Artificial Intelligence
From Stages to States: Unified Iterative Reasoning for MLLMs
Chuang Yu, Xuefei Ma, Yuanhao Feng et al. (+9 more)
Multimodal Chain-of-Thought (MCoT) substantially enhances the complex
reasoning capabilities of
Multimodal Large
Language Models (MLLMs) by explicitly modeling intermediate
reasoning processes. However, most learning-based MCoT methods follow a stage-centric paradigm, where different
reasoning behaviors are assigned to predefined stages and optimized separately. This results in fragmented
reasoning and a training-inference
reasoning-state gap. To address these limitations, we propose ReState, a unified iterative
reasoning framework that reformulates
multimodal reasoning from a stage-driven pipeline into a state-driven dynamic process. It comprises two complementary components: Unified
Reasoning State Modeling (URSM) and Closed-Loop
Reasoning-State Learning (CRSL). URSM unifies
reasoning construction, correct
reasoning preservation, and erroneous
reasoning correction as
reasoning-state transitions within a shared state space, enabling these heterogeneous
reasoning behaviors to be learned jointly. CRSL further incorporates self-generated historical
reasoning states during training and recursively updates the current state during inference, thereby mitigating the
reasoning-state gap and enabling iterative self-refinement without requiring an additional reflection module, critic, or independent correction stage. Furthermore, we construct VersaCoT-10K, a high-quality CoT
dataset spanning eight visual
reasoning domains, which provides diverse supervision for multi-domain
reasoning and
reasoning-state refinement. Extensive experiments demonstrate that ReState exhibits strong adaptability across different MLLM backbones and achieves strong performance on multiple public
reasoning benchmarks, supporting the shift from stage-centric
reasoning toward state-centric
reasoning. Our data and code are available at https://github.com/YuChuang1205/ReState
Read the full abstract ▾
All authors Chuang Yu, Xuefei Ma, Yuanhao Feng, Wuxiong Zeng, Bo Wang, Minghong Cai, Dongming Wu, Fei Zhou, Chen Tang, Wenwen Tong, Lewei Lu, Xiangyu Yue
Artificial Intelligence
CondMSP: Condition-Informed and Resource-Aware Inorganic Materials Synthesis Planning
Heewoong Noh, Gyoung S. Na, Elton Pan et al. (+2 more)
Materials synthesis planning (MSP) connects AI-driven materials discovery to experimental realization by proposing precursors, synthesis operations, and processing conditions for a target material. Existing approaches predict these components separately or in pairs and treat conditions only as a prediction target. Consequently, MSP remains centered on recipe prediction: it leaves unexplored how conditions can serve as process context for constructing synthesis routes, and it does not address which candidate routes should be executed under limited experimental resources. We propose CondMSP, which extends MSP from recipe prediction to execution-aware planning. CondMSP predicts temperature, time, and atmosphere by combining a joint predictor with variable-specific experts, and then uses these predictions both as process context, grounding the generation and
retrieval of operation sequences, and as execution requirements, specifying which thermal stages can share a furnace run and at what cost. This specification is held fixed across all compared methods; within it, CondMSP ranks routes across precursor sets by a common utility and, under furnace budgets, jointly selects routes and allocates their thermal stages by constrained optimization. CondMSP improves condition and operation prediction and, under this shared constraint, raises reference-recipe recovery from 27.9% to 32.9% at three simulated furnace runs per target and from 34.7% to 40.0% at 30 trials, while a new evaluation set of 2,344 targets supports generalization beyond oxide-dominated training chemistry.
Read the full abstract ▾
All authors Heewoong Noh, Gyoung S. Na, Elton Pan, Namkyeong Lee, Chanyoung Park
Artificial Intelligence
Inverse Garment Design with Visual Agents
Nanxiang Jiang, Yunuo Chen, Zeng Tao et al. (+5 more)
We study the problem of inverse garment design, reconstructing simulation-ready 3D outfits with arbitrary layers from a single image, with visual
agents. Unlike differentiable optimization that is time-consuming, or feed-forward methods limited by training data, we introduce DressAgent, a hierarchical agentic system that recovers garment sewing patterns through planning and closed-loop refinement grounded in physical simulation. To this end, we first present an enhanced representation based on GarmentCode for diverse styles and arbitrary dressing layers, and build the first multi-layer sewing pattern
dataset with over 15K outfits for supervision and benchmarking. Inverse design then proceeds coarse to fine: In layer planning and coarse estimation,
agents infer layer order and relations, peel each layer into its own view, and estimate coarse patterns. In fine-grained refinement, an agentic trio of Tailor, Critic, and Orchestrator refines patterns in a closed loop of editing, simulating, and judging against the reference with visual and measured evidence. Carefully designed tools and an evolving
memory make this refinement converge on the target geometry. We also design an agentic generation method for high-fidelity textures. DressAgent outperforms feed-forward methods by a large margin, surpasses or matches differentiable optimization in a fraction of the time, and generalizes to complex layering, diverse poses, and body shapes.
