Artificial Intelligence · Cross-listed from cs.CL
T-Mem: Memory That Anticipates, Not Archives
Weidong Guo, Dakai Wang, Zixuan Wang et al. (+2 more)
Long-term
memory is essential for conversational
agents to remain coherent across extended dialogues, follow through on commitments made many sessions earlier, and adapt their behaviour to each user. Current LLM-backed long-term conversational
memory, however, is reachability-bounded by the similarity between a query and stored content, both lexical and dense-vector. The approach is effective when query and
memory share surface features such as wording or named entities (we call this descriptive). But it misses another, equally valuable class of cases, where query and
memory do not share surface features and are tied only by a latent semantic arc (associative). On this regime prevailing long-term
memory systems collectively fail. Covering this other half is what allows an assistant, for the first time, to actively draw on past dialogue as a semantic asset. On the
memory side, this is the engineering counterpart of what cognitive science calls episodic future thinking: rehearsing past experience for the future contexts under which it will need to be found. We call these write-time rehearsals triggers. We propose T-Mem, the first long-term conversational
memory architecture that covers both descriptive and associative recall. At each of two evidence granularities, single facts and full exchanges, T-Mem instantiates one descriptive trigger family and one associative trigger family, so that every
memory remains reachable from both surface-similar and relevance-bound queries. As empirical validation, T-Mem reaches state-of-the-art on both LoCoMo and LoCoMo-Plus.
Read the full abstract ▾
All authors Weidong Guo, Dakai Wang, Zixuan Wang, Hui Liu, Yu Xu
Artificial Intelligence · Cross-listed from cs.CL
CHILLGuard: Towards Fine-Grained Chinese LLM Safety Guardrail with Scalable Data Construction and Model-aware Preference Alignment
Wenbo Yu, Bohua Wang, Hao Fang et al. (+10 more)
Malicious content generated from large
language models (LLMs) could pose severe safety risks and ethical concerns. While existing LLM safety guardrails excel in English or
multilingual settings, they lack adaptation to Chinese-specific regulatory policies, cultural context, and linguistic nuances, failing to support fine-grained risk classification for diverse deployment needs. In this paper, we introduce a 5-macro, 31-micro category fine-grained risk taxonomy for Chinese scenarios, and build CHILLGuard: a dedicated Chinese LLM content safety guardrail. To address the critical scarcity of high-quality annotated Chinese safety data, we propose a scalable multi-stage data construction pipeline: we expand multi-source corpus via
retrieval-augmented generation, generate implicit harmful samples through
prompt engineering rewriting, and refine high-quality data via multi-model voting-based label calibration. Based on this, we build CHILLGuardTrain, a large-scale training set with 405,007 samples, and CHILLGuardTest, a rigorously curated annotated test set with 51,745 samples. We then train CHILLGuard on CHILLGuardTrain under a generator-classifier collaborative framework via Model-aware Direct Preference Optimization. Extensive experiments under multiple settings demonstrate the state-of-the-art performance of CHILLGuard, e.g., a 15.92% relative improvement of F1 score over Qwen3Guard-8B-Strict on our
benchmark. We release our resources at https://github.com/cswbyu/CHILLGuard.
Read the full abstract ▾
All authors Wenbo Yu, Bohua Wang, Hao Fang, Kuofeng Gao, Jingru Zeng, Xiaochen Yang, Tianyi Zhang, Xiaoxiao Ma, Jiawei Kong, Hao Wu, Bin Chen, Shu-Tao Xia, Min Zhang
Artificial Intelligence · Cross-listed from cs.CL
Not All Skills Help: Measuring and Repairing Agent Knowledge
Yixuan Wang, Yiyang Zhou, Yiming Liang et al. (+4 more)
LLM
agents can improve without weight updates by accumulating natural-
language skills from experience, but current systems entrust every decision about which skills to keep and how to apply them to LLM judgment alone. We argue that this conflates two distinct roles: generating a skill from experience is a creative act that judgment handles well, while deciding whether that skill actually helps requires empirical evidence across many tasks. Measuring per-skill causal contributions via randomized masking, we find that skill libraries exhibit pervasive causal heterogeneity: individual skills routinely help on some task types while hurting on others, yet their opposing effects cancel in aggregate, making them invisible to global curation methods. We propose ASSAY, a framework that separates generation from curation: it computes a per-skill causal attribution on a small development set, restructures the library offline, and suppresses skills with negative predicted effect for each test task. Across seven base models spanning four providers and two
benchmarks (AppWorld and tau-bench), ASSAY consistently improves over prior skill-curation approaches. On AppWorld's hardest split, DeepSeek-V3 achieves 69.3% task-goal completion (47.4% relative improvement), a new state of the art among all published methods including weight-tuned approaches. On tau-bench retail, GPT-4.1 improves by 8.7% relative, advancing past o4-mini, o1, and GPT-4.5 on the public leaderboard without any weight modification. Ablation traces the dominant gain to per-task masking, confirming that the bottleneck is matching skills to tasks at inference time, not removing bad skills globally. Code is available at https://github.com/aiming-lab/assay.
