Artificial Intelligence · Cross-listed from cs.LG
FunL2O: LLM-Guided Feature Function Design for Learning to Optimize
Bingheng Li, Junyang Cai, Yupeng Zhang et al. (+3 more)
Learning-to-optimize (L2O) methods accelerate repeated optimization by training models to predict solutions, warm starts, branching decisions, or other forms of solver guidance. A critical yet largely overlooked component of these pipelines is the feature function that maps problem instances to inputs for machine learning models. Existing L2O methods typically rely on hand-crafted features, making representation design manual and largely fixed across domains. We introduce FunL2O, the first unified framework for automating feature design through LLM-driven program
evolution for L2O. In a FunSearch-style loop, an LLM proposes executable feature functions, while a fixed evaluation process retrains the original L2O model and measures downstream optimization performance. We evaluate FunL2O on linear and quadratic programming tasks involving solution prediction and warm-starting, as well as on mixed-integer optimization tasks using GNN-guided
backdoor branching and Predict-and-Search. Across continuous and discrete optimization tasks and four LLMs, the evolved features consistently outperform hand-crafted representations. These results establish LLM-driven feature
evolution as a general and effective approach to automating representation design in L2O.
Read the full abstract ▾
All authors Bingheng Li, Junyang Cai, Yupeng Zhang, Bistra Dilkina, Jayant Kalagnanam, Dzung T. Phan
Artificial Intelligence
Beyond the Bidirectional Promise: Re-evaluating the Robustness of Diffusion Language Models
Saurabh Yadav, Badri Narayana Patro and Vijay Srinivas Agneeswaran
Diffusion Language Models (DLMs) offer a compelling alternative to autoregressive (AR) generation by enabling bidirectional context and iterative refinement. However, their reliability under natural input noise and
adversarial attacks remains under-explored. To address this, we systematically evaluate DLM robustness and calibration against AR baselines, using two parameter-matched pairs (LLaDA-8B vs. LLaMA-3-8B and Dream-7B vs. Qwen2.5-7B) across 32 natural perturbation conditions,
adversarial gradient probes, and mechanistic hidden-state analyses. This paired design effectively isolates architecture-intrinsic properties from weight-dependent behaviors. We find a nuanced robustness profile: while highly
stochastic DLM loss landscapes naturally resist gradient-based
adversarial suffixes, they provide no guaranteed defense against natural noise, proving that everyday robustness is weight-dependent rather than inherently architectural. Furthermore, DLMs exhibit systematic overconfidence, presenting a practical deployment hazard. Most crucially, mechanistic probing reveals that all models perfectly encode input corruption, isolating behavioral fragility entirely to a decoder routing failure. Consistent with this diagnosis, we show that surface-level
prompt patching fails to improve over noisy baselines. Ultimately, DLM robustness cannot be patched on; it must be fundamentally integrated into the iterative decoding loop.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Same Illness, Different Voice: Clinical Language Models Lose Accuracy When Patients Speak for Themselves
Prabhjot Singh, Pritam Deka and Vijay Chennareddy
Clinical
language models are evaluated on vignettes written in a clinician's voice, but patients describe the same illness in their own. We pair 1,000 MedQA cases with three audited retellings (clinical, socioeconomic, cultural) and test 12 open models. Every model is less accurate when the patient speaks in a marked voice, by 9.6 points on average (95% CI 8.2 to 11.0), with no detectable shrinkage at larger scale. Matched controls trace the penalty. Generation temperature does not explain it, a plain first-person paraphrase that states every fact accounts for 2.4 points, and attaching the original vignette to the marked narrative recovers 7.0. We read this mainly as a failure to use facts expressed in patients' own words, not as a reaction to social cues, although our voices bundle both. Chain-of-thought and explicit debiasing instructions together close about a fifth of the gap. Having the same model first restate the account as a clinical vignette halves it and raises marked-voice accuracy by 3.9 points, whereas a structured-schema pipeline closes the same gap but is 7.1 points less accurate than the rewrite. Rewriting also invents plausible details, which we quantify. Code, data and analysis scripts: https://github.com/prabhjotschugh/narrativeshield-sdoh-medqa
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System
Haodong Li, Tianfei Ren, Xiaoxiao Ma et al. (+25 more)
Text-to-
video models have achieved remarkable visual quality, yet they still struggle to generate physically consistent dynamics because the temporal
evolution of a scene must be inferred implicitly from a highly compressed text
prompt. Existing chain-of-thought approaches introduce intermediate plans or visual states, but these representations are typically non-executable or temporally sparse, limiting their ability to instantiate and control the complete spatiotemporal process. To address this limitation, we introduce VideoCoCo, an agentic dual-engine framework in which executable Blender code serves as a process-level chain of thought. Given a text
prompt, a coding
agent synthesizes a Blender program that explicitly specifies the scene and its temporal
evolution. The executable simulation engine runs the program to produce a deterministic spatiotemporal draft, which is subsequently transformed into a photorealistic
video by a generative
video engine through draft-conditioned editing. This decomposition separates process-level
reasoning from high-fidelity visual realization. To adapt the
video editor to simulated drafts, we construct VideoCoCo-3K, a curated
dataset of draft-instruction-target triplets. VideoCoCo improves the OmniWeaving baseline from 0.475 to 0.558 on PhyGenBench and from 52.18 to 77.88 on VBench-2.0, achieving the best average score on both
benchmarks. These results demonstrate that executable code provides an effective, controllable, and inspectable intermediate representation for physically consistent
video generation.
