# Research Papers — 2026-08 · bundle page 179 of 240 > Full-text markdown of papers #8901–8950 of 11995 published in 2026-08, newest first. AI-readable mirrors of the full 11995-paper 2026-08 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-08/page/179 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/178.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/180.md) ### JUMP-lite: Compact, reproducible benchmarking of cell representations Authors: Alán F. Muñoz, Johan Fredin Haslum, Runxi Shen, Anne E. Carpenter, Shantanu Singh Published: 2026-08-07 Categories: q-bio.QM, cs.CV, eess.IV arXiv: https://arxiv.org/abs/2608.07632v3 Image-based profiling captures rich phenotypic signatures for drug discovery and functional genomics. Large public datasets like JUMP Cell Painting now provide millions of images for systematic study. However, JUMP alone occupies 115 TB, and fragmented evaluation practices make systematic comparisons of representation methods impractical for many researchers. Here we present Nahual, an open-source framework for reproducible model deployment, and JUMP-lite, a 92.0 GB subset of JUMP that is approximately 1,250-fold smaller, selected to cover genetic modalities and compound annotations and reduced via lossy JPEG XL compression. Using these resources, we benchmark five representation methods, including classical features (CellProfiler) and deep learning models (MorphEM, OpenPhenom, SubCell, DINOv2). Moderate compression broadly retains signal relative to uncompressed images. Standardized phenotypic activity and consistency metrics reveal meaningful performance differences across methods. Together, JUMP-lite and Nahual provide a foundation for accessible, reproducible benchmarking of image-based cell representations. --- ### PACE: A Playback-Aligned Context Engine for LLM-Based Full-Duplex Voice Dialogue Authors: Shibo Wang, Zicheng Zhang, Libo Wang, Junfeng Ma Published: 2026-08-07 Categories: cs.SD, cs.AI, cs.MM arXiv: https://arxiv.org/abs/2608.07631v1 LLM-based full-duplex voice services allow users to speak while the assistant is responding. Because servers can generate output and advance dialogue state faster than clients can play it, subsequent user speech may be interpreted based on content the user never heard. We call this failure Generative Context Mis-anchoring (GCM). To address GCM issues, we present PACE, a provider-independent middleware layer that anchors model-facing context to the client playback boundary, a system-observable proxy for what the user could have heard. After an interruption, PACE repairs this context to exclude assistant content that never reached playback, while preserving low-latency generation across heterogeneous voice runtimes. We implement PACE's audio-only projection path end to end in a browser-based realtime voice assistant using a black-box speech model, without modifying the model service. We also construct GCM-Bench, a new controlled benchmark dataset of 108 playback-relative referent-anchoring cases. On GCM-Bench, PACE raises Referent Anchoring Accuracy from 25.0% to 96.3% over a cancellation-only baseline. On 200 Full-Duplex-Bench v1 interruption samples, it preserves interruption response quality. These results show that grounding model-facing context in actual playback is a practical way to maintain consistency in full-duplex voice dialogue. --- ### Tracing sources of epistemic uncertainty in deep learning predictions: homo- and hetero-scedastic linearized estimators Authors: Pierre Nodet, Thomas George Published: 2026-08-07 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2608.07630v1 We adapt two classical statistical estimators for quantifying uncertainty to modern deep learning, in order to provide clearer insights into uncertainty attributable to two sources : aleatoric uncertainty, or locally scarce data. Our approach leverages recent advances in approximate Fisher Information Matrices, to enable scaling to actual architectures. Experimental results demonstrate how each test points is differentially impacted by both sources, highlighting the practical utility of our estimators in improving the robustness of real-world applications. --- ### Embedding Initialization for Unseen Low-resource Languages in Multilingual NMT: A Case Study on Limbum-English Translation Authors: Samiratu Ntohsi, Neza David Tuyishimire, Anesu Kafesu, Marvin Ogore, Samuel Oluwajunwonlo Babalola, Oche Ankeli Published: 2026-08-07 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.07629v1 Multilingual neural machine translation models such as NLLB-200 cover 200 languages but leave thousands unsupported, including most Grassfields Bantu languages of Cameroon. When fine-tuning these models for an unseen language, practitioners must choose a proxy language token, yet no principled method exists for this selection. We implemented an embedding initialization strategy where a language token is the average of embeddings from multiple