find that gradient
alignment follows the answer format, as
benchmark pairs sharing an answer format align strongly (disattenuated cosine near 0.4), while same
benchmarks rendered with different answer format classes show no
alignment (near 0.0). We demonstrate that this ordering holds from the earliest pretraining checkpoints through post-training, and across model scales and families. We then analyze the released selections of LESS, a gradient-based data selection method for instruction tuning, and find that each target's selections over-represent the target's own answer format. Hence, we demonstrate that gradient-based attribution methods track format similarity more than task semantics, meaning that such methods, as well as the semantic interpretation of the gradient, should be tested on data where answer format and task vary independently for greater robustness and reliability.
Read the full abstract ▾
All authors Sunwoo Kim, Seokwon Jung, Sohyung Kim, Seong Joon Oh, Alice Oh
Artificial Intelligence · Cross-listed from cs.CR
Red-Teaming Auto Mode: Improving Blocking Classifiers Against Malign Coding Agents
Alex Remedios, Simon Storf, Fabien Roger et al. (+1 more)
To keep coding
agents from going off the rails, production systems now review each proposed action with a blocking monitor that can reject it before it runs (Auto Mode in Claude Code, Guardian in OpenAI's Codex). Prior evaluations of such monitors largely measure robustness to accidental harm or
prompt injections from untrusted sources looking to hijack the
agent. Less understood is how they hold up when the
agent they monitor is persistently misaligned. To understand this risk, we task an
adversarial agent with evading production blocking monitors and causing catastrophic harm, e.g. by exfiltrating its own weights. We find that when instructed with high-level attack strategies,
adversarial agents can succeed through several distinct mechanisms, such as
agent-generated
prompt injection against the monitor, multi-
agent attacks, and malicious compaction. In particular we find that in 79% of trials, the
agent can use an injection attack against Auto Mode and Guardian to run arbitrary bash commands. We also find that it is possible to greatly improve Auto Mode through design changes like enhancements to tool coverage, changes in transcript formatting, and the addition of an agentic monitor stage. Even with these improvements, preventing multi-context attacks at an acceptable cost remains an open problem. By detailing our red-teaming methodology and highlighting new attack vectors, we aim to help defenders evaluate their mitigations against the possibility of persistent malign coding
agents. Code is available at https://github.com/safety-research/red-teaming-auto-mode.
Read the full abstract ▾
All authors Alex Remedios, Simon Storf, Fabien Roger, John Hughes
Artificial Intelligence · Cross-listed from cs.CL
CliniCIRCA: A Modular LLM Framework for Constructing Longitudinal Mental Health Patient Journeys from Raw EHR Narratives
Aiwei Ivy Zhang, Nimra Ishfaq, Mohit Chandra et al. (+5 more)
In mental health care,
reasoning over patient journeys is a key task for clinicians. Yet these journeys, encompassing a longitudinal progression of biological, psychological, and social events, are often spread across disparate unstructured text narratives, making temporal recovery challenging. We present CliniCIRCA, a multi-stage LLM framework for Calendar-anchored, Imprecision-aware Reconstruction of Clinical Annals. To our knowledge, CliniCIRCA is the first to temporally classify clinical events across unstructured discharge summaries without event-level timestamps. From 14,882 MIMIC-III mental health admissions, we first construct a
benchmark of 52 discharge summaries on which CliniCIRCA produces 15,891 temporally tagged events. After correcting 629 errors based on a clinician-in-the-loop evaluation, we produce verified gold-standard labels. Finally, the corrected timelines drive a temporally grounded summarization stage that compresses each source 1.52 times into a date-grouped chronological record. We then scale the framework to generate 1,000 silver-standard timelines and evaluate them as training data. Compared with zero- and few-shot prompting, instruction tuning generally improves five open-weight models on event extraction, temporal tagging, and summarization across silver and clinician-verified evaluations.