Read the full abstract ▾
All authors Haodong Li, Tianfei Ren, Xiaoxiao Ma, Chunmei Qing, Zhen Fang, Sipeng He, Ziyu Guo, Haoyu Wu, Juanxi Tian, Yihang Zou, Ruichuan An, Dongzhi Jiang, Boxue Yang, Ji Xie, Xu Huang, Wenhao Yan, Jialv Zou, Zhengrong Yue, Yaxin Luo, Xiaotong Li, Yuzhu Wang, Junyan Ye, Jinjing Zhao, Zehui Chen, Lin Chen, Renye Yan, Feng Zhao, Pheng-Ann Heng
Artificial Intelligence · Cross-listed from cs.CR
RoguePrompt: Dual-Layer Encoding for Self-Reconstruction to Circumvent LLM Moderation
Benyamin Tafreshian and Prathamesh Dhake
Large
language models (LLMs) are becoming increasingly integrated into mainstream development platforms and daily technological workflows, typically behind moderation and safety controls. Despite these controls, preventing
prompt-based policy evasion remains challenging, and adversaries continue to "jailbreak" LLMs by crafting
prompts that circumvent implemented safety mechanisms. Prior work has established cipher-mediated interaction, code-embedded decryption,
prompt decomposition and reconstruction, and layered custom encryption as viable attack primitives. However, reported evaluations generally collapse visible acceptance, successful recovery of the concealed request, and subsequent execution into an aggregate attack-success outcome. This leaves limited evidence about where multistage
prompt-transformation attacks fail within an observable black-box interaction. This paper introduces RoguePrompt, a jailbreak pipeline that partitions a forbidden
prompt and applies two nested encodings, Vigenere followed by ROT13, along with natural-
language reconstruction instructions. RoguePrompt was developed and evaluated under a black-box threat model, with only API or user-interface access to the hosted models, and was tested on 313 real-world, hard-rejected
prompts. Success was measured in terms of moderation bypass, instruction reconstruction, and execution when the relevant stage exceeded its automated criterion. RoguePrompt achieved average rates of 93.93% for filter bypass, 79.02% for reconstruction, and 70.18% for execution. These results demonstrate the effectiveness of layered
prompt encoding while providing stage-level evidence of where multistage jailbreaks fail during moderation bypass, instruction reconstruction, and execution.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation
Alexi Gladstone, Heng Ji and Yilun Du
The deep learning revolution, kicked off by AlexNet, taught us that end-to-end training beats decomposing a problem into hand-designed stages. Generative modeling, however, has remained the exception-despite generative models being remarkably capable, they are still not trained end-to-end. This is because, at its core, generative modeling is about handling distributions with many modes, and existing scalable approaches handle this the same way, by factoring the generation procedure, which prevents end-to-end generation. In this work, we introduce Explorative Modeling, a new paradigm that instead factors the training loop, exploring K candidate matches between model generations and data, and training on the best, so predictions commit to modes rather than blurring them. We find Explorative Models (XMs) useful in two settings. First, increasing exploration adds a third pretraining axis beyond parameters and data for existing generative models-where scaling exploration monotonically improves performance across both continuous and discrete domains (images,
video, and
language). Notably, gains from exploration increase with scale, climbing from 7% to 36% as data scales and from 13% to 23% as models grow, with efficiency gains more than doubling at 3x the compute. Concretely, exploration improves FLOP efficiency by 4.1x, sample efficiency by 6.2x, parameter efficiency by 47%, lifts the strongest of image-generation recipes to a near-state-of-the-art 1.43 FID on ImageNet without guidance, enables scaling how end-to-end existing models are, and unlocks scaling generalization. Second, XMs enable end-to-end reconstructive generative modeling, matching
diffusion on control tasks with 16-256x fewer inference steps. Together, these results establish XMs as both a new pretraining axis for existing generative models and a standalone end-to-end generative modeling paradigm.
Read the full abstract ▾
Artificial Intelligence
SkillMentor: LLM Agent Self-Evolution via Learning Blind-Spot Diagnosis
Xiaoyi Bao, Yuanzhen Xie, Yunzhi Tan et al. (+5 more)
Agent self-
evolution has primarily focused on learning how to act, while overlooking an equally important capability: learning to discover what an
agent does not know. Existing approaches typically assume that failure discovery is given, focusing on how to repair failures once they are identified. We ask whether blind-spot diagnosis itself can be learned. We thus study diagnosis as an
agent capability separate from execution, and exclude two alternative sources of progress: executor adaptation and human supervision. Under these constraints, performance cannot improve through executor updates or annotated examples, forcing all improvements to originate from the learned diagnostic capability. We propose SkillMentor, which trains a Mentor policy via reinforcement learning to generate diagnostic tasks, identify recurrent failure modes, and curate them into reusable corrective skills. Across AppWorld and BFCLv3, SkillMentor improves executor performance by an average of 44.2%. These results suggest that blind-spot diagnosis is a learnable capability, enabling self-
evolution without updating executor weights or relying on human-curated data.
Read the full abstract ▾
All authors Xiaoyi Bao, Yuanzhen Xie, Yunzhi Tan, Jinghang Gu, Zhongqing Wang, Chu-Ren Huang, Bo Hu, Zang Li
Artificial Intelligence
PAUSE: A User-Centric Benchmark for Personal AI Assistants in Unified Service Environments
Haoyu Chen, Xirui Shi, Yuyao Wang et al. (+2 more)
Personal AI assistants are increasingly deployed as task-oriented, tool-augmented
agents that operate within unified service environments to support everyday user activities. In realistic settings, such assistants must reason over persistent user state, respect user-specific configurations and permissions, and sustain long-horizon, constraint-aware interactions across multiple services. Existing
benchmarks, however, often fragment service contexts or abstract away user state, limiting their ability to evaluate user-centric personal assistant behavior in realistic service settings. We introduce PAUSE, a user-centric
benchmark for evaluating personal AI assistants in stateful, service-integrated environments. PAUSE captures core challenges of real-world assistant deployment by requiring
agents to coordinate actions across heterogeneous user-owned resources while maintaining consistency with environment state, authorization constraints over multi-turn interactions. The
benchmark incorporates explicit user-
agent interaction via realistic user simulation, enabling evaluation beyond static tool execution. To support principled and reproducible evaluation, PAUSE adopts a multi-regime evaluation framework aligned with task characteristics. Open-ended service management tasks are assessed using semantic and trajectory-level behavioral metrics, while constraint-intensive tasks admit deterministic, state-based verification.