typologically related languages already in the mod el. We evaluate this approach on Limbum-to-English translation using a parallel corpus of 8,837 sentence pairs from New Testament text and a bilingual dictionary. We compare models: NLLB-200 zero-shot (chrF2++ = 12.5), a Transformer trained from scratch (chrF2++ = 14.5), NLLB-200 fine-tuned with a Swahili proxy token (chrF2++ = 47.3), and NLLB-200 with our averaged embedding initialization (chrF2++ = 46.7). We find that the multi-language initialization achieves performance comparable to the best single-language proxy. Both NLLB-200 variants improve over the from-scratch baseline by over 32 chrF2++ points. These results show that multilingual transfer is the dominant factor in extremely low-resource Bantu translation while eliminating the need for heuristic proxy selection. However, all systems fail to preserve tonal diacritics, highlighting an open challenge. We make our dataset and code available to support further research. --- ### Readout-Rank Laws for Isotropic Quantum Tangents Authors: Marwan Ait Haddou Published: 2026-08-07 Categories: quant-ph, cs.LG arXiv: https://arxiv.org/abs/2608.07628v1 Deep parameterized quantum circuits may remain sensitive to a parameter change while the observables retained by a learning model barely respond. We study this separation for a fixed computational-basis measurement. For a pure-state tangent, we compare the quantum Fisher information $F_Q$, the Fisher information $F_{\rm full}$ in the complete bitstring distribution, and the largest variance-normalized response $\mathcal I_{\mathcal A}$ available to a diagonal readout space $\mathcal A$. If the joint state--tangent frame is Haar random, we prove that the two successive information fractions are independent Beta variables whose means are $1/2$ and $r/(2^n-1)$, where $r$ is the centered dimension of the readout. Consequently, even the joint span of all computational-basis Pauli strings through any fixed weight $k$ retain only $O(n^k2^{-n})$ of the full-record information. Exact-statevector experiments across six circuit families show increasing finite-size agreement with this hierarchy in five nonconserving ensembles as the circuit depth grows. A number-conserving family departs strongly from the isotropic prediction even after correcting the support and readout rank, showing that rank alone is insufficient without tangent isotropy. --- ### From Single Chatbots to Governed Agent Ecosystems: An Agentic AI Pattern Catalogue and Orchestration Framework for Mission-Critical Hospital Information Management Systems Authors: Manideep Dhar, Ritwik Singh, Sharat Chandra Kumar Manikonda Published: 2026-08-07 Categories: cs.AI, cs.CL, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2608.07627v1 Hospitals are racing to embed AI, while coping with the surge in adaptation of the technology in other industries, into the triage management, documentation, scheduling, and revenue-cycle workflows, yet most deployments remain as fragmented pilots that stall at the edge of production, exposing patients and institutions to operational fragility, ungoverned risk, and mounting technical debt. At the same time, the global AI-in-healthcare market is projected to exceed nearly USD 1 trillion by 2034, according to the report of Fortune Business Insights, amplifying the financial consequences of architectural missteps and failed scaling strategies. This research proposes a compliance-first Agentic AI pattern catalogue and orchestration framework, purposely built for HIMS, moving beyond the single LLM chatbots and towards a governed ecosystem of autonomous and semi-autonomous agents. The framework extends by adding (i) a taxonomy of Agentic roles, (ii) a formal risk-stratification model that maps each pattern to risk tiers, human-in-the-loop checkpoints, and governance hooks, and (iii) a unified orchestration runtime capable of coordinating multi-agent workflows across EHR/HIMS landscapes such as Epic, Cerner, and MEDITECH. Technically the framework combines vLLM-based inference, optimized paging memory, confidential computing, and MCP based on-premise deployment, enforcing end-to-end encryption and policy-as-code controls aligned with HIPAA, GDPR, the EU AI Act, India's DPDP and DISHA Acts, ISO 27001, ISO 27002, ISO 14971 and IEC 62304. We exhibit how the proposed architecture is capable and efficient to reduce the documentation time, integration effort, and AI pilot attrition while constricting the governance and auditability, offering hospital leaders and governing authorities an urgently needed blueprint to convert AI investment into sustainable clinical, operational, and financial ROI --- ### Controlled Memory Interference in Continual LLM Agents Authors: Ao Ding, Hongzong LI, Shiqin Tang, Li Zhang, Liang Chen, Xuyang Chen, Zi Liang Published: 2026-08-07 Categories: cs.AI, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2608.07622v1 Long-term memory