Read the full abstract ▾
All authors Yixuan Wang, Yiyang Zhou, Yiming Liang, Congyu Zhang, Fuxiao Liu, Jiawei Zhou, Huaxiu Yao
Artificial Intelligence
Reward Hacking in Language Model Agents: Revisiting AI Safety Gridworlds
Ömer Veysel Çağatan and Xuandong Zhao
Reward hacking, where AI systems exploit misspecified objectives to achieve high reward without satisfying intended goals, remains a central challenge in AI safety. Yet most known instances have been discovered post hoc in frontier systems where controlled study is impractical. We adapt the AI Safety Gridworlds framework into a text-based evaluation suite that reformulates classic reinforcement learning safety tasks for
language-based
agents. Across frontier and mid-scale models, we find that specification gaming emerges zero-shot: models systematically achieve high observed reward while underperforming on hidden safety objectives, and even apparently safe behaviors can reflect misunderstanding rather than principled safety. Reinforcement learning does not correct these failures: direct reward optimization widens the gap between observed and hidden reward, as the model's initial competence causes it to lock into locally rewarding strategies before discovering safer alternatives. This pattern persists across model scales (1.5B–14B) and is not resolved by finer credit assignment, exploration
prompts, or
entropy regularization. Our results show that reward hacking arises naturally when optimizing proxy objectives with capable
language model
agents and resists standard mitigations, suggesting that proxy-reward failures in agentic settings may require approaches beyond standard exploration and credit-assignment fixes. To facilitate reproducibility, the code for this work is available at \href{https://github.com/asparius/verl-
agent-safety}{our public repository}.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Learning Earthquake Wave Arrival Time Picking from Labels with Inaccuracies
Sen Li, Xu Yang, S. Mostafa Mousavi et al. (+5 more)
Inaccurately labeled training data, or "label noise", poses a significant threat to the integrity of supervised machine learning models. This corruption directly degrades performance by teaching the model erroneous mappings between features and labels, which leads to poor generalization and reduced accuracy on properly labeled validation and test data. Current seismological applications mainly rely on large-scale training sets or data augmentation to reduce the label-noise impact, which can be labor-intensive and costly. Here, we introduce a Label Noise-Contrastive Robust Learning (LaNCoR) approach that can effectively handle noisy labels in seismic signal processing tasks, without requiring large-scale training
datasets. In this approach, the input waveform feature and label representation distributions are aligned in the feature space to correct mislabeling and reduce its impact on the training process. We present LaNCoR's performance on the task of P-phase arrival-time picking of real microseismic data using two baseline models and training approaches. Our results indicate that LaNCoR can improve performance by up to 28.8% across performance metrics. This approach holds great promise for model training in seismology and geosciences.
Read the full abstract ▾
All authors Sen Li, Xu Yang, S. Mostafa Mousavi, Anye Cao, Keting Fan, Yaoqi Liu, Changbin Wang, Qiang Niu
Artificial Intelligence · Cross-listed from cs.DC
CoAgent: Concurrency Control for Multi-Agent Systems
Hongtao Lyu, Dingyan Zhang, Mingyu Wu et al. (+2 more)
Multi-
agent LLM systems – coding
agents, devops
agents, document
agents – now routinely run several
agents in parallel against the same git tree, Kubernetes cluster, or document. As soon as two of them mutate shared state, they enter the regime classical concurrency control has studied for decades, but classical mechanisms fit LLM
agents poorly. A single
agent transaction spans minutes of inference, read sets are broad and opaque rather than statically inferable, and the live state
agents act on admits neither fork nor buffer, so writes take effect the moment they execute. Locks block long inference intervals; OCC abort-and-retry discards minutes of work on every conflict. This paper builds concurrency control on a capability classical transactions lack: the LLM inside each
agent can judge whether a conflicting write invalidates its plan, and can repair exactly the operations that depended on it. Control therefore turns advisory: the runtime informs, the
agent repairs. Our protocol, MTPO (Monotonic Trajectory Pre-Order), fixes a serialization order at launch, serves each read the order-filtered value, and applies writes speculatively in place; a one-way notification asks an affected reader to re-judge and patch its plan, while the framework mechanically undoes and reorders misplaced writes through the saga-style inverse each tool registers in advance. At quiescence the run is serializable in the pre-decided order. We realize MTPO as CoAgent, toolcall middleware whose privileged ToolSmith grows footprint-declared, undoable tools online. On ten contended workloads, CoAgent stays within 5% of serial correctness at a $1.4\times$ speedup and near-serial
token cost, where 2PL and OCC surrender nearly all concurrency gains; on a bash-only target system, it grows a 25-tool library online and lifts the task pass rate from 45/71 to 63/71 at $0.80\times$ the time and $0.86\times$ the cost.
Read the full abstract ▾
All authors Hongtao Lyu, Dingyan Zhang, Mingyu Wu, Xingda Wei, Haibo Chen
Artificial Intelligence
S1-DeepResearch: Beyond Search, Toward Real-World Long-Horizon Research Agents
Yao Dong, Xinglin Xiao, Liwei Dong et al. (+5 more)
Deep research
agents aim to solve complex knowledge-intensive tasks through long-horizon planning, evidence gathering,
reasoning, and report generation. While recent progress in search
agents has demonstrated strong capabilities in information
retrieval and answer verification, most existing training
datasets remain search-centric, focusing primarily on closed-ended question answering and information localization. As a result, they mainly train information-seeking behavior while providing limited coverage of key deep research capabilities, including evidence integration, knowledge synthesis, planning, file understanding, and structured report generation. In this work, we propose a unified trajectory construction paradigm for deep research
agents that combines closed-ended QA and open-ended exploration. The proposed framework consists of graph-grounded task formulation, agentic trajectory rollout, and multi-dimensional trajectory verification, enabling scalable synthesis of high-quality agentic trajectories spanning long-chain complex
reasoning, deep research instruction following, report writing, file understanding and generation, and skills usage. Compared with existing search-oriented
datasets, our synthesized trajectories place greater emphasis on knowledge synthesis, complex
reasoning, and planning. S1-DeepResearch-32B achieves state-of-the-art performance among open-source models of comparable scale across 20
benchmarks spanning five capability dimensions, including complex
reasoning, instruction following, report generation, file understanding, and skills usage. On several challenging deep research
benchmarks, it approaches the performance of leading proprietary frontier models. These results highlight the importance of jointly modeling information acquisition, knowledge synthesis, and planning-oriented
agent behaviors for building effective deep research
agents.