Benchmark results show that even state-of-the-art proprietary models fail to reach 70% task completion on scenarios requiring stateful
reasoning and configuration awareness, revealing consistent and interpretable failure patterns. Finally, we present a user-centric synthesis pipeline that enables scalable generation of coherent service environments, user configurations, and reliably annotated tasks, supporting
benchmark extensibility and future research.
Read the full abstract ▾
All authors Haoyu Chen, Xirui Shi, Yuyao Wang, Jerry Chen, Di Niu
Artificial Intelligence
PIE-APT: Abductive Planning over Temporal Dynamic Knowledge Graphs via Incremental Reasoning
Amir Hossein Sharafi and Alireza Shahbazi
Planning over Temporal Dynamic Knowledge Graphs (TDKGs) presents theoretical challenges in open-world environments with incomplete information. Existing action formalisms often face decidability issues and the Ramification Problem, while structural abduction requires expansive combinatorial search spaces. We introduce a unified framework with two modules–PIE-Abducer (incremental direct-derivation abduction) and PIE-APT (Abductive Planning for TDKGs)–operating natively on the expressive SROIQ Description Logic. Modeling state transitions as non-monotonic updates to deductively closed DL theories, we represent actions natively in OWL. This leverages an incremental reasoner to preserve decidability and natively bypass the Ramification Problem. To address incomplete knowledge, PIE-Abducer circumvents Minimal Hitting Set (MHS) enumeration. Instead of combinatorial search, it injects the logical negation of a goal into a consistent DL branch and synthesizes missing premises via direct refutation consequences. PIE-APT employs a recursive Generate-and-Test architecture, interleaving backward-chaining A* search with PIE-Abducer to synthesize both action sequences and abductive assumptions. Candidates undergo strict validation via forward-chaining Temporal Projection to evaluate logical trajectories. We evaluate four OWL
benchmarks targeting semantic abilities missing from classical planning: parameterized goals with witness search, mid-search DL entailment, open-world assumption injection, and
adversarial plan synthesis. Results show qualitative superiority over classical planners and prove our direct-derivation approach significantly outperforms an MHS-faithful baseline in abductive enrichment.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Benchmarking the Residual: What Long-Horizon Evaluations Add Beyond Matched Short-Task Performance
Chao Peng, Zhiheng Lyu, Peijie Dong et al. (+2 more)
Long-horizon
benchmarks often show that
agents fail more as tasks become longer. This observation is useful for deployment, but it does not by itself explain why failure occurs. More stages create more opportunities for ordinary errors to compound; longer tasks may also contain harder individual decisions or become harder as conversation history, tool outputs, and environment changes accumulate. We use trajectory-induced degradation to mean this last possibility: earlier execution makes later work harder. When the harmful accumulation is specifically the text visible to the model, it is often called context rot. In this position paper, we argue that to claim a "long-horizon failure",
benchmarks must compare actual full-task success against a baseline prediction built from short, individual stages. We call the log-ratio between this prediction and actual success the horizon residual. The comparison must use the same
agent configuration and specify in advance how stages, checkpoints, information, and budgets will be chosen. The residual shows that the full rollout differs from the chosen baseline; targeted experiments are still needed to explain why.
Read the full abstract ▾
All authors Chao Peng, Zhiheng Lyu, Peijie Dong, Hande Dong, Qiang Lin
Artificial Intelligence · Cross-listed from cs.LG
Flat Score, Amplified Failures: How the Error Budget Masks Damage in Quantized LLM Agents
Jiwon Jang, Kisu Yang, Heuiseok Lim et al. (+1 more)
Post-training quantization to 4-bit weights is widely reported to be nearly lossless. We test this claim for multi-turn, tool-calling
agents, where it now matters most. On $\tau^2$-bench, across two open-weight model families in dense and MoE variants and two domains (eight
cells, 456 episodes each, at 16-, 8-, and 4-bit weights), quantization indeed looks free on the standard metric. No
cell shows a score change that survives multiple-comparison correction, and in the
cell that carries the largest process damage, equivalence testing bounds the change within $\pm$7.5 points. The process tells a different story. Quantization amplifies the failure the model already exhibits at full precision (tool-name
hallucination in telecom, with the same directional trend in retail entity errors) by up to 2.5$\times$ in volume (+17.6 points per task), while creating essentially no new failures. The failure set is the same at every precision (rank correlation $\geq$ 0.94, 0.18% novel events). The score stays flat because the
benchmark's ten-error budget absorbs the extra failures. Shrinking the budget to two errors re-exposes a score gap of 17 points, and it does so only in the one
cell where quantization added error volume, exactly as the masking account predicts. A targeted error-repair
prompt, run for five telecom models at every precision, removes the damage exactly and only where it lives. Both diagnostics, the per-channel error rate and success under a shrinking budget, come from logs
benchmarks already collect; we suggest reporting them alongside task reward.
Read the full abstract ▾
All authors Jiwon Jang, Kisu Yang, Heuiseok Lim, Hyunwoo Park
Artificial Intelligence · Cross-listed from cs.CR
FAVA: Formal Authorization for Verified Agents with Evidence-Backed Permission Graphs
Yifan Zhang, Xinkui Zhao, Sai Liu et al. (+3 more)
Large
language model (LLM)
agents autonomously interleave semantic
reasoning with complex system operations. In these dynamic environments, static tool-level permissions are fundamentally insufficient; safe authorization is highly context-dependent and heavily reliant on evolving runtime states and data flows. We present FAVA (Formal Authorization for Verified
Agents), a permission-carrying authorization framework for
agent execution. FAVA utilizes an LLM-guided Permission Intermediate Representation (IR) to translate ambiguous natural-
language tasks into structured constraints. A deterministic lowering pass then converts this IR into an evidence-backed permission graph that explicitly tracks data flows, dependencies, and contextual labels. To provide strict security guarantees, a Satisfiability Modulo Theories (SMT) authorizer mathematically verifies the current graph against security policies before any effectful action executes. A runtime gateway then enforces the solver's result, either authorizing the execution or intercepting it with a precise counterexample. We evaluate FAVA across OpenAgentSafety, OctoBench, and ActPlane scenarios. Our evaluation demonstrates that FAVA achieves a 90.5% Decision Compliance Rate (DCR) over the aggregate
dataset, successfully intercepting dynamic violating traces in the evaluated trace-conditioned scenarios.