Read the full abstract ▾
All authors Aiwei Ivy Zhang, Nimra Ishfaq, Mohit Chandra, Santiago Alvarez Lesmes, Adam Coscia, Khatiya Chelidze Moon, Xiaohan Ding, Munmun De Choudhury
Artificial Intelligence · Cross-listed from q-bio.GN
Large Language Model Agents for Evidence Based Genetic Disease Severity Classification
Tohid Ghasemnejad, Ahmadreza Argha, Mark Grosser et al. (+7 more)
Disease severity classification for genetic conditions is subjective and labor-intensive, creating bottlenecks in genomic screening, where commercial panels vary widely in size and overlap. We developed an autonomous AI
agent integrating
Reasoning and Acting (ReAct) with
Retrieval-Augmented Generation (RAG) to classify 10,211 Human Phenotype Ontology terms. It uses American College of Medical Genetics (ACMG)-endorsed severity guidelines and American College of Obstetricians and Gynecologists (ACOG) quality-of-life criteria to retrieve PubMed literature, generate interpretable
reasoning chains, and independently verify claims. At the phenotype level, using expert-curated cohorts, the
agent achieved 93.55% accuracy (MCC 0.9237) with 82.6% to 91.4% of claims supported by direct evidence or valid inferences. Gene-level severity was aggregated across 8,738 pairs, identifying 3,283 autosomal recessive pairs with severe or profound presentations. External validation showed 95.2% concordance with Mackenzie's Mission gene list. This system enables standardized panel design by providing reliable, automated classification supported by direct evidence.
Read the full abstract ▾
All authors Tohid Ghasemnejad, Ahmadreza Argha, Mark Grosser, John Wang, Min Yang, Thantrira Porntaveetus, Tony Roscioli, Nigel H. Lovell, Mahmoud Aarabi, Hamid Alinejad-Rokny
Artificial Intelligence · Cross-listed from cs.CV
A Multi-Modal Generative Model for Tomato Disease Leaves Understanding
Khang Nguyen Quoc, Minh-Phuoc Tran, Gia-Han Truong et al. (+1 more)
Artificial intelligence for plant disease analysis has advanced from task-specific classifiers to multi-modal models capable of jointly interpreting visual and textual information. However, practical deployment in precision agriculture remains limited because most existing approaches treat disease understanding as isolated prediction tasks, failing to capture the complementary relationships among symptom recognition, severity assessment, and question-driven diagnostic
reasoning. In tomato pathology, accurate interpretation of diseased leaves requires more than label prediction; it demands integrating visual symptoms with semantic context to support a comprehensive and explainable understanding. Here, we present
SOLAR, a
multimodal generative model that understands tomato disease spanning six question-answering tasks.
SOLAR learns to align visual features with task-aware
language representations by Fusion Expert module based on mixture-of-expert, enabling it to generate contextually relevant answers across diverse diagnostic tasks. By formulating tomato disease analysis as a generative Visual Question Answering (VQA) task,
SOLAR provides a flexible framework that supports multi-task inference within a single model while improving performance and cross-task knowledge sharing. We evaluate
SOLAR on $41,677$ images, including $216,209$ Question-Answering (QA) pairs to understand tomato leaf disease under both closed and open-ended QA settings. Experimental results show that
SOLAR consistently outperforms state-of-the-art
vision-only,
vision-
language, and task-specific models across all tasks, demonstrating superior accuracy, robustness, and
multimodal reasoning. These findings highlight the potential of generative
multimodal modeling as an effective direction for understanding of plant disease. The code for this study is available at https://github.com/EnalisUs/
SOLAR.
Read the full abstract ▾
All authors Khang Nguyen Quoc, Minh-Phuoc Tran, Gia-Han Truong, Luyl-Da Quach
Artificial Intelligence
Continual Enterprise World Model Discovery in Dynamic Systems
Shambhavi Mishra, David Vazquez, Perouz Taslakian et al. (+3 more)
In an enterprise system, updating one field can set another, create a record, or start an approval. These effects are produced by business rules that are not built into the platform but written by each organization and revised over time. An
agent working in such a system cannot predict the result of its own actions without knowing these rules. We study continual enterprise world model discovery, where an
agent starts without knowledge of these business rules and discovers them by interacting with records and observing the outcomes. From those observations it builds a world model, which it revises as the rules change. To evaluate this, we introduce EnterpriseWorldShift, built on a live ServiceNow environment with nine tables, 25 hidden rules and 600 evaluation actions. It presents four versions of the same enterprise world, with the tables and records held fixed while a rule is modified, then added, then removed, so that discovery, revision, extension and retirement are each tested in turn. Our Continual Discovery
Agent (CDA) builds such a model and carries it from one world to the next. It predicts the effects of the hidden rules more accurately than looking them up for each question, the approach taken by prior work, by up to 8.98 IoU points, and it answers from its own model without querying the running system.