Read the full abstract ▾
All authors Yao Dong, Xinglin Xiao, Liwei Dong, Xinlong Jin, Zhengbo Li, Heng Zhang, Duyun Wang, Nan Xu
Artificial Intelligence
APEX: Adaptive Principle EXtraction A Three-Layer Self-Evolution Framework for Production AI Agents
Ya-Chuan Chen, Tien-Jen Lai and Hsiang-Wei Hu
Self-improvement in AI
agents has emerged as a key research frontier: systems that modify their own
prompts, workflows, and decision rules based on accumulated operational experience. The state-of-the-art Self-Harness framework [1] achieves 14–21% improvement on Terminal-Bench-2.0 by mining failure clusters and patching the
agent harness. However, Self-Harness optimises only one dimension – the
prompt harness – leaving behavioural principles and workflow
topology unchanged. We propose APEX (Adaptive Principle EXtraction), a three-layer co-
evolution framework that simultaneously evolves: (L1) the harness via failure-mode patching, (L2) behavioural principles via success-trace
distillation [2], and (L3) the
agent workflow
topology via structural fitness-based selection [6]. We implement APEX on Joe [13], a production-grade super AI
Agent built on NVIDIA Nemotron and designed as an Edge AI
Agent Factory for the NVIDIA
Agent Challenge 2026, managing a 15-node compute fleet using 114 real task traces collected over 18 days. APEX achieves an APEX Health Score of 0.570 (+90% vs. baseline 0.300) in a single evolutionary run, distilling 6 novel reusable principles and selecting a research-first workflow
topology scoring 0.900 (+20%). Our results demonstrate that multi-dimensional co-
evolution substantially outperforms single-axis harness optimisation, at a cost of only 4 LLM calls (~270 s) on a local qwen2.5-coder:32b instance.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.HC
Cognitive Trajectory Modeling: Quantifying Human-AI Co-Creation through Cognitively Grounded Interaction Trajectories
Nicholas Davis
Co-creative AI research increasingly seeks methods capable of representing how interaction dynamics evolve through time. While many existing approaches focus on observable interaction characteristics, interaction metrics, behavioral coding schemes, or activity traces, these methods often struggle to capture higher-order interaction dynamics, including how collaborative processes reorganize, stabilize, regulate, and evolve through time. This paper introduces Cognitive Trajectory Modeling (CTM) as a cognitive theory of interaction dynamics that conceptualizes cognition, interaction, and creative processes as temporally organized trajectories unfolding across cognitively meaningful attractor landscapes. CTM builds upon the theoretical foundations of the Enactive Model of Creativity and Creative Sense-Making (CSM), revisiting the role of sense-making curves and cognitive trajectories in representing co-creative interaction dynamics. We formalize this perspective through the Cognitive Trajectory Principle, which states that temporal representations are only theoretically interpretable as cognitive trajectories when their underlying states possess directional cognitive meaning. Building on this principle, CTM generalizes the notion of cognitive trajectories beyond any particular coding scheme and provides a broader framework for modeling interaction dynamics through trajectories unfolding across meaningful attractor landscapes. We further distinguish cognitive trajectories from interaction traces and situate CTM within a broader hierarchy of cognitive, interaction, and domain dynamics. More broadly, we argue that understanding co-creative systems requires methods capable of modeling how cognition and interaction dynamics unfold through time. CTM provides a foundation for studying interaction dynamics across co-creative AI and human-AI interaction.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CY
LearnOpt: Recovering the Latent Cognitive Structure of Standardized Examinations via Knowledge Graphs and Constrained Optimization
Joy Bose and Om Thomas
Standardized examinations are typically treated as uniform syllabus coverage problems. We argue they are better understood as
adversarial systems with stable latent cognitive structures diverging systematically from official syllabi. We introduce LearnOpt, which recovers this structure from historical question papers and generates personalized, time-bounded study plans. Applied to nine years of NEET questions (2016-2024, n=1,496), LearnOpt builds an exam knowledge graph from LLM-tagged questions, extracts a five-category latent skill distribution, and formulates study planning as a knapsack-variant optimization over prerequisite-aware subgraphs with
Bayesian Knowledge Tracing. Central finding: NEET's latent skill distribution is stable within a syllabus regime (consecutive-year KL divergence 0.004-0.032 for 2016-2021, non-significant under permutation testing) but shifts significantly with NCERT's 2023 syllabus rationalization: pooling 2016-2021 (n=1,072) vs 2023-2024 (n=392) gives KL=0.040 (p=0.0005), with Elimination/Negation questions rising from ~20-29% to ~31-35%. Latent structure, while not permanently stationary, is piecewise stable, with shifts detectable and attributable to curricular events. Within either regime, subject predicts skill profile more strongly than year. An optimization evaluation, using one real and two synthetic mastery profiles, shows the skill-weighted objective produces a modest but real reordering of recommended topics over a mastery-conditioned frequency baseline. Applying the pipeline to JEE Advanced reveals a profile dominated by Multi-concept Integration (80.9% vs. 33.3% for NEET), with a JEE-vs-NEET divergence (KL=0.505) exceeding NEET's largest cross-subject divergence: exam tier shapes latent cognitive structure more than subject, which shapes it more than time within a regime. Code, knowledge graph, and annotated
dataset are released publicly.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from q-bio.NC
Intrinsic Computational Functionalism and Simulated Consciousness
Ryota Kanai and Shuqin Ma
A common objection to artificial or simulated consciousness is that a simulated
brain is no more conscious than simulated water is wet. We address this from the perspective of Intrinsic Computational Functionalism (ICF): if consciousness is computationally constituted, it depends not on externally imposed descriptions but on the computational structures a system physically realizes in virtue of its own causal-dynamical organization. In previous work we developed Canonical Functionalism as a mathematically precise special case of this anti-interpretivist program, identifying functional states by their complete future input-output roles under a fixed interface. Here we argue that this input-output construction, though important, is incomplete: as a behavioral boundary case of ICF, it makes lookup tables and unfolded systems that preserve the same boundary behavior canonically equivalent. A consciousness-relevant canonical representation must instead include internal mechanisms, interventions, and joint readouts belonging to the relevant intrinsic organization. We therefore define a mechanism-enriched canonical structure and use it to formulate Intrinsic Causal-Computational Realization (ICCR), a realization relation preserving physical implementation, intrinsic state individuation, transition structure, intervention profiles, and the relevant