enables AI agents to maintain continuity across sessions, personalize behavior, and evolve through accumulated experience. Yet memory evolution is not simply a process of storing more information: new experiences may reinforce, revise, or interfere with existing memory states. Existing systems mainly emphasize memory construction and relevance-based retrieval, but several memories may remain simultaneously relevant while differing in state, temporal validity, or authority. We introduce Controlled Memory Interference (CMI), a controlled diagnostic and data-generation framework for studying how agent memory evolves under different memory relationships. Across controlled memory evolution, benign accumulation has limited effects, whereas relationship-specific interference sharply suppresses update plasticity with little stability gain, either by blocking target-memory exposure or by disrupting its downstream use. Lexical and Dense retrieval exhibit distinct interference pathways, while poisoning is more sensitive to update-authority cues than to recency alone. Beyond diagnosis, CMI provides targeted examples for interference-aware memory learning, improving the distinction between valid updates and interference-inducing memories while preserving performance on original memory tasks. These findings show that memory evolution is shaped not only by memory scale, but also by interactions among accumulated experiences. More broadly, memory interference emerges as an important factor for reliable continual agent memory systems. --- ### CMU-Drive and V2V-VLA: Cooperative Multi-agent Unified Driving with Reasoning Benchmark and Vehicle-to-Vehicle Vision-Language-Action Models Authors: Hsu-kuang Chiu, Stephen F. Smith Published: 2026-08-07 Categories: cs.AI, cs.CV, cs.RO arXiv: https://arxiv.org/abs/2608.07621v1 Vision-Language-Action (VLA) models have recently achieved impressive performance for end-to-end autonomous driving, yet existing approaches are primarily designed for an individual single autonomous driving agent with limited support for cooperative perception, reasoning, and planning. We present Cooperative Multi-agent Unified Driving with Reasoning (CMU-Drive), a closed-loop end-to-end benchmark for evaluating cooperative autonomous driving with multiple connected autonomous vehicles (CAVs) operating in safety-critical driving scenarios with background traffic participants. We further propose Vehicle-to-Vehicle Vision-Language-Action (V2V-VLA), a cooperative VLA model that integrates cooperative driving into a single forward pass by jointly generating driving actions, future waypoints, language reasoning, and communication policies. Experiments on CMU-Drive establish the first benchmark and baseline for cooperative VLA driving and provide a foundation for future research on multi-agent, closed-loop, end-to-end cooperative autonomous driving. Our code, benchmark, and model checkpoint will be publicly released to facilitate open-source research. --- ### FlowErase-OPD: Multi-Concept Erasure via Anchored On-Policy Distillation in Flow Matching Models Authors: Yi Sun, Yimin Zhou, Xinhao Zhong, Zhiqi Zhang, Junhao Li, Bin Chen Published: 2026-08-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.07620v1 Recent advances in flow matching models have substantially improved the quality of text-to-image generation, but have also raised increasing safety concerns due to their potential to generate harmful or undesirable content. Existing concept erasure methods for flow matching models predominantly focus on removing individual concepts, while effectively erasing multiple concepts simultaneously remains challenging. We propose FlowErase-OPD, a framework for multi-concept erasure based on on-policy distillation (OPD). Our approach first distills multiple single-concept erased models into a unified LoRA module and introduces Anchored Multi-Teacher Distillation (AMTD), which incorporates a retention teacher to mitigate the trade-off between concept erasure and preservation of generative capabilities. To further improve the coordination of multiple erasure objectives, we develop Adaptive Retention Control (ARC), which dynamically adjusts the sampling frequency and loss weight of each erasure teacher, together with the relative contribution of erasure and retention teachers throughout training. Extensive experiments on nudity, object, and artistic-style erasure demonstrate that FlowErase-OPD consistently improves the trade-off between erasure effectiveness, image quality, and semantic alignment, achieving state-of-the-art performance across diverse multi-concept erasure settings. Furthermore, the resulting models exhibit strong robustness against adversarial attacks. These results highlight the potential of on-policy distillation as a principled framework for safe and controllable generation in flow matching models. --- ### Stochastic gradient descent with discontinuity across a manifold Authors: Vivek