Read the full abstract ▾
All authors Nanxiang Jiang, Yunuo Chen, Zeng Tao, Zizhang Li, Qi Guo, Jiajun Wu, Yin Yang, Chenfanfu Jiang
Artificial Intelligence
Self-Representation Alignment in Diffusion Models for Video Background Music Generation
Jincheng Zhang, György Fazekas and Charalampos Saitis
Diffusion models have been widely used for various generative tasks. However, recent studies have demonstrated that the internal representations learned in the
diffusion models' denoising process are insufficiently meaningful, which can hinder the generation performance. To address this, we propose a novel
diffusion U-Net architecture enhanced by explicitly aligning the weaker representation from the earlier layer conditioned on higher noise with the better representation from the later layer conditioned on lower noise during training, which we use for the challenging
multimodal task of
video background music generation. Our
diffusion U-Net Self-Representation
Alignment (U-SRA) employs an
alignment loss to effectively guide our
diffusion model to learn good internal representations, thereby enabling it to produce higher-quality symbolic music conditioned on
video features. We employ a cross-
attention mechanism to synchronize music with
video segments. Experiments on a
benchmark video-music
dataset demonstrate that the proposed U-SRA approach for
video background music generation surpasses the state-of-the-art across key evaluation metrics, including
video-music
alignment and overall music quality.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
ELECT: Settling Identity Before Rendering for Scalable Story Visualization
Mehrajul Abadin Miraj, Md. Mahmudul Hasan, Meherun Farzana et al. (+9 more)
Training-free story visualization without reference images must preserve recurring entities across frames while scaling to long narratives. Existing methods typically maintain consistency by conditioning each frame on other frames of the same story, coupling generation time, VRAM, or both to story length. We introduce ELECT, which instead settles cross-frame identity before final rendering through a
language-guided scene-entity mapping and stationary anchors elected from the model's own drafts. This makes the per-frame cost of the final rendering pass independent of story length. Joint
attention exceeds 96 GB of VRAM at 32 scenes, whereas ELECT remains at 8.3 s per frame and under 20 GB VRAM from 10 to 1000 scenes. On the Story50 long-story
benchmark, ELECT reaches 0.833 average Character Consistency Similarity (aCCS), compared with 0.826 for ten-round refinement, at one seventh of its generation cost, with lower text
alignment (0.327 vs. 0.340). At 1000 scenes, to our knowledge, the first evaluation of training-free story visualization at this length, ELECT exceeds ten-round refinement by 0.017 aCCS and the nearest flat-cost baseline by 0.091, while also surpassing refinement in text
alignment at one twenty-fourth of its generation time. These results show that long-horizon consistency need not require increasingly expensive inter-frame conditioning as stories grow.
Read the full abstract ▾
All authors Mehrajul Abadin Miraj, Md. Mahmudul Hasan, Meherun Farzana, Aniket Joarder, Mahmudul Hasan, Abir Chakraborty Partha, Md. Ahasanul Alam, Redwan Ahmed Rizvee, Md. Fahim Arefin, Md Mahmudur Rahman, Md. Tanvir Alam, Md Mosaddek Khan
Artificial Intelligence
Agent-Canary-Mas: End-to-End Evaluation of Protocol Risk in Long-Horizon Multi-Agent Systems
Xiuming Liu, Le Gai, Zhiyuan Chang et al. (+4 more)
Agent-to-
agent protocols allow LLM
agents to discover peers, exchange results, and coordinate tool use. A locally successful protocol attack, however, may be rejected by a later
agent or propagated into a consequential task decision. Measuring local exploitability alone leaves this difference unresolved and provides limited evidence about which participant caused the final outcome. We present
Agent-Canary-Mas, an end-to-end evaluation system that follows protocol risk through long-horizon multi-
agent tasks. It covers five risk classes and 13 subclasses across A2A, ANP, and BCS, with 975 matched malicious–benign task pairs in five business domains. A shared OpenClaw framework runs autonomous, tool-using
agents under different underlying models while preserving the task and execution setup. Matched runs separate local protocol success from downstream consequences; retained evidence connects participant selection, message consumption, tool activity, and task-state changes. We further evaluate a protocol-context Guard that checks an object's authority at consequential handoffs. Across three model conditions, local attack success is frequently at or above 90%, while consequence conversion ranges from 7.1% to 100.0%. Cross-
agent evidence raises macro-averaged Audit-F1 from 29.7% to 95.5%. On Finance tasks, the Guard lowers average ASR from 86.1% to 53.8% and PTCR from 65.5% to 31.2%, with a measurable completion tradeoff. These results show that protocol risk depends on how
agents use exchanged objects throughout the task, and that evaluating this path supports more informative risk assessment, attribution, and defense.
Read the full abstract ▾
All authors Xiuming Liu, Le Gai, Zhiyuan Chang, Peiyang Li, Bin Zhu, Shuo Wang, Chao Feng
Artificial Intelligence · Cross-listed from cs.GT
Improving the Bounds on Approximating Weighted Maximin Share for Chores
Trung Thanh Nguyen, Khaled Elbassioni and Jörg Rothe
We investigate the problem of allocating indivisible chores among
agents with arbitrary positive weights and additive nonnegative cost functions. An allocation is said to be $\alpha$-weighted-maximin-share (WMMS) fair if the cost incurred by each
agent is at most $\alpha$ times her weighted maximin share. We establish that every instance admits a $4.124234528$-WMMS allocation. Moreover, for instances in which all weights and costs are rational numbers represented in binary, we give an
algorithm that computes a $4.12424$-WMMS allocation in time
polynomial in the number of
agents, the number of chores, and the total binary encoding length of the input. Complementing these upper bounds, we construct a family of instances with strictly positive, identically ordered costs for which the optimal WMMS approximation factors converge to $e$. Together, our results substantially narrow the previously best-known gap of $[2,12]$ established by Li et al.~\cite{LWX26} to $[e,4.12424]$.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
OceanFlow: Coherent Flow Matching for Probabilistic Ocean Modeling
Yuan Gao, Fan Xu, Hao Wu et al. (+1 more)
Probabilistic ocean modeling is essential for risk-aware marine operations,
climate analysis, and scientific decision-making, where downstream decisions depend on the conditional distribution of future ocean states rather than a single deterministic trajectory. Recent data-driven ocean models have made deterministic global ocean modeling increasingly accurate and efficient, but probabilistic ocean modeling remains underdeveloped. Specifically, perturbation-driven ensembles can create spread without explicitly optimizing the joint distribution of their members, often yielding poor calibration and physical inconsistency. To address these issues, we propose OceanFlow, a coherent flow matching framework for probabilistic global ocean modeling. OceanFlow first establishes a sharp, stable mean anchor for the conditional ensemble. Flow matching then learns a coherent state-conditioned pathwise law that jointly reshapes the residual distribution around this anchor at each transition, preserving the predictive center while refining state-dependent uncertainty. We further introduce a Factorized Dynamics Operator (FDO), which combines factorized transitions with a learned state-conditioned response to parameterize the mean anchor and residual-flow velocity. Extensive experiments show that OceanFlow improves ensemble-mean accuracy, probabilistic reliability, and physical-consistency diagnostics over competitive baselines, supporting coherent flow matching as an effective route toward data-driven probabilistic ocean modeling. Code is available at https://github.com/YuanGao-YG/OceanFlow.