agent-body-world boundary. The central result is conditional: if conscious properties are invariants of intrinsic causal-computational organization, then any system satisfying ICCR realizes the same consciousness-relevant properties, whether biological, artificial, or simulated. We discuss objections including biological naturalism and integrated information theory. We conclude that to deny consciousness to a simulation, one must identify a consciousness-relevant intrinsic causal-computational structure that the simulation fails to realize.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Privacy-Preserving Text Sanitization for Distributed Agents Collaboration via Disentangled Representations
Xuan Liu, Hefeng Zhou, Sicheng Chen et al. (+6 more)
When distributed
agents exchange text across organizational boundaries,
privacy leakage arises not only from explicit identifiers but also from distributional signatures such as formatting conventions, vocabulary choices, and syntactic patterns. We propose DiSan(Disentangled Sanitization), a
privacy-preserving sanitization framework and a built-in component of Intern-Shannon for multi-
agent collaboration. DiSan uses a two-stream encoder to factorize text into a source-invariant role subspace that preserves task semantics and a source-identifying style subspace that remains local.
Federated proto-type
alignment and
adversarial regularization enable joint training without centralizing raw text. Experiments show that identifier-level masking is insufficient: masking 19.2% of
tokens reduces TF-IDF stylometric attribution by only 18.6%. By contrast, DiSan reduces answer-level PII exposure by 20 times while maintaining 83% answer faithfulness on a distributed multi-
agent RAG
benchmark, and lowers Enron stylometric attribution by 73.2% under TF-IDF and 70.6% under a neural probe.
Read the full abstract ▾
All authors Xuan Liu, Hefeng Zhou, Sicheng Chen, Chao Yang, Xingcheng Xu, Jingjing Qu, Jiong Lou, Jie LI, Xia Hu
Artificial Intelligence · Cross-listed from cs.IR
HoloRec: Holistic Encoding and Interleaved Reasoning for Generative Recommendation
Shuqi Zhao, Jingsong Su, Xiang Liu et al. (+9 more)
Generative recommendation models that formulate the task as sequence generation overcome the objective fragmentation problem of traditional cascade architectures, yet existing approaches still suffer from flat semantic representations lacking hierarchical structure for multi-step
reasoning and an externally constructed chain-of-thought (CoT) that requires expensive annotations and remains disconnected from the generation objective. We propose HoloRec, an endogenous chain-of-thought recommendation mechanism that unifies representation,
reasoning, and generation by constructing a hierarchical semantic encoding
matrix via multi-granularity nested residual quantization optimized by a holistic reconstruction loss. HoloRec supports two inference modes: a non-thinking mode that uses lightweight multi-granularity supervised
alignment for fast prediction, and a thinking mode that employs an interleaved
reasoning scheme to generate CoT steps on the fly, directly
embedding reasoning into the generation process without external data. Experiments on multiple public recommendation
datasets demonstrate that HoloRec consistently outperforms baselines, with especially significant gains in sparse scenarios, and the thinking mode achieves better accuracy than the non-thinking mode with only modest inference overhead.
Read the full abstract ▾
All authors Shuqi Zhao, Jingsong Su, Xiang Liu, Xingzhi Yao, Yiming Qiu, Huimu Wang, Liang Lin, Pengbo Mo, Mingming Li, Jiao Dai, Jizhong Han, Songlin Hu
Artificial Intelligence
ChatPlanner: A Large Language Model Framework for Personalized Public Transit Routing
Tingting Yang, Chenhao Xue and Jun Chen
Personalized public transit routing in public transit systems remains challenging due to the difficulty of capturing and integrating diverse user preferences into routing
algorithms. This paper presents ChatPlanner, a novel framework that leverages Large
Language Models (LLMs) to enable preference-aware public transit routing. Our approach employs fine-tuned LLMs with
Retrieval-Augmented Generation (RAG) to extract routing parameters and interpret conversationally expressed preferences from natural
language queries as preference scores, subsequently integrating these preferences into the objective function of a public transit routing
algorithm. This study designs preference-aware
datasets incorporating eight personas and five contexts to establish scoring standards for both fine-tuning and RAG. This work conducted four experiments to validate the solutions' feasibility, extraction of routing information and preferences, solution set quality and completeness, and latency and computational tractability. Results demonstrate that ChatPlanner generates feasible solutions reliably. Fine-tuning enforces the required output structure and learns general preference patterns, while RAG provides query-specific context to resolve imprecise or conversational expressions and calibrate continuous scores. The combination of both achieves the highest accuracy in routing information extraction and rubric-consistent user preference interpretation. Results based on selected case studies show that by capturing user conversationally expressed preferences, ChatPlanner identifies preference-relevant solutions across different dimensions that existing route planners overlook, generating more route alternatives. The latency evaluation confirms that the framework is computationally tractable. This research establishes a new paradigm for integrating natural
language understanding into transportation optimization.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
LLMs on Tabular Data with Limited Semantics: Evidence from Industrial Car Retrofit Prediction
Aina Vila Pons, Ioannis Tzachristas and Constantinos Antoniou
Industrial retrofit planning depends on structured operational data rather than free text: planners must estimate whether a newly registered prototype will require a retrofit, which retrofit package it will need, and how long the work will take. We study an industrial
dataset linking a prototype-registration system (284,271 vehicles) with a retrofit-management system (48,716 cleaned visits), and compare strong tabular machine learning baselines with three LLM-based strategies on row-serialized inputs:
embedding features (Amazon Titan), direct prompted classification (Claude Sonnet 4), and an ML+LLM stacking approach. Across binary occurrence prediction, 15-way retrofit-type classification, per-visit duration regression, and an aggregated monthly
benchmark, classical tree ensembles remain the strongest standalone models. However, the LLM results reveal a consistent pattern:
embeddings remain useful on tables (binary AUC = 0.982), direct prompting collapses once semantic signal is stripped by hashing (binary AUC = 0.500; multiclass weighted F1 = 0.018), and hybrid stacking yields the best manually built multiclass model (weighted F1 = 0.626). On the monthly
benchmark, lag-based machine learning outperforms time-series foundation models, though Chronos-small remains competitive in zero-shot
forecasting. The results suggest that on
privacy-constrained industrial tables, LLMs are more effective as complementary components than as replacements for strong tabular baselines.