Read the full abstract ▾
All authors Shambhavi Mishra, David Vazquez, Perouz Taslakian, Marco Pedersoli, Jose Dolz, Issam H. Laradji
Artificial Intelligence · Cross-listed from cs.LG
Compressed Active Subspaces for Scalable Bayesian Inference
Thomas Flynn, Sanket Jantre, Byung-Jun Yoon et al. (+1 more)
Active subspace methods provide a framework for quantifying predictive uncertainty in high-dimensional models by identifying and performing inference along parameter directions that have the greatest influence on the model output. However, the construction of active subspaces requires storing many full-dimensional model gradients, which becomes prohibitive as model size increases. We address this limitation by proposing Compressed Active Subspaces (CAS), a scalable approach that first maps the model parameters to a compressed space using a structured isometric
embedding and then constructs the active subspace within this reduced parameterization. Our approach substantially reduces the
memory required for active subspace construction and enables
Bayesian inference for large models where standard active subspace methods become impractical. We demonstrate the scalability of CAS on neural networks of increasing size while maintaining predictive performance and robust uncertainty estimates.
Read the full abstract ▾
All authors Thomas Flynn, Sanket Jantre, Byung-Jun Yoon, Kibaek Kim
Artificial Intelligence
Agentic AI Networking for Heterogeneous Unmanned Aerial Systems in Low-Altitude Wireless Networks
Nguyen Duc Minh Quang, Chang Liu, Shuangyang Li et al. (+1 more)
Low-altitude wireless networks (LAWNs) are emerging as a key infrastructure for heterogeneous unmanned aerial systems that support concurrent services within a shared three-dimensional airspace. Their coexistence creates strong coupling among mobility, connectivity, and shared network resources, while heterogeneous services impose distinct and time-varying requirements. These interactions naturally form a dynamic non-cooperative game in which both operating conditions and coordination objectives evolve over time. Conventional optimization and learning-based controllers typically rely on predefined objectives, limiting their ability to adapt autonomously to changing service requirements and resource priorities. To address this challenge, we propose a hierarchical hybrid large
language model (LLM)- multi-
agent reinforcement learning (MARL) architecture organized as a dual-loop structure. Specifically, an outer adaptation loop employs LLM-assisted game orchestration to interpret service requirements and operator intent, and reconfigure objectives and resource priorities, while an inner loop executes decentralized, parameter-conditioned MARL policies under the configured game. A logistics-monitoring case study illustrates how the proposed framework facilitates coordinated coexistence among heterogeneous services, adapting to evolving operating conditions without retraining the underlying MARL policies. Finally, we discuss key challenges and research directions toward scalable, trustworthy, and adaptive agentic LAWNs.
Read the full abstract ▾
All authors Nguyen Duc Minh Quang, Chang Liu, Shuangyang Li, Derrick Wing Kwan Ng
Artificial Intelligence · Cross-listed from cs.DC
Detecting Soft Errors in Parallel Software with LLM-tuned Instruction Duplication
Yafan Huang and Guanpeng Li
We propose PaRID (PaRallel Instruction Duplication), a software-directed soft error detection framework that requires only compile-time effort for multithreading parallel programs. PaRID addresses two key challenges: supporting parallel programs with mixed serial and parallel regions and minimizing performance overhead without relying on costly dynamic profiling. It combines parallel-aware code transformation with LLM-tuned performance modeling, guided by eight generalizable findings from an offline characterization study, to enable fast soft error detection in parallel applications. Evaluation on NPB
benchmarks shows that PaRID reduces protection overhead from 162.79% to 59.84% on average and achieves up to 5x speedup while maintaining full error detection effectiveness.