Read the full abstract ▾
All authors Yuan Gao, Fan Xu, Hao Wu, Xiaomeng Huang
Artificial Intelligence · Cross-listed from cs.LG
SARATHI: Decoupled Data-Free Probing and Adaptive Reconstruction for Structured LLM Pruning
Sankar Behera, Dhruv Singh, Satyadev Ahlawat et al. (+1 more)
Structured
pruning reduces the inference cost of large
language models (LLMs) by permanently removing
neurons and weight rows, yielding dense, hardware-agnostic speedup. Existing post-training methods couple
neuron selection and weight reconstruction through a shared calibration
dataset, introducing domain bias and out-of-
memory failures at high sparsity. We propose SARATHI, a framework that decouples these two stages. A data-free NMF Residual Subspace Probe scores
neurons using intrinsic weight geometry, without accessing any calibration data, and carries a formal connection to Robust PCA. Adaptive OBS then reconstructs the pruned weights with a localized calibration batch, operating in $\mathcal{O}(d^2)$ peak
memory per layer and eliminating the global
memory bottleneck of coupled methods. A Bias Shift Compensation step corrects systematic activation drift in post-LayerNorm architectures that would otherwise cause perplexity collapse at high sparsity. Experiments across six models from two architecture families (gated and non-gated FFN) at 15–40% sparsity show that SARATHI achieves competitive perplexity and matches or exceeds existing structured
pruning baselines on zero-shot accuracy.
Read the full abstract ▾
All authors Sankar Behera, Dhruv Singh, Satyadev Ahlawat, Yamuna Prasad
Artificial Intelligence · Cross-listed from cs.CL
REPRO: Reflective Evolutionary Prompt Optimizer for Automated LLM Red-Teaming
Abrar Alotaibi and Moataz Ahmed
Safety-aligned large
language models (LLMs) remain vulnerable to
adversarial prompts that bypass their safety training. Existing automated red-teaming methods either require privileged access unavailable in production, rely on manually engineered per-model templates, or optimize a single objective without population-level diversity. We present REPRO (Reflective Evolutionary
Prompt Optimization), a pure black-box framework that discovers
adversarial prompts through evolutionary optimization driven entirely by a compressed open-weight 7B reflective model on a single consumer GPU. REPRO introduces two mechanisms absent from prior work, both isolated in a component ablation: semantic crossover, an LLM-guided multi-parent recombination operator, and
Bayesian strategy selection via Thompson Sampling informed by structured failure analysis. We catalog REPRO's behavior on AdvBench, JailbreakBench, and HarmBench across 36 target models from 11 families, including GPT-5-nano, Claude-3.5-Sonnet, Gemini-2.5-Pro, and Grok-4.1. Under our protocol REPRO reaches 100% attack success rate (ASR) on every evaluated target in a single turn, at a median of 24 target queries per behavior. Two properties of the protocol qualify that figure. The judge scoring candidates during optimization also produces the reported ASR, and search halts when it accepts, so ASR reports whether search succeeded within the iteration budget rather than success at a fixed budget. All baseline figures are transcribed from their original papers, which use different judges, budgets, and model versions. We therefore present this as a catalog of model coverage under one protocol rather than a head-to-head ranking, and develop both qualifications in the paper.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
CacheLink: Functional KV Transport for Zero-Prefill Cross-Model Context Handoff
Haomiao Qiu, Yining Tang, Zijia Song et al. (+3 more)
KV caches make long-context serving efficient by reusing past computation, but model switching breaks this reuse and forces the receiver to prefill the context again. We study zero-prefill cross-model context handoff: translating a sender cache into a receiver-compatible state so that the receiver can continue directly without prefilling same context. Existing affine transport methods show that receiver KV states can be substantially reconstructed from sender caches. However, through extensive analyses, we find that reconstruction fidelity is a poor proxy for receiver utility. Similar K/V reconstruction errors can lead to substantially different
attention patterns, predictive distributions, and downstream accuracy, because conventional reconstruction objectives overlook the query-dependent functional importance of K and V in receiver
attention. We thus introduce CACHELINK, which learns a coupled K/V correction through the receiver behavior directly. Across four independently trained sender–receiver pairs and seven evaluation panels, CACHELINK improves the equal-weight mean over all methods for every pair. In matched diagnostics, CACHELINK changes K/V squared error by less than 0.4% while substantially changing receiver
attention and next-
token behavior. At 32K context, it reduces handoff latency by up to $7.27\times$ relative to receiver re-prefill. Our findings verify that reconstruction fidelity alone is insufficient and that preserving the receiver computation induced by the transported cache is important for effective cross-model KV transport.