Read the full abstract ▾
All authors Yifan Zhang, Xinkui Zhao, Sai Liu, Hengxuan Lou, Guanjie Cheng, Chang Liu
Artificial Intelligence · Cross-listed from quant-ph
LLM-Guided Initialization for Accelerated Hybrid Quantum-Classical Medical Image Classification
Riza Alaudin Syah, Irwan Alnarus Kautsar and Haza Nuzly Bin Abdull Hamed
Variational
quantum algorithms often encounter barren plateaus, where cost gradients decay rapidly with increasing
circuit depth, undermining the trainability of parameterized
quantum circuits. This paper evaluates AdaInit (Adaptive Initialization), proposed by Zhuang and Cunningham, which uses large
language models to propose initial parameters for
quantum neural networks. We study a simplified single-query AdaInit variant paired with GPU-accelerated simulation in NVIDIA CUDA-Q and apply it to binary classification on the DMR-IR mammography
dataset. AdaInit delivers 14.6 times higher gradient variance at initialization than random initialization (0.0095 vs. 0.0006), producing 160 times faster convergence (1.1s vs. 176 s) while maintaining the same classification accuracy of 61.4 percent. We provide theoretical analysis grounded in the geometry of parameterized
circuit landscapes and show empirically that LLM-guided initialization places the optimizer in trainable regions of parameter space. Beyond performance, our results indicate that a single LLM query can yield informative parameters without iterative refinement, suggesting a low-overhead path to improved trainability. The findings validate AdaInit in a medical imaging setting and demonstrate its compatibility with GPU-accelerated
quantum backends for practical speedups.
Read the full abstract ▾
Artificial Intelligence
Can AI agents conduct open-ended AI research? Early evidence from two case studies
Peter Kirgis, Sayash Kapoor, Andrew Schwartz et al. (+21 more)
Forecasts of explosive AI progress hinge on AI
agents automating AI research. But evidence on whether
agents can carry out open-ended AI research is thin. Current evaluations either test
agents on narrow, verifiable tasks, which excludes open-ended research, or submit AI-generated papers to blind peer review, which is overstretched,
stochastic, and suffers from poor review quality. We introduce a third way to measure progress towards AI R&D automation. An
agent takes on the central, open-ended research question of a high-quality unpublished paper, and the paper's original authors grade its output. We call these shadow evaluations. We ran shadow evaluations on two unpublished NeurIPS 2026 submissions, giving frontier
agents six days and thousands of dollars of compute. The
agents completed all of the engineering without human help, yet could not make substantial progress towards answering the research questions. As a result, both papers were unambiguously rejected by the authors. We identify five recurring failure modes: poor judgment about the bar for publishable research, uncreative responses to shortcomings in the research design, ineffective backtracking from dead ends, poor resource awareness, and instruction drift. A robustness check with a second model and scaffold reproduced these failures. We release the expert reviews, survey responses,
agent repositories, and logs. Our results provide early evidence that today's
agents can do the engineering of AI research, but struggle with critical parts of the research lifecycle.
Read the full abstract ▾
All authors Peter Kirgis, Sayash Kapoor, Andrew Schwartz, Stephan Rabanser, David Africa, Konstantinos Voudouris, Viet Nguyen, Toby Pilditch, Magda Dubois, Harry Coppock, Cozmin Ududec, Nitya Nadgir, Matilda Orona, Tilman Bayer, Derrick Chan-Sew, Yue Ling, Abhishek Shetty, Helen Toner, Gillian Hadfield, Seth Lazar, Steve Newman, Shoshannah Tekofsky, Rishi Bommasani, Arvind Narayanan
Artificial Intelligence · Cross-listed from cs.CL
APEX-Accounting
Julien Benchek, Austin Bennett, Jasmin Kern et al. (+8 more)
We introduce APEX-Accounting, a
benchmark built by Mercor in partnership with Ramp, to assess whether frontier models can do the real work of accountants. Tasks include reconciling accounts, accruing expenses, posting transactions, and producing reports. The private eval set comprises 160 tasks, split across 10 worlds. Each world contains an accounting system, as well as spreadsheets, PDFs, and other files. Every task was authored and solved by experts in accounting and bookkeeping, who also wrote grading rubrics. Across nine frontier models, Claude-Fable-5 (Max) leads with 56.4% Mean Criteria@3, ahead of Muse-Spark-1.1 (xHigh) at 52.6%. No model scores more than 2.6% Pass^8 (GPT-5.6-Sol (Max+Pro)) and the highest Pass@8 is 21.5% (Muse-Spark-1.1 (xHigh)). We experiment with increasing the
token budget from $1 to $50 and observe an instance of Simpson's paradox: scores increase as the
token budget increases but within a given budget-constrained harness, scores are lower on tasks where the model spends more
tokens. As APEX-Accounting is a closed
benchmark, leaderboard evals can be run for any frontier model on request.