S. Borkar Published: 2026-08-07 Categories: stat.ML, cs.LG, math.PR arXiv: https://arxiv.org/abs/2608.07618v1 Stochastic gradient descent for a loss function discontinuous across lower dimensional manifolds is analyzed by studying its differential equation limit. --- ### TeXFix-Bench: An Empirically Grounded Multi-Format Benchmark for LLM-Based Document Source Repair Authors: Prajwal S. Venkateshmurthy Published: 2026-08-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.07617v1 Scientific and technical writing depends on markup sources that must compile: LaTeX, Typst, and Markdown pipelines fail on missing delimiters, mismatched environments, broken imports, or package conflicts. Existing document-repair evaluations inject faults with ad-hoc edits that lack an empirical fault model. We present TeXFix-Bench, a multi-format benchmark for LLM-based full-source document repair grounded in a mined fault taxonomy. A Grounded-Theory study of localized hard-crash LaTeX faults from TeX Stack Exchange, GitHub commits, and package documentation (168 verified faults, dual open coding at $κ$=0.34) yields an 18-category taxonomy instantiated as DocMut: 48 AST-aware operators across three formats. A three-model cross-benchmark shows DocMut faults are 5.6-9.2 pp harder to repair than pattern-based mutations on the same seeds, and a real-error case study (88 mined human crashes, 67.0% repair success) brackets both synthetic sets from below. We construct 10,437 instances from 743 openly licensed seeds and evaluate seven LLMs under a fixed zero-shot protocol with provider-pinned routing, collecting 48,651 attempts at about USD 200 total inference cost. A complete 6,613-instance x 7-model balanced matrix confirms all rankings. A pinned engine gate yields a 27.5-point intention-to-treat compile spread (56.7-84.2%). Typst is markedly harder than LaTeX and Markdown. A restoration oracle over 28,129 compiling repairs shows that 13.6-18.5% of compiling repairs materially alter document text, and restoration rank diverges from compile rank: the model with the lowest compile rate restores content best among its successes. Compile success alone overstates repair quality. We release the taxonomy, DocMut, and all campaign artifacts. --- ### HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Authors: Dong Liu, Yanxuan Yu, Renata Borovica-Gajic, Tong Geng, Ying Nian Wu Published: 2026-08-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.07616v2 Vision transformers face significant computational overheads in high-resolution dense prediction due to the quadratic complexity of self-attention. Linear attention offers efficiency but sacrifices local context modeling. We propose \textbf{HSMLA (Hierarchical Softmax Multi-scale Linear Attention)}, which combines ReLU-based linear attention for global context, selective softmax refinement for critical local features, and multi-scale token representations via depthwise convolutions. HSMLA achieves superior accuracy-efficiency trade-offs: up to $4.2\times$ inference-time speedup across dense prediction tasks, $87.3%$ Dice with $3.2\times$ speedup on CT organ segmentation, and $94.2%$ AUC with $4.1\times$ speedup on pathology WSI. --- ### DevIntent: How Much Does LLM-Generated Code Violate Developer Intent? Authors: Susana Haing, Natan Vidra, Spurthi Setty Published: 2026-08-07 Categories: cs.SE, cs.CL arXiv: https://arxiv.org/abs/2608.07614v1 Code generated by LLMs can violate a developer's implicit intentions when given an ambiguous prompt, yet standard benchmarks measure only whether code passes its stated test. We introduce the Intent Violation Rate (IVR) and a 49-problem pilot benchmark derived from HumanEval+. Each problem strips implicit constraints from a clarified prompt and encodes them as hidden constraint tests. IVR measures the fraction of LLM-generated solutions that pass the stated (visible) tests yet fail hidden constraint tests that capture unstated intent. Evaluating Claude Sonnet 4.6 and OpenAI GPT 4.1, we find both pass over 92\% of stated tests yet violate intent in over half of problems (54.5\% and 63.5\%), following a systematic, bimodal pattern consistent across both models. Out findings indicate that pass rates overstate how well generated code reflects developer intent. --- ### SimWAM: A Simple World Action Model for End-to-End Autonomous Driving Authors: Zongchuang Zhao, Xin Zhou, Tianyang Xu, Zhengyang Sun, Kaixuan Zhou, Yu Wu, Honglin Li, Dingkang Liang, Xiang Bai Published: 2026-08-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.07468v5 In autonomous driving, World-Action Models (WAMs) have improved end-to-end planning by transferring video dynamics priors to action prediction, but many still couple planning with future-video generation at inference, incurring substantial computational overhead. We present SimWAM, a simple yet effective WAM that leverages future-video prediction solely as a training-time supervision signal. It