Read the full abstract ▾
All authors Haomiao Qiu, Yining Tang, Zijia Song, Ruizi Han, Ziyue Qiao, Miao Zhang
Artificial Intelligence
Data Portability Revisited: Toward the Human-Centric, AI-Driven Data Ecosystems of Tomorrow
Mark Fenwick, Michael Fertik, Paulius Jurcys et al. (+1 more)
This Article critically examines the contemporary regulatory framework and discourse surrounding data portability in the United States. Using recent regulatory developments in the European Union as an illustration, this Article suggests that although data access and portability are identified as vital issues in multiple policy instruments, in its current iteration, at least, legal conceptions of portability continue to reinforce the interests of service providers and data controller enterprises rather than individual end users. This Article argues that a paradigm shift toward a more human-centric data approach to data governance must occur, under which data would be recognized as fundamental to an individual's identity in a digital age. Therefore, it should be placed in the hands of individuals rather than service providers or data controller enterprises. This Article considers technical and
market trends in the European Union that reveal and facilitate such a change. It suggests that regulatory frameworks should better align with these technological and
market developments to encourage change-inducing trends among
market actors. In short, this Article identifies a transformative approach to data portability that empowers individuals with the freedom and ability to aggregate their data in secure personal spaces under their control or dominion. Such a human-centric perspective on data portability is crucial in building Artificial Intelligence (AI)-powered applications for individual consumers that can pave the way for the human-centric, AI-driven data ecosystems of the future.
Read the full abstract ▾
All authors Mark Fenwick, Michael Fertik, Paulius Jurcys, Timo Minssen
Artificial Intelligence
Large Decision Models: Repurposing Large Language Models as Single-Pass Decision Makers
Ziyi Chen, Yan Zhang, Jianhui Wei et al. (+2 more)
Large
language models make decisions through parallel prefill and sequential decoding. Although effective, this approach incurs decoding costs and does not explicitly expose decision probabilities. Existing task-specific classifiers require per-task training and offer limited generalization to unseen decision schemas. We propose Large Decision Models (LDMs), repurposing
language models to return explicit probabilities over labels specified at run time using one prefill forward pass. We first adapt models to this interface through Diverse Decision Supervision (DDS), covering varied domains, rules and labels. To further narrow the performance gap to a
reasoning model, Self-Posed
Reasoning Distillation (SPRD) adds tasks generated by a frozen teacher, filters them for answer consistency, and trains on label distributions obtained from repeated teacher
reasoning. We evaluate on DecisionVista, pairing new-schema tests with held-out human-labelled sources. Across three base models, the recipe improves accuracy over a step-matched baseline by 1.8 and 1.5 percentage points, respectively, achieving a 182-fold speedup in latency over
reasoning rollout on Gemma-4-31B.
Reasoning remains stronger on the new-schema test, motivating a confidence router for uncertain decisions. On development sets, routing recovers a median 92% of
reasoning's accuracy advantage while generating 27-58% of its
tokens. Code is available at https://github.com/JianhuiWei7/LDM.
Read the full abstract ▾
All authors Ziyi Chen, Yan Zhang, Jianhui Wei, Jianing Yin, Daoan Zhang
Artificial Intelligence · Cross-listed from cs.CY
The Imperishable Record, Forgiveness, and the Future of Criminal Justice
Mark Fenwick, Paulius Jurcys and Sebastian Porsdam Mann
Digital technologies can preserve records of wrongdoing indefinitely, and AI can give those records continuing influence over a person's future. We describe this condition as the eternal data present and argue that it threatens the possibility of forgiveness. In criminal justice, formal punishment has an end, whereas the harms caused by the continued use of criminal records may not. Drawing on Hegel's account of the "hard heart" and Arendt's account of the irreversibility of action, we distinguish two dangers that digital systems can combine. People may be permanently identified with what they have done, and acts that cannot be undone may continue to determine what happens to them. We propose a right to remain unfinished, supported by rights to limits on the weight given to older records, to re-evaluation in light of personal change, to reassessment of inferences that affect their lives, and to time limits on the use of records in specified decisions. These proposals extend the ethics of AI beyond accuracy, transparency, and non-discrimination to address how long past wrongdoing should be allowed to govern a person's life.
Read the full abstract ▾
Artificial Intelligence
When Skills Remain But Access Fails: Factorized Skill Memory for Continual Skill Internalization
Haomiao Qiu, Yining Tang, Hongyi Wan et al. (+3 more)
Skill internalization aims to convert externally specified procedural skills into persistent model capabilities, allowing
language-model
agents to execute them without retrieving or reinjecting skill descriptions at inference time. Yet when new skills are learned continually, whether previously internalized skills remain usable is still poorly understood. We study forgetting in continual skill internalization and uncover a clear hierarchical structure. Early in subsequent training, a model may lose the ability to invoke an old skill from the raw request, while supplying only the correct canonical skill name substantially restores the learned behavior; with further optimization, this conditional execution also degrades. We call these two stages skill-addressing forgetting and skill-execution forgetting. Guided by this finding, we introduce Factorized Skill
Memory (FSM), which separates continual skill
memory into a plastic Address
Memory and a stable Execution
Memory. At each stage, FSM trains a new LoRA executor using only current-stage data, freezes it after acquisition, and appends it to Execution
Memory; in parallel, Address
Memory incrementally learns to map current requests to executors without replaying historical requests or execution trajectories. At inference time, Address
Memory selects one executor from the raw request, and only that frozen executor performs a single
language-model generation. On a five-stage
benchmark built from 100 TaskBench skills, FSM achieves 65.95% mean exact match and 93.38% addressing accuracy across two task orders, improving over the strongest replay-free parameter-isolation baseline by 14.3 percentage points while remaining within 1.9 points of Replay, which retains historical training examples.
Read the full abstract ▾
All authors Haomiao Qiu, Yining Tang, Hongyi Wan, Changfeng Sun, Ziyue Qiao, Miao Zhang
Artificial Intelligence · Cross-listed from cs.CR
Security in LLM-Assisted Coding: A Systematic Literature Review
Liang Yuan, Maryam Khanian Najafabadi, Mashud Rana et al. (+1 more)
Large
Language Models accelerate software development but introduce severe security vulnerabilities. This systematic review investigates security risks in automated coding,
benchmark limitations, and the role of human developers. Findings indicate that models frequently generate insecure code and faulty patches due to training data biases. Additionally, the models themselves are susceptible to direct attacks. Current evaluation methods suffer from data contamination and lack robust security metrics. Consequently, human oversight remains essential. Safer integration of automation will require more security-aware model architectures, stronger security-specific
benchmarks, and more effective human-AI collaboration frameworks to mitigate these systemic risks.