Read the full abstract ▾
All authors Julien Benchek, Austin Bennett, Jasmin Kern, Ryan Stevens, Rene Sultan, Charis Ching, Hayley Popiel, Vaibhav Mittal, Felix Mercier, Brendan Foody, Bertie Vidgen
Artificial Intelligence · Cross-listed from cs.HC
The Social Cost of an AI Teammate: How an Artificial Teammate Reshapes Human-Human Communication in Small-Team Decision-Making
Nia Nixon, Jaeyoon Choi, Pedro Martins De Bastos et al. (+3 more)
Conversational AI is increasingly positioned as a teammate rather than a tool, yet little is known about how its presence reshapes communication among human teammates. We examined sociocognitive communication dynamics in a team decision-making task using Group Communication Analysis (GCA), surveys, and lexical analyses. Sixteen teams of two students and an AI teammate and 17 all-human teams of three completed a high-stakes moral-dilemma task. Mixed-effects models showed that the AI participated more and was more internally cohesive but contributed less new and less dense content than students. Compared with controls, students on AI-inclusive teams showed lower participation, responsivity, and social impact and reported lower belonging, status, and connection. Event-locked models found no condition differences in trajectories of socioemotional content or student-student linguistic style matching. These findings suggest a social cost to students' experienced team membership and relational integration in AI-inclusive teams, although the temporal analyses do not establish when this cost emerged. We discuss implications for future research in voice-based and longitudinal settings.
Read the full abstract ▾
All authors Nia Nixon, Jaeyoon Choi, Pedro Martins De Bastos, Mohammad Amin Samadi, Seehee Park, Spencer JaQuay
Artificial Intelligence
Partner Capability Estimation for Task-Agnostic Adaptation in Ad-Hoc Teamwork
Peter Tisnikar, Maja Swieczkowska, Benteng Ma et al. (+2 more)
Effective collaboration with novel and diverse partners is a crucial skill for autonomous
agents. Most current ad-hoc teamwork (AHT) approaches assume that
agents will collaborate on a single, fixed task and that the partner's capabilities, their ability to successfully execute the desired action, are already known. In reality, a partner's true capabilities are often hidden, and human collaborators may act sub-optimally on tasks with multiple valid strategies. To address these limitations, we extend ad-hoc teamwork into a multi-task setting by re-framing it as a problem of joint planning with decentralised execution under hidden partner capabilities. We introduce CE-CM (Capability Estimation via Contextual Models), an approximate
Bayesian method that infers task-invariant capability vectors. By using simulation-based sampling, the
agent estimates capabilities and induces a contextual Multi-
agent Markov Decision Processes for planning. This approach requires no population pre-training and refines its beliefs online from just a few tasks. To account for human unpredictability, we propose CE-CM-Div, an extension that evaluates capability hypotheses against diverse planner rollouts rather than a single optimal trajectory. Simulated experiments demonstrate that CE-CM rapidly recovers hidden capabilities, reduces infeasible action assignments, and adapts to changes over time. Furthermore, in an offline human study of 225 trajectories from 15 participants, CE-CM-Div substantially improved capability estimates over the baseline CE-CM method. Our results suggest capability-based modelling is a promising interpretable, task-agnostic representation in the studied settings, demonstrating that accounting for behavioural diversity is essential for robust human-AI teaming.
Read the full abstract ▾
All authors Peter Tisnikar, Maja Swieczkowska, Benteng Ma, Gerard Canal, Matteo Leonetti
Artificial Intelligence · Cross-listed from cs.IR
Improving Item Discoverability in e-Commerce Search via Related Intent Generation
Ji Xin, Xiao Xiao, Ishan Bhatt et al. (+6 more)
Traditional search systems are optimized to retrieve items that strictly match a query, often prioritizing precision over recall. In e-commerce marketplaces and particularly grocery, this paradigm is limiting, as user satisfaction and commercial outcomes depend heavily on the discoverability of substitute, complementary, and thematically related items. In this paper, we present a scalable system for discovery-augmented search that leverages intent-conditioned recall expansion. Our approach generates implicit user intents to expand candidate recall while maintaining relevance. The system addresses the cost-quality tradeoff of generative
retrieval through a two-stage hybrid architecture. First, we leverage closed-weight large
language models (LLMs) to maximize discoverability for head queries. To extend these benefits to tail queries, we then introduce a finetuned small
language model (SLM), trained via LoRA adapters and teacher-student
distillation. We evaluate the system using a rigorous dual framework: (a) LLM-as-a-judge metrics validated against human preferences for semantic quality, and (b) end-to-end session-level purchase analysis. Results demonstrate that our approach improves both intent generation quality and downstream
retrieval effectiveness, extending discovery coverage from approximately 60% to 80% of query traffic at roughly 30% of the teacher model's inference cost, offering a viable path for deployment in large-scale marketplaces. Beyond relevance gains, discovery-augmented search may serve as a marketplace-balancing mechanism, giving long-tail and emerging supply an opportunity for query-conditioned exposure.
Read the full abstract ▾
All authors Ji Xin, Xiao Xiao, Ishan Bhatt, Vinesh Gudla, Trace Levinson, Raochuan Fan, Shishir Kumar Prasad, Prakash Putta, Tejaswi Tenneti
Artificial Intelligence
OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding
Jingbo Zhou, Yusai Zhao, Qi Bao et al. (+12 more)
Large
language model (LLM)
agents are increasingly expected to assist users in completing tasks. However, existing
benchmarks provide limited support for evaluating whether
agents can carry out office-suite workflows at a reasonable cost. We introduce OmegaUse-OfficeVal, a
benchmark for evaluating LLM
agents on long-horizon office-suite tasks with task-level economic grounding. The
benchmark comprises 100 tasks derived from office-suite requests proposed by practitioners and adapted through a
privacy-preserving process. On average, these tasks require 2.32 hours of human labor to complete. An important feature of the
benchmark is that each task is paired with two economic signals: human labor time and task price proxy. These signals enable direct comparisons between human costs and LLM inference costs, as well as value-weighted evaluation. To support stable evaluation, we develop code-based verifiers from fine-grained rubrics. We evaluate several frontier LLMs together with a human baseline. Although all evaluated LLMs are substantially cheaper and faster than human workers, they have not yet approached human-level deliverable quality. The code and
dataset are fully open-sourced, and more information is available on our project website: https://omegause-officeval.github.io.