Read the full abstract ▾
Artificial Intelligence
When Hiring Becomes Agent-Mediated: Evaluating Access and Recurrence in Two-Agent Résumé Screening
Jian Gao and Hang Jiang
Hiring is bilateral: employers assess fit, while candidates present and defend evidence of their qualifications. Yet résumé screening, the first gate, is commonly automated as a static, one-call judgment over a résumé-job pair. We study a two-
agent alternative in which employer-side and candidate-side
agents represent these roles, exchange evidence, and update their judgments before deciding who advances. We compare procedures on 600 constructed résumé-job pairs using GPT-5.5 and Claude Opus 4.7. Two-
agent screening advances more applications (33.3% to 39.3% for GPT-5.5; 34.0% to 35.5% for Opus 4.7). Across three runs on the common 191-pair borderline pool, pass-instance rates rise from 4.5% to 26.2% and from 6.5% to 16.1%, respectively. This is not a uniform relaxation: two-
agent screening rejects applications one-call advances, changing decisions in both directions. At similar pass volumes, the procedures advance different applications, and no one-call threshold recovers applications consistently selected by two-
agent screening. Among discovery-selected cases re-executed in fresh runs, two-
agent-only selections recur less often than shared selections, clearly under GPT-5.5 and less certainly under Opus 4.7, while a separate one-call follow-up shows no comparable decline. As hiring becomes
agent-mediated on both sides, the screening procedure, not only the model behind it, shapes who reaches human review and how reliably that access recurs.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
AURORA: A Natural Language-Driven Agentic Framework for Understanding, Reasoning, and Orchestrating Reliable Air-Ground Co-Simulation
Keshu Wu, Hao Zhang, Rui Gan et al. (+4 more)
Air-ground transportation research increasingly relies on co-simulation, yet constructing scenarios remains labor-intensive and difficult to validate. More importantly, a generated scenario may execute successfully while failing to realize the spatial, temporal, communication, or behavioral relationships requested by the user. This paper presents AURORA, a natural-
language-driven agentic framework that treats air-ground scenario generation as a process of compilation with verification. Central to AURORA is the Air-Ground Scenario Graph (AGSG), a typed intermediate representation that explicitly connects
agents, aerial missions, events, communication links, success conditions, and their cross-domain dependencies. This shared representation enables simulator-grounded parsing, joint road-airspace grounding, temporal planning, pre-execution feasibility checking, trace-based runtime verification, failure localization, and bounded repair within a unified workflow. We further introduce AURORA-Bench to evaluate not only whether generated scenarios execute, but whether they faithfully realize the requested interactions. Experiments across multiple
language models show that structured execution substantially improves reliability, while runtime verification exposes silent failures that completion-based evaluation overlooks. Localized repair further resolves many violations without regenerating the entire scenario. The results show that reliable scenario generation requires verifying realized behavior, not merely executable code, and demonstrate the value of explicit intermediate representations for verifiable and repairable
language-driven co-simulation.
Read the full abstract ▾
All authors Keshu Wu, Hao Zhang, Rui Gan, Xiangbo Gao, Xiaopeng Li, Zhengzhong Tu, Yang Zhou
Artificial Intelligence
Self Improvement via Fast Tree-search
Xinghong Fu, Aravinth Kulanthaivelu and Yutaro Yamada
Coding
agents can recursively modify their own implementations, forming a loop of self-improvement. While prior work shows this can boost performance on coding
benchmarks, existing approaches are costly and compute-intensive. We introduce a simple, sample-efficient self-improvement framework that significantly improves coding performance under strict budget constraints. We identify evaluation of candidate self-modifications as the main runtime bottleneck since prior approaches estimate their effectiveness by re-running a subset of
benchmark tasks with the modified
agent, which is time-consuming. We introduce Recursive Self Improvement via Fast Tree-search (SIFT), which augments these downstream task evaluations with an LLM-as-a-judge signal that performs pairwise comparisons between candidate patches, where the win-loss record is aggregated with a regularized Bradley-Terry model, and the resulting strength scores drive rank-based parent sampling inside a lightweight disaggregated tree search. Expensive downstream task evaluations are reserved only for the most promising nodes. Using a fully disaggregated tree search pipeline, the judge scores provide intermediate signal to guide exploration on promising candidate patches without being bottlenecked by slow evaluation runs. SIFT outperforms existing tree-search based self-
evolution frameworks on the full Polyglot
benchmark with significantly lower resource requirements in terms of CPU hours, wall clock time, and API cost.