Read the full abstract ▾
All authors Liang Yuan, Maryam Khanian Najafabadi, Mashud Rana, Varvara Vetrova
Artificial Intelligence
SkillFusion: Towards Reliable Multi-Skill Composition for LLM Agents
Enhao Huang, Xinye Zhao, Yiming Li et al. (+5 more)
Independently authored skills can impose incompatible requirements, competing preferences, and redundant instructions when jointly loaded by an LLM
agent. We propose SkillFusion, an offline compiler that reconciles these interactions into a reusable merged skill. Its central idea is to make composition decisions explicit through typed, scoped constraints linked to their source directives. A type-scope gate selects candidate interactions, while selective fallback revisits pairs potentially missed by structural
pruning. A classifier identifies interaction types, and an
adversarial verifier re-examines uncertain judgments. The resolver applies conditional routing or explicit priorities to hard conflicts, verified abstraction to soft conflicts, and deduplication to redundant instructions. Source-linked checks guide synthesis and compression, and metadata synthesis supports discovery of the merged skill. The resulting artifact retains associated scripts and resources and can be reused across tasks and executor models. SkillFusion achieves the highest mean Success among evaluated non-oracle methods on all three
agent benchmarks and on both transfer
benchmarks across three executor models. At the largest tested instruction configurations, it achieves over 2.5 times the Success of unresolved multi-skill loading, highlighting the growing value of reconciliation as composition becomes more demanding. The code will be open-sourced after the review process concludes.
Read the full abstract ▾
All authors Enhao Huang, Xinye Zhao, Yiming Li, Bingrun Yang, Nanjun Zhou, Chunshu Xia, Hongwei Yao, Zhan Qin
Artificial Intelligence
MemeLogos: Knowledge-Driven Retrieval-Augmented Reasoning for Harmful Meme Detection
Hexiang Gu, Saihui Hou, Changlan Liu et al. (+4 more)
With the rapid proliferation of social media, harmful memes have become a growing threat to online ecosystems. Their harmfulness is often implicitly conveyed through complex interactions among visual, textual, and contextual cues, making accurate detection challenging. Recent studies have introduced
Retrieval-Augmented Generation (RAG) and external knowledge into harmful meme detection. However, existing methods mainly retrieve similar instances or auxiliary information, limiting their ability to capture reusable harmfulness knowledge and underlying
reasoning mechanisms, and thus constraining both detection performance and interpretability. To address these challenges, we propose MemeLogos, a knowledge-driven
retrieval-augmented
reasoning framework for harmful meme detection. MemeLogos abstracts recurring harmfulness patterns and
reasoning structures from diverse harmful cases into reusable knowledge units and organizes them into a dedicated
star-shaped knowledge graph. By combining structured knowledge
retrieval with an explicit multi-stage
reasoning process inspired by cognitive mechanisms, MemeLogos leverages retrieved knowledge to guide harmfulness
reasoning, improving both detection reliability and interpretability. Extensive experiments show that MemeLogos consistently outperforms existing harmful meme detection methods while generating more coherent and interpretable
reasoning, demonstrating the effectiveness of structured harmfulness knowledge for
multimodal content understanding.
Read the full abstract ▾
All authors Hexiang Gu, Saihui Hou, Changlan Liu, Min Ren, Huijia Wu, Hongxun Gu, Zhaofeng He
Artificial Intelligence
Scalable Robust MCTS with Anytime Deterministic Optimality Guarantees
Tomer Massas and Vadim Indelman
MDP planners often rely on nominal transition models that may differ from the true dynamics. Robust MDP planning accounts for this uncertainty through a set of admissible models, but doing so with limited online computation is challenging: the search tree grows exponentially with the horizon and each robust backup requires an additional optimization. Existing online robust methods remain limited in scale and offer at most probabilistic guarantees. We introduce, to the best of our knowledge, the first deterministic anytime guarantees for robust online MDP planning. We restrict computation to the sampled search tree while deterministically bounding the contribution of unsampled trajectories. For any fixed policy, we derive lower and upper bounds on the gap between its projected and true robust values under rectangular and non-rectangular uncertainty sets. Under rectangular uncertainty, we propagate these bounds through the robust Bellman operator to bound the optimal robust value. These bounds are computable from the current sampled tree, hold at every node, tighten as the sampled support expands, and converge to the robust values as full support is recovered. We develop CAR-MCTS, a bound-guided MCTS planner that uses these deterministic bounds to guide exploration, prune provably suboptimal branches, and terminate once the optimal root action is certified. The fixed-policy bounds also yield an anytime policy-evaluation mechanism that certifies the robust value of any policy, independent of how it was obtained. Experiments verify the deterministic bounds, their tightening under support expansion, substantial branch
pruning, root-action certification, and convergence to the optimal robust policy. To our knowledge, this is the first scalable robust MCTS framework with anytime deterministic guarantees for both online planning and policy evaluation, without enumerating the full state space.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SE
When Messages Go Wrong: Understanding Communication Faults in LLM-Based Multi-Agent Systems
Jinhao Zhou, Xiaoyu Zhang, Jiongchi Yu et al. (+2 more)
LLM-based multi-
agent systems (LLM-MAS) use specialized
agents that exchange messages to accomplish complex tasks. Their reliance on networked protocols, remote tools, and model endpoints exposes communication to message loss, delay, and context expiration. Because
agents often exchange open-ended natural
language, anomalies can alter task-relevant information while leaving messages processable, allowing semantic errors to propagate through subsequent interactions. Systematic studies of faults in inter-
agent communication remain limited. This paper presents a large-scale empirical study of how communication faults manifest, propagate, and affect task outcomes in LLM-MAS. We construct a cross-layer taxonomy linking lower-stack disturbances to application-visible faults and develop a fault-injection and tracing pipeline. Our evaluation covers more than 29,000 executions across 100 tasks, five domains, three workflow
topologies, and three model configurations. We find that 20.7% of failures with complete detection records occur without an immediate failure signal, reaching 76.2% for partial-content faults. Flat maintains 53.0% task success under communication faults, compared with 3.3% and 3.2% for Sequential and Hierarchical, respectively. This advantage primarily arises when an alternative information path preserves the evidence required by downstream
agents. We also evaluate execution-side and evidence protection mechanisms and find that they recover different failure cases. Evidence recovery depends on whether trustworthy information remains accessible through an unaffected path. These observations provide empirical insights into communication-fault propagation, workflow resilience, and protection design for LLM-MAS.