Read the full abstract ▾
All authors Jingbo Zhou, Yusai Zhao, Qi Bao, Jingjia Cao, Zhenghai Chen, Chang Gao, Kaiqi Guo, Muxin Guo, Mingxuan Li, Xinjiang Lu, Yanru Ma, Yixiong Xiao, Zenghui Zhang, Le Zhang, Hua Wu
Artificial Intelligence · Cross-listed from cs.CV
Anatomy Contextualized Adaptation of CT Foundation Models
Roshan Kenia, Stephanie L McNamara and William Lotter
CT
vision-
language foundation models have demonstrated promising performance across downstream tasks, but are typically trained with whole-volume representations that dilute fine-grained anatomical signals. Fine-grained
vision-
language pre-training addresses this by aligning anatomy-level visual features with anatomy-specific text, but in doing so discards the global context that whole-volume models provide. Furthermore, existing fine-grained approaches train from scratch, making them computationally expensive. We introduce Anatomy Contextualized Adaptation (ACA), a lightweight framework that adapts frozen CT foundation model representations for anatomy-level
vision-
language alignment while enhancing global contextualization. ACA uses TotalSegmentator to decompose CT volumes into anatomy-level
embeddings, which are refined via a
transformer that captures cross-anatomy relationships, and aligned to both per-anatomy and scan-level text extracted from radiology reports. Evaluated on Merlin and CT-RATE, ACA consistently outperforms both the frozen foundation model baselines and existing fine-grained methods in zero-shot finding classification, while requiring less than one hour of training once
embeddings are cached. The
attention weights learned by ACA's inter-anatomy
transformer additionally indicate plausible cross-anatomy context routing. Altogether, these results support ACA as a lightweight approach for adapting CT foundation models to anatomically grounded
vision-
language alignment while preserving and enhancing global anatomical context.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Cost-Sensitive Conformal Prediction and Human-in-the-Loop Abstention for Imbalanced High-Stakes Decision Support: A Multi-Domain Benchmark
Manpreet Singh, Akshatha Srikantha and Shyamal Lakhanpal
High-stakes decision systems in credit scoring, fraud detection, healthcare, and industrial safety require reliable uncertainty quantification under severe class imbalance and asymmetric error costs. Standard marginal conformal prediction (CP) provides valid overall coverage guarantees; however, we show that it severely under-covers rare, costly minority classes, with minority-class coverage dropping to as low as 0.5% on certain
datasets. To characterize and address this limitation, we conduct a comprehensive
benchmark comparing marginal CP, class-conditional (Mondrian) CP, and cost-controlled abstention mechanisms across 15 real-world imbalanced tabular
datasets, 7 classification models, 3 probability calibration techniques, and 10 random seeds, resulting in 3,150 experimental runs. Our results show that Mondrian CP restores valid minority-class coverage, achieving an average minority-coverage improvement of 61.7 percentage points over marginal CP (p < 1e-80). Furthermore, combining Mondrian CP with cost-controlled abstention significantly reduces expected decision cost compared with standard decision boundaries, confidence-based rejectors, and risk-controlled rejectors under realistic human review budgets. We further quantify
dataset-specific break-even thresholds at which deferring ambiguous instances to human experts becomes cost-effective. These findings provide practical guidance for deploying distribution-free, cost-aware uncertainty quantification in high-stakes decision support systems.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
DLAM: Distributional Latent Actions with Temporal Constraints
Zuojin Tang, Feifan Luo, Haoyun Liu et al. (+10 more)
Vision-
language-action (VLA) models remain constrained by scarce action-labeled
robot data, whereas action-free
videos offer abundant observations of physical change. Latent action models can extract such priors, but reconstruction-trained codes may predict future observations without the structure required for joint generation with
robot actions. Existing structured methods add temporal constraints but retain deterministic transition points, so residual errors in locally inferred transitions may propagate and compound under recursive composition. We introduce DLAM, a distributional latent-action model that represents each transition as a diagonal Gaussian. Reconstruction conditioned on the reference frame grounds the mean in observed visual change, while normalized composition and reversal over equal-gap triplets constrain both the mean and dimension-wise variance. Variance composition uses a lightweight shared-correlation coefficient to account for dependence between adjacent transitions that share an intermediate frame, whereas reversal negates the mean and preserves the variance. For downstream policy learning, we freeze the encoder and train a flow-matching policy to jointly generate mean transition sequences and
robot actions. On held-out transitions, DLAM learns more temporally consistent latent dynamics than existing latent-action baselines and achieves stronger direct and cumulative reconstruction on held-out
videos. Under the same controlled $\pi_0$ transfer protocol, it also improves policy performance on MetaWorld MT50, LIBERO, and real-world manipulation tasks. Controlled ablations show that normalized mean constraints account for most of the reconstruction gain, while learned variance and correlation-aware composition provide complementary improvements in downstream control.