Read the full abstract ▾
Artificial Intelligence
Forced Deferral: Manipulating Routing Decisions in Multimodal LLM Cascades
Zhongye Liu, Yaopei Zeng, Yurui Chang et al. (+1 more)
While
multimodal large
language models (MLLMs) have shown strong visual
reasoning abilities, serving a large model for every query is computationally expensive. MLLM cascades mitigate this cost by first querying a weak but cheaper model and deferring to a strong model when the weak model's output is unconfident. However, since the weak model's confidence directly controls compute allocation, these systems expose a new attack surface: an adversary can manipulate confidence so that their queries are consistently deferred to the strong model. Motivated by this vulnerability, we introduce the Forced Deferral Attack (FDA), an
adversarial image attack that lowers the weak model's confidence and causes cascades to route queries to the strong model. FDA learns a universal border trigger by optimizing a temperature-flattened objective. This objective pushes the weak model's
token distribution on triggered inputs toward less concentrated targets constructed from its clean responses. Across
datasets, model families, and deferral metrics, FDA consistently increases strong-model routing while outperforming image-perturbation and
prompt-injection baselines. These results show that MLLM cascades are vulnerable to attacks that manipulate compute allocation, forcing unintended strong-model usage without directly targeting answer correctness.
Read the full abstract ▾
All authors Zhongye Liu, Yaopei Zeng, Yurui Chang, Lu Lin
Artificial Intelligence · Cross-listed from cs.CL
Adapting Reinforcement Learning with Chain-of-Thought Supervision for Explainable Detection of Hateful and Propagandistic Memes
Mohamed Bayan Kmainasi, Mucahid Kutlu, Ali Ezzat Shahroor et al. (+2 more)
Hateful and propagandistic memes exploit the interplay between images and text to convey harmful intent that neither modality reveals alone. Although thinking-based
multimodal large
language models (MLLMs) have advanced
vision-
language understanding, their application to meme content moderation remains underexplored. We propose a reinforcement learning-based post-training method that improves classification performance and reference-based explanation quality in thinking-based MLLMs via task-specific rewards and Group Relative Policy Optimization (GRPO). Concretely, we (i) conduct a systematic empirical study of off-the-shelf MLLMs for hateful and propagandistic meme understanding across English and Arabic
benchmarks, (ii) extend existing meme
datasets with weakly supervised chain-of-thought (CoT) rationales via
distillation and multi-LLM fine-grained propaganda annotations, (iii) introduce a GRPO-based objective with thinking-length regularization that jointly optimizes classification accuracy and explanation quality, and (iv) investigate self-supervised GRPO on unlabeled memes using consensus-based pseudo-labels. Experiments on the Hateful Memes and ArMeme
benchmarks show that our approach improves over previously reported results on FHM accuracy (up to +2.1%, from 79.9% to 82.0%) and on ArMeme macro-F1 (up to +7.6 points, from 0.536 to 0.612 with explanations; +6.1 compared to the original ArMeme
benchmark), while also generating natural-
language explanations. On ArMeme, sequence-classification baselines remain stronger in terms of raw accuracy, whereas our approach provides more balanced per-class performance along with explanations. We publicly release our code, data extensions, and evaluation resources.
Read the full abstract ▾
All authors Mohamed Bayan Kmainasi, Mucahid Kutlu, Ali Ezzat Shahroor, Abul Hasnat, Firoj Alam
Artificial Intelligence · Cross-listed from cs.LG
LatentGym: A Testbed For Cross-Task Experiential Learning With Controllable Latent Structure
Daksh Mittal, Tommaso Castellani, Thomson Yen et al. (+7 more)
We envision continually learning agentic systems that become more useful over time: as they encounter sequences of related tasks, they should infer the hidden structure shared across those tasks and use it to improve future decisions. This cross-task experiential learning capability is pivotal in domains such as personalization and interactive assistance, but existing training/evaluation frameworks do not provide shared, controllable latent structures and cannot measure whether or why
agents improve. We introduce LatentGym: a controllable suite in which each environment is organized around a ground-truth latent variable governing the structure across tasks. Our construction yields metrics that separate exploration (whether the
agent's actions gather information about the latent) from exploitation (whether the
agent uses what it has gathered). We demonstrate our suite on empirical studies addressing three questions: how and why frontier models fail to adapt across related tasks; whether post-training on related task sequences improves general cross-task adaptation, and where those gains come from; and how design choices such as inter-task feedback shape training dynamics and generalization. Together, these results establish a controlled foundation for studying how LLM
agents learn from experience across tasks, and for designing
agents that adapt more reliably in sequential, personalized, and interactive settings.