Read the full abstract ▾
All authors Jinhao Zhou, Xiaoyu Zhang, Jiongchi Yu, Fahao Chen, Jun Wu
Artificial Intelligence · Cross-listed from cs.SD
BridgeCodec: Mamba Enhanced Neural Audio Codec with Schrödinger Bridge at Low Bitrate
Zijian Lin, Jing Yang, Jinghao Luo et al. (+3 more)
Neural audio codecs achieve remarkable performance but operate as closed ecosystems with rigidly co-trained encoderdecoder pairs, severely hindering interoperability. To resolve this, we propose BridgeCodec, a versatile framework that decouples these pairs by translating latent representations between mismatched, frozen endpoints. We formulate this cross-codec translation as a Schrödinger Bridge optimal transport problem, enabling robust mapping between disparate distributions without predefined noise priors. To efficiently capture longrange
speech temporal dependencies, we integrate a Mambaenhanced U-Net architecture. We validate BridgeCodec on an extreme deployment scenario: mapping a lightweight 8 kHz source encoder directly to a 48 kHz target decoder at an ultralow bitrate of 1 kbps. Experimental results demonstrate that BridgeCodec achieves superior wideband reconstruction and high perceptual quality, successfully bridging heavily bottlenecked, heterogeneous codecs.
Read the full abstract ▾
All authors Zijian Lin, Jing Yang, Jinghao Luo, Zhuo Wang, Fan Fan, Zhiyong Wu
Artificial Intelligence
Hidden in Plain Sight: Advancing Harmful Content Understanding via Perception-Aware Adversarial Self-Play
Yisong Xiao, Benlei Cui, Haiwen Hong et al. (+8 more)
Despite significant advances in
language understanding, Large
Language Models (LLMs) can still miss meaning hidden in plain sight, failing to identify harmful intent in expressions readily understood by humans. Malicious users exploit this gap by strategically disguising harmful content to evade automated moderation, posing a serious threat to online platform safety. The vulnerability reflects a fundamental cognitive asymmetry between human readers, who integrate contextual, phonetic, and visual cues to decipher the intent behind deliberate obfuscation, and text-based LLMs, which rely primarily on
token sequences and have limited exposure to evolving evasions. To bridge this asymmetry, we propose PASP (Perception-Aware
Adversarial Self-Play), which combines multi-perceptual views with
adversarial self-play to improve understanding of harmful intent as evasions evolve. Specifically, PASP constructs textual, phonetic, and visual views of each input, preserving its original context while exposing pronunciation and glyph cues obscured in
token space. During
adversarial self-play, an attacker uses defender feedback to generate intent-preserving evasions, while the defender is trained using an intent-invariance reward to understand harmful intent across changing surface forms. Extensive experiments show that PASP reduces adaptive attack success rates by up to 73.71% and 74.49% on ChineseHarm-Bench and EvoHarmBench, respectively, preserves model capabilities with minimal degradation, and effectively interprets real-world evasive expressions in e-commerce.
Read the full abstract ▾
All authors Yisong Xiao, Benlei Cui, Haiwen Hong, Shiji Zhao, Zonghao Ying, Yaoyuan Zhang, Longtao Huang, Aishan Liu, Hui Xue, Ting Ma, Xianglong Liu
Artificial Intelligence · Cross-listed from cs.LG
World Modeling through Spectral Alignment
Holger Molin, William Peng, Marco Bagatella et al. (+1 more)
How do we tell a world model what information to preserve? We study this question through the lens of spectral representation learning. We introduce SpecWM, a JEPA framework that explicitly specifies desired relationships between observations through a target similarity kernel and trains the encoder to reproduce those relationships in its
embedding geometry. Different kernels provide different supervision, ranging from physical state information to a fully self-supervised temporal kernel requiring only the ordering of observations within trajectories. We characterize the global optima of the objective, establish conditions for linear recoverability and invariance to nuisance information, and connect temporal-kernel similarity to the behavioral successor measure under an idealized setting. Empirically, the choice of kernel strongly controls which physical quantities are recoverable from the representation. More importantly, temporal spectral
alignment improves CEM planning success over LeWorldModel from 52% to 68% on OGBench Cube, 49% to 77% on OGBench Scene, and 29% to 51% on CALVIN. These results suggest that explicitly specifying representation geometry provides a simple way to steer what latent world models preserve for control.