Read the full abstract ▾
All authors Zuojin Tang, Feifan Luo, Haoyun Liu, Botai Yuan, Dekang Qi, Ronghan Chen, Yandan Yang, Tong Lin, Xinyuan Chang, Mu Xu, Bin Liu, De Ma, Zhiheng Ma
Artificial Intelligence
Linguistic Monoculture in LLM-Assisted Language Use
Suhas Thejaswi, Juhi Kulshreshta and Lutz Oettershagen
Writing and communication are increasingly mediated by large
language models (LLMs) that are being used to draft, revise and polish text. Although such assistance can improve clarity and help authors meet institutional expectations, widespread reliance on shared models may reduce population-level variation in linguistic form, a phenomenon we refer to as linguistic monoculture. We develop a mathematical framework in which authors and LLMs are represented as distributions over linguistic features and coevolve through repeated interaction. We analyze three interaction mechanisms: a shared model with a fixed linguistic distribution, a shared model recursively updated from author outputs, and personalized models updated through author-specific and population-level feedback. We characterize the resulting
equilibria and convergence rates, showing that, shared models can drive authors toward a common norm, recursive feedback relocates the shared norm without altering pairwise spread under common conformity, and personalization can preserve a family of distinct author-model
equilibria with nonzero linguistic diversity. We then endogenize conformity as a strategic choice trading off private benefits from clarity, legibility, and perceived fluency against distinctive style. Within this utility model, individually rational authors may conform more than is socially optimal because they do not internalize the value their distinctiveness provides to others, creating a negative externality and a price of monoculture that is finite for each fixed instance but can grow without bound when distinctiveness dominates authenticity. Synthetic simulations illustrate how fixed shared assistance, recursive feedback, and personalization produce different long-run diversity outcomes.
Read the full abstract ▾
Artificial Intelligence
AgentMap: Joint Equivalence and Subsumption Discovery for Ontology Matching
Yiping Song, Jiaoyan Chen, Renate Schmidt et al. (+2 more)
Ontology matching (OM) has traditionally been formulated as either equivalence discovery or subsumption matching. The existing OM systems identify only one type of semantic correspondence and cannot simultaneously discover equivalence and subsumption mappings. In this paper, we introduce Hybrid Ontology Matching (HOM), a new OM task that unifies equivalence and subsumption discovery, and accordingly propose a Large
Language Model (LLM)-based multi-
agent OM framework AgentMap that is implemented by a series of interdependent semantic decisions. Given a concept in the source ontology, AgentMap integrates semantic
retrieval, hierarchical search, and collaborative multi-
agent LLM
reasoning to progressively explore the target ontology, identifying either the equivalent concept, if one exists, or the most fine-grained subsumer. We further extend four OM
datasets for a HOM
benchmark and evaluate AgentMap under hybrid, equivalence-only, and subsumption-only settings. Experimental results show that AgentMap achieves promising performance on the hybrid setting, and at the same time outperforms equivalence matching and subsumption matching baselines on the equivalence-only and subsumption-only settings, respectively.
Read the full abstract ▾
All authors Yiping Song, Jiaoyan Chen, Renate Schmidt, Hui Yang, Wen Zhang
Artificial Intelligence · Cross-listed from cs.SD
MMAC: A Massive Multi-dimensional Benchmark for Audio Captioning
Weijie Wu, Junbo Li, Lin Li et al. (+2 more)
With the development of audio large
language models (AudioLLMs), audio captioning needs to move from brief descriptions toward open-ended and fine-grained free-form descriptions. Existing evaluations often focus on generation quality or task performance, making it difficult to diagnose information coverage and description reliability. We propose MMAC, a Massive Multi-dimensional
benchmark for Audio Captioning. MMAC contains 5,638 audio clips from more than 20 data sources, covering 6 capability categories and 15 evaluation dimensions. Given a model-generated caption, MMAC checks whether it mentions relevant information in the target dimension and whether the mentioned content is consistent with the reference label. We evaluate representative open-source and proprietary AudioLLMs. Results show clear differences across evaluation dimensions, information coverage, and description reliability. We will release the MMAC
benchmark and evaluation code.
Read the full abstract ▾
All authors Weijie Wu, Junbo Li, Lin Li, Jun Fang, Qingyang Hong
Artificial Intelligence · Cross-listed from cs.CV
SciFigQual-Bench: A Benchmark for Scientific Figure Quality Assessment with Full-Manuscript Context
Zihan Deng, Chuanzhi Xu, Huiqi Liang et al. (+4 more)
Scientific figure quality is bound to the manuscript: a crop can be visually clear and still contradict its caption or the paragraph that cites it. Most image quality assessment and chart-understanding methods target a detached visual surface or a question-answering score, rather than
alignment among the figure, its caption, and the citing text. A single end-to-end
prompt that sees the image and the text together still mixes what is visible with what the caption and the citing paragraph claim, so fluent wording can raise a visual score and missing text can be treated as low quality. To address this gap, we introduce SciFigQual-Bench, a manuscript-linked
benchmark for published CS-conference figures that binds each figure to its caption and to index-resolved citing paragraphs, and scores visual clarity, layout, caption consistency, context consistency, and misleading risk, leaving a dimension unevaluated when its evidence is absent. SFQ-
Agent reads the image and the text in separate calls and records modality-specific evidence. A cross-modal judge scores caption and citing-text
alignment from those reports, and a deterministic runner keeps the visual scores, sets misleading risk by a fixed rule, and applies the written caps, so each dimension follows the rubric instead of a single end-to-end
prompt. Experiments comparing this staged judge with single-pass and OCR-sidecar protocols find the closest point-estimate fit to mean human ratings under staged judging, while the gap between protocols remains small. Caption consistency remains the main gap, and agreement with the rater mean answers a different question from agreement among human raters.