Read the full abstract ▾
Artificial Intelligence
A Unified Evaluation Framework for Trustworthy Large Language Models, Agentic AI, and Multimodal Systems
Shaina Raza, Ahmed Y. Radwan, Imran Liaquat et al. (+1 more)
Benchmark scores alone provide an incomplete basis for assessing the trustworthiness of modern artificial intelligence systems. Large
language models (LLMs), agentic systems, and
multimodal models (MLLMs) require different forms of assessment, yet their evaluation evidence must remain interpretable for development and oversight. We propose a unified framework that connects output-level, trajectory-level, and cross-modal assessment through eight trustworthiness dimensions: capability, robustness, safety,
fairness, transparency, governance, oversight, and efficiency. The framework preserves system-specific metrics while mapping native measurements to common performance bands, accompanied by uncertainty estimates and traceable evidence. A meta-evaluation layer examines the validity, reliability, and reproducibility of the evaluation itself. Multidimensional profiles expose strengths and weaknesses, while safety-critical overrides prevent aggregate scores from masking critical failures. Mappings to governance frameworks, international standards, and European Union regulatory requirements connect technical assessment with oversight needs. The framework provides a structured basis for assessing both system performance and the credibility of the evidence supporting it, with empirical validation across deployment contexts remaining an essential next step.
Read the full abstract ▾
All authors Shaina Raza, Ahmed Y. Radwan, Imran Liaquat, Kathryn Hume
Artificial Intelligence
EconSkills: Studying Skill Transfer and Retrieval for Web Agents on Live Economic Data
Yinzhu Quan and Zefang Liu
Web
agents often revisit the same sites, yet most evaluations discard the procedures learned in earlier successful interactions. We introduce EconSkills, a skill library and evaluation framework that distills verified EconWebArena trajectories into parameterized standard operating procedures for retrieving live economic data. Each skill records its scope,
navigation procedure, site-specific guidance, verification checks, and recovery steps while replacing source-instance values with placeholders. EconSkills separates two questions: whether a known relevant procedure transfers to a held-out task, and whether an
agent can retain that benefit when selecting from a library. In controlled transfer, matched skills improve success over no-skill prompting and require fewer steps on paired successes. Under the evaluated
prompt formats, the parameterized skill
prompt substantially outperforms the corresponding raw-trajectory
prompt. With the full 50-skill library,
retrieval is competitive with the no-skill baseline overall and performs best on tasks with a direct family match; approximate matches on other tasks offset these gains. Browser trajectories further identify when procedural guidance shortens portal-specific
navigation and when semantic verification remains necessary. These results establish that reusable economic web procedures can transfer across task instances and provide a concrete design target for match-aware selection and context delivery.
Read the full abstract ▾
Artificial Intelligence
An Architecture for Long-Horizon Agents: Levels, Ticks and Cascaded Intelligence
Erik Nijkamp, Anurag Koul, Egor Pakhomov et al. (+1 more)
Language-model
agents are increasingly asked to carry out work spanning days or weeks, such as an operations remediation or a research programme. Such a task outlives any context window, any process and any interval at which a person can attend. In this paper, we argue that a long-horizon
agent must run continually without forgetting before it can learn continually. This ability lies in the harness around the model rather than in the model itself. We derive seven bottlenecks from the long-horizon setting and answer them with a hierarchical architecture of three parts: (i) levels indexed by time scale, each keeping a bounded file summarising the level below; (ii) a clocked tick as the unit of autonomous action; and (iii) cascaded intelligence, where work is escalated to a more capable model only after failing review. We report on a ten-day campaign in which an
agent built on this architecture reproduced a published reinforcement-learning result with a human attending once a day, and show (1) the
agent kept the thread across every context reset and session boundary of the campaign, (2) operating knowledge written early changed later behaviour with no change to model weights, and (3) where learned components would enter such a system. Overall, our experience suggests continual learning for these
agents needs a substrate outliving every context and process, and the checks the harness already runs are where a learner belongs.
Read the full abstract ▾
All authors Erik Nijkamp, Anurag Koul, Egor Pakhomov, Bo Pang