Read the full abstract ▾
All authors Holger Molin, William Peng, Marco Bagatella, Randall Balestriero
Artificial Intelligence · Cross-listed from cs.LG
Pessimistic Latent Task-aware Optimization for Robust Offline Meta-Reinforcement Learning
Chang-Hoon Jeong, Kisung Shin, Hanwool Sul et al. (+1 more)
Context-based offline meta-reinforcement learning (COMRL) has advanced almost entirely through better task representations, which separate task identity from artifacts of the behavior policy so that the latent reflects the task alone. The implicit expectation has been that a clean representation will transfer to out-of-support (parameter-extrapolation) tasks. On such a task, however, the encoder produces a latent outside the training support, where the policy has never been trained. We address this gap with Pessimistic Latent Task-aware Optimization (PLATO), which exposes the policy to off-support latents during training. PLATO assumes a mild
manifold hypothesis: task latents lie on a low-dimensional
manifold, and out-of-support tasks lie farther from the training centroid. It exploits this geometry by perturbing inferred latents outward from the centroid to synthesize counterfactual tasks. A learned decoder ensemble then rolls out short trajectories at each perturbed latent, and the policy is updated on the imagined transitions under a pessimism weight that down-weights steps on which the ensemble disagrees. We prove that the perturbation leaves the training support by a controllable margin and that the out-of-support generalization gap is bounded by the same perturbation reach, and we give explicit conditions, verified empirically, under which the epistemic disagreement at the perturbed latent stays bounded away from zero. On eight MuJoCo continuous-control
benchmarks, PLATO consistently improves out-of-support returns over strong COMRL baselines while remaining competitive on in-distribution tasks. Our code is available at https://github.com/deephoony/plato.
Read the full abstract ▾
All authors Chang-Hoon Jeong, Kisung Shin, Hanwool Sul, Byoung-Tak Zhang
Artificial Intelligence
SpecFit: Not All Draft Tokens Cost the Same in Offloaded MoE Inference
Hongliang Cao, Xiuyu Li, Siqi Wang et al. (+3 more)
Mixture-of-experts (MoE) models activate only a few experts per
token, but when their expert weights are offloaded to host
memory, host-to-device (H2D) expert transfers enter the critical path of decoding. Speculative decoding verifies several draft
tokens in one forward pass, yet in an MoE model each verified
token activates its own experts, so a larger draft tree transfers more experts. Because of this H2D cost, speculative decoding commits several
tokens per verification cycle yet is sometimes even slower than autoregressive decoding. Based on this observation, we propose SpecFit, which chooses the verified draft subtree to maximize predicted throughput rather than acceptance length. SpecFit estimates the expected number of committed
tokens from draft path probabilities and predicts cycle time from the node count and the per-layer union of the experts the subtree activates; this union is a monotone submodular coverage function, so each node pays only for the experts it adds. An exact search over ancestor-closed subtrees returns the subtree with the highest predicted throughput; run after each draft level, the same search also decides when to stop drafting, and the unmodified target verifies the result. On CNN/DailyMail summarization and a GSM8K subset with Qwen3-30B-A3B, SpecFit decodes 21.6% and 7.0% faster than EAGLE-3 with the same expert cache and 1.97x and 1.72x as fast as vanilla EAGLE-3. Code is available at https://github.com/Chlience/SpecFit.
Read the full abstract ▾
All authors Hongliang Cao, Xiuyu Li, Siqi Wang, Ziming Wang, Jingmin Zhu, Hailong Yang
Artificial Intelligence · Cross-listed from cs.CL
Sensitivity or Criterion? Measuring and Moving When Language Models Act
Sixun Dong, Yebowen Hu, Ming Yin et al. (+3 more)
Before an
agent acts, it must decide whether action is warranted. A single accuracy cannot distinguish failure to recognize a warranted action from reluctance to act. Signal-detection theory separates sensitivity from criterion, but criteria estimated from authored binary labels depend on each
benchmark's example mix. We introduce FlipAct, a diagnostic of tool use in physical states. A rule over annotated tool properties computes each answer and a graded evidence score, fixing the Yes/No boundary at zero across models. Questions form 2-by-2 quads that hold required knowledge fixed while the state flips. The slope of the fitted Yes-rate curve measures sensitivity; its crossing at one half measures criterion. Across 44 open models, sensitivity rises with size within a family, and its ranking agrees with three of four external when-to-act
benchmarks. Models respond to evidence sign rather than magnitude, accepting actions that leave the state no better about as often as helpful ones. When Yes means act, most models are conservative across rephrasings; in some, this partly reflects a preference for No. Criterion is not determined by size. Activation steering shifts criterion with weights fixed;
distillation from a model's own steered copy puts the shift into its weights without a significant sensitivity change. The distilled shift transfers to six external
benchmarks, including two without Yes/No answers, while criterion-free AUC is preserved on the five
benchmarks where it is available. Accuracy improves where models start conservative and declines or remains within error where they start permissive. Project page: https://sixundong.com/projects/flipact
Read the full abstract ▾
All authors Sixun Dong, Yebowen Hu, Ming Yin, Yiran Chen, Fei Liu, Chen Chen
Artificial Intelligence
CoverSynth: Coverage-Guided Generation of Retrieval Evaluation Sets
Anahita Sharma, Apaar Shanker, Rishav Chakravarti et al. (+6 more)
Enterprise
agents need
retrieval evaluation sets that expose domain-specific failures and guide developers towards efficient deployment tradeoffs. Neither expert-human-authored sets nor current synthetic generation methods provide a methodology for achieving the necessary coverage, reliability, efficiency, and discriminability required for such decision-making. Simultaneously, the field does not have an assessment framework for determining when an evaluation set has satisfied these properties. We introduce an evaluation set assessment framework for these criteria and CoverSynth – a generator specifically designed to satisfy these criteria without incurring the high cost of human expert labeling. Starting from an unannotated corpus, CoverSynth targets coverage across
retrieval demands and system capabilities. Deterministic checks locate evidence quotes in their sources, while model-based checks assess semantic validity to guarantee reliable ground truth. Across five public enterprise-style corpora, our method provides informative variation in difficulty, revealing unseen failure modes such as an inability of
agents to handle underspecified or ambiguous requests. On the RepLiQA corpus, 91% of human-generated queries can be answered by all members on a panel of 12
retrieval systems, compared to only 12% of CoverSynth-generated queries. Finally, in a repeated TechQA/RepLiQA study, 12 of 12 within-harness model contrasts have positive nominal 95% intervals on generated sets, compared with 4 of 12 on human sets. CoverSynth makes coverage and evidence quality explicit construction objectives, producing corpus-grounded evaluations that reveal
retrieval headroom and differences between
agent configurations.