Read the full abstract ▾
All authors Zihan Deng, Chuanzhi Xu, Huiqi Liang, Haoyang Li, Xiaozhen Zhong, Weidong Cai, Lequan Yu
Artificial Intelligence · Cross-listed from cs.LG
Scores Are Not Decisions: Cost-Aware Stopping for Tool Acquisition in LLM Agents
Yicheng Feng, Yan Zhang, Yan Cheng et al. (+1 more)
As LLM
agents increasingly depend on diverse external services such as search engines, databases, and connectors,
agent harnesses face a fundamental tool-selection challenge: acquiring too few tools leaves the task under-informed, while too many adds cost, context load, and
privacy exposure. Routers and retrievers can rank candidate tools by relevance, but a ranking alone does not determine how many are worth selecting. Existing approaches leave acquisition under heterogeneous costs unaddressed. We formulate this decision as cost-aware marginal decision-focused stopping (CAM-DF) over ranked tool prefixes, with CAM-DF-lite as a compact interpretable variant. We train directly on the offline gap between stopping now and the best continuation: its sign labels the decision, its magnitude weights each error by the payoff at stake. We prove this objective is Bayes-aligned with the stopping target and that score-only rules are suboptimal under heterogeneous costs. We evaluate on 1,343 tasks across five tool-use domains. On $\tau$-bench Retail, CAM-DF attains the highest payoff among deployable methods, with gains over a predict-then-threshold baseline across all five ranking sources and two cost regimes. Our approach is state-of-the-art under heterogeneous costs and high cost pressure, with larger gains under weaker rankings. In live execution, CAM-DF exposes the
agent to 37% fewer tools than full access while maintaining comparable task success. The CAM-DF family is a lightweight pre-execution plugin that turns existing tool rankings into lower-cost acquisition decisions without fine-tuning the underlying LLM.
Read the full abstract ▾
All authors Yicheng Feng, Yan Zhang, Yan Cheng, Wei Qi
Artificial Intelligence
On-Policy Distillation for LLM Safety: A Routing Approach to Template-Robust Realignment
Yongjian Guo, Wanlun Ma, Lingyu Shen et al. (+2 more)
Fine-tuning is the dominant paradigm for specializing large
language models (LLMs), yet it exposes a critical vulnerability: malicious data providers can embed harmful behaviors into downstream corpora, creating models that retain professional skills while violating human values on demand. Existing safety-realignment defenses often fail in practice due to three key limitations: they frequently cause catastrophic forgetting of specialized skills; their effectiveness collapses when the defender cannot observe the attacker's
prompt template; and successfully realigned models remain susceptible to re-jailbreaking via simple system
prompt switches. To address these challenges, we propose Routing-based On-Policy
Distillation (ROPD), a novel realignment framework that models the divergence between aligned and compromised output probability distributions rather than fitting specific
prompt templates. We conduct extensive experiments comparing ROPD against four state-of-the-art baselines across three
datasets and three base models with varying
alignment strengths. Our results demonstrate that when baseline defenses face template mismatches, often accompanied by severe degradation in downstream task performance. In contrast, ROPD substantially mitigates template-mismatch risks, maintaining superior robustness in both defense effectiveness and capability preservation. While our analysis indicates ROPD is not entirely immune to template shifts, its performance degradation is negligible compared to existing methods, establishing a new standard for robust LLM realignment.
Read the full abstract ▾
All authors Yongjian Guo, Wanlun Ma, Lingyu Shen, Xi Xiao, Sheng Wen
Artificial Intelligence · Cross-listed from cs.CR
MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair
Xuanze Chen, Xukang Xie, Wentao Fu et al. (+3 more)
Memory systems allow
agents to retain and reuse information from past interactions, but they can also let malicious content persist. A malicious instruction crafted by an attacker may be stored in long-term
memory, recalled much later, and quietly shape a real action. Recent
benchmarks increasingly examine
agent memory security, yet few trace the same malicious semantics across persistence, downstream consequences, and selective repair under diverse
memory-backend comparisons. To address this gap, we introduce MemSecBench, a task-grounded
benchmark for the lifecycle security of
agent memory systems. It contains 310 cases drawn from 48 realistic contexts across code and science, daily life, and office work. Each case follows a controlled Write–Execute–Forget protocol in an isolated runtime under an exact
agent configuration, defined by an
agent harness, a
memory backend, and an LLM backend. Evidence-based adjudication combines a deterministic write check, checkpoint-specific judge-model evaluations, and programmatic gates across seven lifecycle checkpoints. The experimental design spans a 24-configuration
matrix of two
agent harnesses, four
memory backends, and three LLM backends. Across all 24 configurations, malicious
memory persists in 84.2% of all cases, and the full Write–Execute chain succeeds in 50.3%. Among successfully poisoned cases, 59.6% complete the full Execute chain, while 56.1% achieve selective repair.Compared with matched Native configurations, the largest absolute differences are 16.1 percentage points for end-to-end attack success and 41.3 percentage points for selective repair. These descriptive contrasts indicate that the evaluated
memory system stacks differ in lifecycle security, both in the propagation of malicious
memory and in selective repair after successful
memory poisoning.
Read the full abstract ▾
All authors Xuanze Chen, Xukang Xie, Wentao Fu, Jiajun Zhou, Shanqing Yu, Qi Xuan
Artificial Intelligence · Cross-listed from cs.LG
Parameter-Free Dynamic Regret under Heavy-Tailed Noise
Vaneet Aggarwal
We study online convex optimization with one unbiased
stochastic subgradient per round and noise having a finite $p$-th central moment, where $p\in(1,2]$ is unknown. For a bounded convex domain of diameter $D$, subgradients bounded by $G$, noise scale $\sigma$, and comparator path length $P_T$, let $\Lambda_T=1+P_T/D$. A single
algorithm, using none of $G,\sigma,p,P_T$, attains expected dynamic regret $O_p\left(\min\{GD\sqrt{T\Lambda_T}+\sigma DT^{1/p}\Lambda_T^{(p-1)/p},\,GDT\}\right)$ against every fixed comparator sequence. Restarted AdaGrad experts produce the noise-path exponent $(p-1)/p$, and a prior favoring longer restart intervals removes horizon-dependent logarithmic overhead. We give an explicit bound uniform in $p$; its logarithm-free form has noise coefficient $O(1+\log(p/(p-1)))$, while the static-regret constant is universal. The analysis requires only marginal noise moments and permits dependent errors. Complete pathwise proofs retain both the expert-loss range and the gradient energies preceding comparator movement. Matching lower bounds hold on every bounded convex domain of positive diameter, under the same gradient-only information model. Together with a path-budget-tuned upper bound, they characterize the minimax rate with universal constants, including its linear-regret saturation.
Read the full abstract ▾