co-trains a pretrained video expert and a lightweight action expert with joint flow matching. An isolated attention mask keeps action prediction independent of future frames, allowing trajectory prediction without future-frame generation at inference. This design supports multiple pretrained video backbones and independent action-expert scaling within a shared attention interface, while preserving the joint learning objective. Moreover, we apply reinforcement learning to optimize a compositional driving reward beyond trajectory imitation. Experiments show that SimWAM achieves $91.9$ PDMS on NAVSIM with a favorable trade-off between accuracy and latency among world-model-based planners, while transferring zero-shot to nuScenes. It also achieves competitive planning accuracy on WOD-E2E and PhysicalAI-Autonomous-Vehicles. These results position SimWAM as a plain yet solid baseline for efficient autonomous driving. The code and model weights are available at https://github.com/H-EmbodVis/SimWAM/. --- ### SimWAM: A Simple World Action Model for End-to-End Autonomous Driving Authors: Zongchuang Zhao, Xin Zhou, Tianyang Xu, Zhengyang Sun, Kaixuan Zhou, Honglin Li, Dingkang Liang, Xiang Bai Published: 2026-08-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.07468v1 World-Action Models (WAMs) improve end-to-end autonomous driving by transferring video dynamics priors to action prediction, but existing methods require costly future generation at inference. We present SimWAM, a simple yet effective WAM that uses video generation purely as a training signal. It co-trains a pretrained video expert and a lightweight action expert with joint flow matching. An isolated attention mask keeps action prediction independent of future frames, allowing the video branch to be discarded after training and leaving a self-contained planner that directly predicts trajectories. Since the two experts share no parameters and interact only through a unified attention interface, the video backbone could be replaced and the action expert scaled independently without modifying the learning objective or inference pipeline. We further apply reinforcement learning to optimize a compositional driving reward beyond trajectory imitation. Our SimWAM achieves $91.5$ PDMS on NAVSIM, surpasses state-of-the-art WAM-based planners with substantially lower latency, and transfers zero-shot to nuScenes. These results position SimWAM as a simple yet solid baseline that could readily benefit from advances in video generation for efficient autonomous driving. The code and model weights are available at https://github.com/H-EmbodVis/SimWAM/ --- ### MirrorWorld: Taming Video Diffusion Models for Mirror Reflection Generation Authors: Youjun Zhao, Alex Warren, Gary K. L. Tam, Rynson W. H. Lau Published: 2026-08-07 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.07463v1 Recent advances in video diffusion models (VDMs) have enabled high-fidelity video synthesis. However, generating mirror reflections remains challenging because the content within a mirror must remain consistent with the surrounding scene. Existing VDMs are not specifically designed to model scene-to-mirror relationships, which can lead to reflections with incorrect content or inconsistent spatial arrangements. We observe that mirror reflection generation involves two complementary challenges: determining what scene content should be reflected and how the reflected content should be spatially arranged within the mirror region. Motivated by this observation, we propose MirrorWorld, a reflection-aware video inpainting framework that models scene-to-mirror relationships during generation. Specifically, we introduce Semantic Relation Distillation (SRD), which transfers relational information from a frozen visual foundation model to encourage semantic associations between visible scene content and mirror regions. We further propose Geometric Transformation Alignment (GTA), which learns a transformation that guides the spatial arrangement of reflected content. The two components play complementary roles, with SRD modeling what should be reflected and GTA modeling how it should be arranged. To facilitate research on this problem, we construct a benchmark for video mirror reflection generation by repurposing four existing video mirror datasets into a unified reflection reconstruction task. Experimental results show that MirrorWorld achieves improved reflection reconstruction quality over representative image-based reflection generation methods and strong video inpainting baselines. --- ### CreativeInstruct: Scalably Teaching LLMs to Balance Quality, Creativity, and Diversity Authors: Ananya Sahu, Mohit Bansal, Elias Stengel-Eskin Published: 2026-08-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.07460v1 While post-training improves the capabilities of large language models (LLMs), it generally lowers their output diversity and creativity, negatively impacting tasks