Read the full abstract ▾
All authors Anahita Sharma, Apaar Shanker, Rishav Chakravarti, Sneha Srinivasan, Vijay Kalmath, Dylan Wilbur, Yuan Li, Sara Bolouki, Yuan Xue
Artificial Intelligence
State Representation Shapes Long-Horizon Agent Learning and Transfer: An Empirical Study
Dong Nie, Rui Lan, Yixin Nie et al. (+1 more)
An end-to-end success rate alone cannot distinguish failure to learn an action from failure to apply it as task state changes. We study this distinction in deterministic tool workflows that provide the current artifact state and candidate action recipes. Using 1.7B, 8B, and 27B Qwen models, we compare supervised learning across workflow horizons and cross the state representation used for training with the one used at evaluation. Horizon-matched supervision yields high completion, but an H4-trained 1.7B model transfers poorly to longer workflows under full-state observations. In an H16 crossover, compact-trained 1.7B adapters complete 50/50 held-out tasks in compact view and 0/50 in full view for each of three paired training seeds; full-trained outcomes vary across seeds. A separate 8B adapter pair shows a similar asymmetry. The view dependence also appears in paired-choice tasks where both candidate calls are executable and the correct choice depends on table contents; here, the compact mask does not consult the target action. An explicit relevance cue improves full-view execution but does not close the gap for the tested checkpoint. In a separate 27B ScienceWorld study, compact-state training improves local accuracy under both views, indicating that the transfer pattern depends on the task and observation construction. Together, these experiments identify representation-sensitive transfer as a bottleneck in the controlled workflows, without isolating content reduction from other changes to the observation.
Read the full abstract ▾
All authors Dong Nie, Rui Lan, Yixin Nie, Lingzi Hong
Artificial Intelligence
A Decade of PhotoMappers: A Longitudinal Study of Crowdsourced Disaster Photos Geolocalization with Vision-Language Models and Geospatial Reasoning
Hao Li, Wenping Yin, Fabian Deuser et al. (+5 more)
Crowdsourced disaster imagery provides timely, ground-level observations when conventional disaster mapping is delayed or incomplete, yet its geographic value depends on where observations are produced, how they are interpreted, and whether they can be reliably located as actionable Geospatial Intelligence (GEOINT). Using more than a decade of PhotoMappers, a crowdsourced disaster-mapping initiative, this study examines the changing geography of disaster information and asks how emerging GeoAI models compare with human geographic interpretation. We combine longitudinal spatial analysis with cross-view geolocalization using street view imagery (SVI) and remote sensing imagery (RSI), and evaluate
vision-
language models (VLMs)
reasoning through 30 indicators spanning geographic cues and
reasoning evidence. The results reveal a geographically and temporally uneven archive shaped by changing disaster types, Community Lifelines, and operational priorities. Integrating VGI, SVI, and RSI with Sinkhorn re-ranking achieves 40.90% R@1, 61.10% R@5, and 69.45% R@10, while yearly R@1 varies markedly from 25.00% to 65.07%. Geographic
reasoning is similarly uneven: Qwen3.6-27B achieves an overall agreement of 67% compared with 51% for InternVL3-8B, with both models showing greater difficulty with localized and place-specific evidence than broad spatial configurations. We argue that the value of GeoAI lies less in replacing volunteered geographic interpretation than in complementing it, scaling candidate
retrieval while retaining human judgment for ambiguous and consequential cases. This provides a pathway toward more human-centered and responsible GeoAI for disaster mapping. All data and code are openly available at https://github.com/bobleegogogo/PhotoMappers-VLM.
Read the full abstract ▾
All authors Hao Li, Wenping Yin, Fabian Deuser, Jia Jia, Ziqi Liu, Levente Juhász, Fan Zhang, Filip Biljecki
Artificial Intelligence · Cross-listed from cs.LG
E8 Lattice Key Quantization for Low-Bit KV-Cache Compression
Sasho Nedelkoski, Alexander Acker, Soeren Becker et al. (+2 more)
Compressing the key-value (KV) cache is essential for serving long-context large
language models (LLMs) under
memory constraints. While current scalar quantization methods achieve significant compression, they typically face a quality-fidelity trade-off, either suffering from performance instability at 2-bit precision or necessitating 3-bit keys to maintain model quality. In this work, we demonstrate that a uniform low-bit k2v2 configuration (2-bit keys and 2-bit values) can preserve near-baseline quality by using vector quantization (VQ) based on the $E_8$
lattice for KV keys. We show that structured VQ exploits correlations across adjacent dimensions to achieve signal-to-quantization-noise ratios (SQNR) higher than those of independent scalar quantization at the same key payload rate. To ensure practical utility, we adapt a table-based asymmetric scoring
algorithm that avoids explicit codebook dequantization during
attention computation and preserves decode-throughput parity with scalar baselines. Across five LLM families, our $E_8$ k2v2 approach yields \textasciitilde$6\times$ KV compression, roughly 20% smaller than scalar k3v2 (3-bit keys and 2-bit values), while retaining near-baseline long-context perplexity. In our full-suite perplexity evaluation, $E_8$ improves over scalar k3v2 in 80% of model–
dataset–context settings. These results indicate that $E_8$
lattice VQ improves quality per byte while keeping throughput at parity, suggesting that structured key quantization is a useful primitive for KV-compression stacks. Overall, our work provides a low-overhead primitive for expanding the quality-
memory frontier in long-context LLM inference.
Read the full abstract ▾
All authors Sasho Nedelkoski, Alexander Acker, Soeren Becker, Dominik Scheinert, Odej Kao