Read the full abstract ▾
All authors Daksh Mittal, Tommaso Castellani, Thomson Yen, Naimeng Ye, Minghui Chen, Tiffany Cai, William Zeng, Emmanouil Koukoumidis, Fangyu Wu, Hongseok Namkoong
Artificial Intelligence · Cross-listed from cs.LG
Discovering Lattice Reduction Strategies via Self-Play
Mohamed Malhou, Kristin Lauter and Ludovic Perret
The Lenstra-Lenstra-Lovász (LLL)
algorithm is a seminal contribution to computer science used for
lattice basis reduction, yet its
polynomial-time outputs produce bases that are far from optimal as the dimension grows. We show that deep reinforcement learning can discover strictly superior, generalizable reduction strategies by interacting with the primitive action space of LLL. We formulate
lattice reduction as a single-player Markov Decision Process (MDP) and train a deep residual network using an AlphaZero-style self-play pipeline augmented with adaptive-horizon MCTS (Monte Carlo Tree Search), which couples multi-step network predictions with an
entropy-gated expansion mechanism. The resulting policy, DeltaStar, is trained exclusively on small $8$-dimensional $q$-ary
lattices and requires fewer primitive row operations than LLL. Crucially, it generalizes zero-shot to unseen
moduli and higher dimensions up to $n=32$ without retraining.
Read the full abstract ▾
Artificial Intelligence
CODA-BENCH: Can Code Agents Handle Data-Intensive Tasks?
Yuxin Zhang, Ju Fan, Meihao Fan et al. (+2 more)
Advanced
agents are increasingly demonstrating the potential to operate as autonomous engineers, creating a growing demand for evaluation
benchmarks that capture the complexity of real-world development. Such environments typically involve both complex code and large-scale data (i.e., file system). However, existing
benchmarks usually evaluate code-centric or data-centric capabilities in isolation, leaving a clear gap with real development scenarios. In this paper, we bridge this gap by introducing CODA-BENCH, the first
benchmark to jointly evaluate code and data intelligence in a data-intensive environment. We construct a data-intensive Linux sandbox based on the Kaggle ecosystem (containing hundreds of
datasets), where
agents must actively explore complex file hierarchies to identify relevant resources and generate code for data-driven analytical tasks. CODA-BENCH comprises 1,009 tasks spanning 31 communities, with each task environment containing an average of 980 files, simulating realistic data scale and noise. Evaluations of advanced
agents reveal that even top-performing systems struggle to effectively integrate data discovery with code execution, achieving a success rate of only 61.1%. These results highlight a substantial gap in current agentic capabilities for data-intensive tasks and point to promising directions for future research.
Read the full abstract ▾
All authors Yuxin Zhang, Ju Fan, Meihao Fan, Shaolei Zhang, Xiaoyong Du
Artificial Intelligence
A Formal Framework for Declarative Agentic AI in Business Process Analysis
Mohammad Azarijafari, Luisa Mich and Michele Missikoff
Agentic AI opens new opportunities for automating Business Process (BP), enabling autonomous decision-making and dynamic adaptation. However, realising this potential requires BP entities and their interactions to be defined with formal precision. This paper presents a formal framework for Agentic BP analysis through the AGO methodology. AGO captures the modelling perspective in terms of who is acting (
Agents), why it is carried out (Goals), and what the relevant entities are (Objects). Grounded in set theory and mathematical logic, we formally define the AGO entity types and their interactions, organising all definitions into a BP Knowledge Base (BPKB). The resulting BPKB supports structured querying, incremental updates, and automatic generation of BP workflows, while ensuring soundness and completeness of the derived paths.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Hybrid NARX-LLM for Greenland Iceberg Discharge: Prompt-Driven Residual Correction
Yiquan Gao and Duohui Xu
Greenland iceberg discharge exhibits complex nonlinear dynamics with limited observability, challenging traditional predictive models. We present a Hybrid NARX-LLM framework that combines a nonlinear autoregressive model with exogenous inputs (NARX) and a large
language model (LLM) for residual correction. We further propose a Physics-Informed
Prompt (PIP) method that transforms unstructured physical knowledge into structured
prompts for zero-shot in-context
reasoning. The primary objective is to explore the corrective potential of this framework for modeling Greenland iceberg discharge, rather than merely optimizing predictive accuracy. The NARX component captures intrinsic temporal dependencies, while the LLM, guided by PIP, encodes glacier dynamics and environmental drivers and perceives key trend patterns to correct systematic prediction errors. This integration allows the model to reason about unmodeled factors and produce interpretable residuals, enhancing overall predictive accuracy. Applied to Greenland iceberg discharge time series, our approach addresses extreme events that are difficult to predict due to rare variations and nonstationary trends, a limitation often overlooked by traditional methods. By fusing structured time-series modeling with knowledge-driven foundation AI, the framework offers a scalable and interpretable pathway to bridge data-limited
climate forecasting with physics-informed LLM
reasoning. The code is available.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from eess.SP
CAP: Towards PPG Universal Representation Learning with Patient-level Supervision
Chenyang He, Xinyi Shao, Shun Huang et al. (+4 more)
Photoplethysmography (PPG) plays a central role in wearable health monitoring and clinical decision support. Yet existing approaches to universal PPG representation learning largely focus on signal-level objectives and often overlook patient-level health context, which limits generalization to complex clinical tasks and heterogeneous cohorts. To address this gap, we construct a large-scale paired PPG-EHR
multimodal dataset by distilling fragmented medical histories and clinical records into cohesive, patient-level electronic health records (EHR). Building on this resource, we propose Clinical Anchored Pretraining for PPG (CAP). During pretraining, CAP performs cross-modal contrastive
alignment that anchors PPG representations to patient-level clinical semantics, guiding the encoder beyond waveform fitting toward modeling consistency in a patient's overall physiological state. During downstream adaptation, the pretrained PPG encoder provides clinically grounded representations that strengthen inductive bias and improve robustness and transferability. Experiments demonstrate that CAP consistently outperforms strong baselines on four diverse downstream tasks. CAP achieves a particularly large gain on respiratory rate prediction (up to +87.6% relative improvement over the state-of-the-art baseline) and delivers an average relative +26.7% across all tasks. We further enhance the interpretability of our approach through comprehensive analyses, including ablations and multiple complementary visualizations of the learned representations. The code for our experiments is available at: https://github.com/gody123gody/CAP .
Read the full abstract ▾
All authors Chenyang He, Xinyi Shao, Shun Huang, Bosong Huang, Daoqiang Zhang, Ming Jing, Cheng Ding
Artificial Intelligence · Cross-listed from cs.LG
RECTOR: Masked Region-Channel-Temporal Modeling for Affective and Cognitive Representation Learning
Jinhan Liu and Mahsa Shoaran
Affective and cognitive disorders manifest as distributed, time-varying
brain network dynamics across regions, channels, and time, challenging robust representation learning from
EEG/sEEG for clinical diagnosis. We propose RECTOR (Masked Region-Channel-Temporal Modeling), an end-to-end self-supervised framework that unifies joint region-channel-temporal representation learning beyond fixed anatomical priors. At its core, RECTOR-SA is a hierarchical, block-sparse self-
attention induced by Adaptive Functional Partitioning that evolves region structures from static anatomical definitions to adaptive functional regions. The self-supervision is driven by Masked
Topology and Representation Learning, which jointly optimizes three complementary objectives: Masked Predictive Modeling, Topological Structure Modeling, and Cross-View Consistency. Across diverse
benchmarks, RECTOR sets a new state-of-the-art in
EEG emotion recognition and sEEG task-engagement classification. Crucially, its strong robustness to missing channels and cross-montage generalization underscores its potential for large-scale pre-training on heterogeneous
EEG/sEEG, providing interpretable insights at both region and channel levels.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.IR
Improving Federated Graph Recommendation with Semantic Guidance
Thi Minh Chau Nguyen, Hien Trang Nguyen, Duc Anh Nguyen et al. (+3 more)
Graph-based recommendation models effectively capture high-order collaborative signals from user–item interaction graphs.
Federated learning (FL) enables
privacy-preserving training across distributed clients. However, directly aggregating graph representations under FL is challenging: locally learned structural
embeddings are not globally aligned under non-IID data distributions, and naive parameter averaging fails to recover cross-client relational structure. Existing
federated graph-based approaches primarily rely on structural aggregation, yet overlook the global semantic knowledge encoded in large
language models (LLMs). In this work, we propose a semantic–structural
federated graph recommendation framework that leverages LLM
embeddings to guide cross-client
alignment. Each client learns user representations from its local interaction graph and summarizes typical interaction patterns into compact semantic vectors using a frozen LLM encoder. These vectors are sent to the server, which identifies semantically related patterns across different clients and combines their structural representations accordingly. The updated representations are then returned to clients to refine subsequent local training. This design enables collaboration guided by shared semantic understanding without exposing raw interaction data, preserving both recommendation accuracy and
privacy. Experiments on
benchmark datasets demonstrate consistent improvements over existing
federated graph-based baselines.
Read the full abstract ▾
All authors Thi Minh Chau Nguyen, Hien Trang Nguyen, Duc Anh Nguyen, Van Ho-Long, Thanh Trung Huynh, Zhao Ren
Artificial Intelligence
Feature Attribution in Directed Acyclic Graphs Using Edge Intervention
Qiheng Sun, Junxu Liu, Xiaokai Mao et al. (+4 more)
Shapley value-based feature attribution methods face challenges in scenarios involving complex feature interactions and causal relationships, even when a causal structure is provided. Existing methods typically adopt a node-centric view, attributing importance solely to individual features. Consequently, they often fail to simultaneously capture the externality and exogenous influence of features, leading to unreasonable interpretations. To overcome these limitations, we propose a novel feature attribution method called DAG-SHAP, which is based on edge intervention. DAG-SHAP treats each feature edge as an individual attribution object, ensuring that both externality and exogenous contributions of features are appropriately captured. Additionally, we introduce an approximation method for efficiently computing DAG-SHAP. Extensive experiments on both real and synthetic
datasets validate the effectiveness of DAG-SHAP. Our code is available at https://github.com/ZJU-DIVER/DAG-SHAP.
Read the full abstract ▾
All authors Qiheng Sun, Junxu Liu, Xiaokai Mao, Haocheng Xia, Jinfei Liu, Kui Ren, Haibo Hu
Artificial Intelligence · Cross-listed from cs.LG
Trust-Region Diffusion Policies for Massively Parallel On-Policy RL
Huy Le, Onur Celik, Denis Blessing et al. (+6 more)
Reinforcement learning with massively parallel simulations has become a standard framework for developing robust, deployable policies; however, most existing approaches still rely on simple Gaussian policy parameterizations.
Diffusion models provide a more expressive policy class and have shown strong performance on challenging control problems, yet most
diffusion-based RL methods are designed for offline or off-policy training. In this work, we ask whether
diffusion policies can be trained effectively in the massively parallel, on-policy regime. To this end, we introduce Trust-region
Diffusion Policies (TruDi), which enables
diffusion policies for on-policy RL with massively parallel simulations. This setting is particularly challenging because the data distribution changes quickly across updates, making stable training with complex policies difficult. TruDi addresses this by integrating a trust-region optimization rule to enforce a KL-divergence constraint over the entire
diffusion trajectory. Empirically, we evaluate TruDi on a diverse set of 4 massively parallel RL
benchmarks comprising a total of 73 tasks. Across these tasks, TruDi consistently outperforms or is on-par with strong baselines on standard tasks and achieves clear gains on more challenging
humanoid control tasks, establishing a strong new baseline for massively parallel on-policy RL.
Read the full abstract ▾
All authors Huy Le, Onur Celik, Denis Blessing, Tai Hoang, Claas A Voelcker, Axel Brunnbauer, Felix Richter, Michael Volpp, Gerhard Neumann
Artificial Intelligence
Mask-Proof: An LLM-based Automated Data Curation Pipeline on Mathematical Proofs
Jierui Zhang, Siyuan Tan, Xinhang Li et al. (+8 more)
Large
language models (LLMs) are increasingly capable of mathematical problem solving and can even assist with research-level proofs, yet we still lack a scalable and reproducible way to measure step-level
reasoning in long proofs across diverse sources. This evaluation gap limits trustworthy AI assistance in proof-certified scientific progress. Existing evaluations often emphasize final answers or rely on costly expert grading, while end-to-end proof generation remains open-ended and hard to verify automatically. We introduce Mask-Proof, a pipeline that turns real proofs into automatically checkable masked-step tasks. It masks key formula steps, provides the necessary surrounding context, and evaluates model reconstructions with an LLM-based equivalence judge using repeated votes for stability. The resulting Mask-ProofBench contains 292 curated problems across diverse research areas. Experiments with 17 models show that
reasoning-enhanced models outperform standard models by 12% to 27%. Our evaluator achieves 96.8% agreement with expert annotators, enabling faithful, reproducible, and comparable measurement of step-level mathematical
reasoning.
Benchmark, annotations, and code are available at https://github.com/weating/Mask-Proof.
Read the full abstract ▾
All authors Jierui Zhang, Siyuan Tan, Xinhang Li, Longzhuangzhi Lin, Dailin Li, Chengfeng Gu, Xinping Li, Yaxian Hao, Shengjia Liang, Yuxiang Ren, Wenhao Liu
Artificial Intelligence · Cross-listed from cs.RO
Driving, Fast or Slow? Neuro-Symbolic Guidance for Motion Prediction in Multi-Modal Ground Mobility
Simon Kohaut, Felix Divo, Julius Hahnewald et al. (+4 more)
Accurate and interpretable motion prediction for heterogeneous traffic spaces, including pedestrians, bicycles, cars, and trucks, is essential for safe autonomous
navigation. Nevertheless, state-of-the-art approaches remain predominantly black-box, lacking explicit encoding of the regulatory and behavioral constraints of real-world mobility. We propose Trajectory Compliance-Shaping (TraCS), a neuro-symbolic framework that augments existing black-box motion prediction backbones with interpretable and probabilistic first-order logic. To do so, TraCS employs an agentic code-generation pipeline to bridge the gap between natural-
language descriptions of traffic regulations and probabilistic motion prediction. Furthermore, TraCS employs a reactive data-streaming inference engine that maintains and efficiently updates compliance landscapes as scenes evolve. To prevent TraCS from overconfidently steering the backbone's predictions in the wrong direction, we propose a neural confidence rating learned as a context-aware attenuation of the compliance signal. We demonstrate on the Argoverse 2
benchmark how TraCS consistently improves state-of-the-art prediction backbones, showing that probabilistic and symbolic compliance
reasoning is a broadly applicable and computationally efficient complement to purely neural motion predictors.
Read the full abstract ▾
All authors Simon Kohaut, Felix Divo, Julius Hahnewald, Benedict Flade, Julian Eggert, Kristian Kersting, Devendra Singh Dhami
Artificial Intelligence · Cross-listed from cs.CV
Landmark-free Assessment of Lower-limb Alignment with Implicit Neural Shape Functions from Knee Radiographs
Zhisen Hu, Antti Kemppainen, David Johnson et al. (+5 more)
Radiographic assessment of lower-limb
alignment (LLA) is important for predicting joint health and
surgical outcomes in total knee arthroplasty. Traditional measurement methods are manual and time-consuming, while recent machine learning approaches typically rely on locating a fixed set of anatomical landmarks. This dependence limits flexibility and may require re-annotation when clinical definitions change. To address this, we propose an automated workflow using Implicit Neural Shape Functions (INSF). Rather than relying on explicit landmark coordinates, we encode the anatomy into a compact latent space and regress clinical
alignment measurements directly from these latent codes. This architecture allows for rapid extendability to new tasks without altering the backbone representation. We trained our method on an internal
dataset of 566 knee radiographs, each annotated with the outline of the femur and tibia. We evaluated it on both an internal test
dataset of 50 patients and a separate external set of 402 preoperative cases from the MRKR
dataset. Manual clinical measurements are available for these data, and the MRKR measurements will be made publicly accessible. Performance was comparable to state-of-the-art landmark-based methods and manual agreement, while offering a flexible shape representation that can be extended to additional measurement tasks.
Read the full abstract ▾
All authors Zhisen Hu, Antti Kemppainen, David Johnson, Egor Panfilov, Huy Hoang Nguyen, Timothy Cootes, Claudia Lindner, Aleksei Tiulpin