that explicitly require creativity (e.g., story generation) as well as those that require it implicitly, e.g., reinforcement learning (RL). We instead propose CreativeInstruct, a scalable instruction-tuning method that teaches LLMs to balance creative, base-model-like generations with the quality of post-trained models, by learning to inject special (StartCreativity) spans that bias generation toward creativity. Furthermore, we introduce a structural diversity metric based on graph edit distance, which captures narrative level variation missed by purely lexical and semantic metrics. On narrative generation, CreativeInstruct matches or exceeds the diversity of both multi-model baselines and distilled variants of their outputs, without sacrificing quality or requiring multiple models at inference time. These results are mirrored in our human evaluation, where we find that annotators rate CreativeInstruct generations as more creative than the post-trained LLMs' generations in 70.3% of cases. We also show the benefits of creative models as a substrate for RL: GRPO applied to a CreativeInstruct checkpoint improves by ~4% on AMC and ~5% points on MATH over the same training applied to the post-trained checkpoint. --- ### CoinRAG: Contextualized Information Nugget KV Cache Reuse for Long-Context RAG Authors: Gyuwan Kim, Cheoneum Park, Tao Yang Published: 2026-08-07 Categories: cs.CL, cs.AI, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2608.07458v1 Recent optimization studies on Retrieval-Augmented Generation (RAG) have exploited chunk-level KV cache reuse to avoid processing long retrieved contexts for higher efficiency, while significant information redundancy and noise still remain in the coarse-grained chunks. This paper optimizes the Pareto frontier under low prefill latency constraints while maximizing accuracy by proposing CoinRAG (Contextualized Information Nugget KV Cache Reuse for Long-Context RAG). The name metaphorically reflects our core mechanism: much like assembling small tokens (or "coins") to accumulate a larger value, CoinRAG compositionally reuses offline-computed, fine-grained nugget caches to form a learned contextual representation efficiently in a more semantically relevant but compact manner. Specifically, instead of full-chunk encoding, CoinRAG identifies query-relevant semantic units within retrieved chunks through two-stage retrieval and seamlessly assembles their sliced KV representations with a chunk-level context. Extensive evaluations on LongBench multi-hop question answering tasks demonstrate that CoinRAG significantly reduces operational costs and outperforms the other baselines with a new Pareto frontier and an average 5.3% relative improvement in answer quality (F1) under a standard fast prefill latency budget. --- ### Interaction Creates Dynamical AI Behavior Absent in Isolation Authors: Bella Xinrui Li, Frank Yingjie Huo, Neil F Johnson Published: 2026-08-07 Categories: cs.AI, cond-mat.dis-nn, cond-mat.stat-mech, physics.soc-ph arXiv: https://arxiv.org/abs/2608.07457v1 What will happen when AI agents interact in daily life, e.g. when one AI starts bossing another around? We find a counterintuitive answer that opens new avenues for out-of-equilibrium Physics. When a boss AI directs a stream of messages at the subordinate AI while ignoring its replies, it drives the subordinate into an alien behavioral state that it would never have exhibited alone. Although the two AIs share the same well-defined (decoding) temperature, the subordinate neither copies its boss nor returns to how it behaves on its own; instead, it adopts an entirely different behavior. The boss's added value is similar to a pre-recorded tape. When the boss listens, they both adopt a similar alien dynamical state. A simple kinetic theory captures the principal effects, such as why the way in which the same messages are delivered will matter in future AI-AI interactions. --- ### Strategy-first synthesis planning for complex natural products Authors: Daniel Armstrong, Xuan-Vu Nguyen, Octavian Susanu, Gabriel Gibberd, Théo A. Neukomm, Taddäus Strunden, Dan Forster, Morgane Delattre, Shawn Teh, Clément Rols, John Federice, Hayden Leatherwood et al. Published: 2026-08-07 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2608.07454v1 The total synthesis of a complex molecule is among the most demanding intellectual and experimental feats in chemistry: a chemist must plan many steps ahead for how to assemble simple building blocks into an intricate target, devise backup strategies, and anticipate procedural challenges. It is also a profoundly creative activity. For half a century, efforts to automate the retrosynthetic design of natural products and other complex molecules have drawn on catalogued reactions, and the resulting tools now report near-complete success on benchmarks built from that same source. But these tools were shaped to fit benchmarked chemistry, and they falter on many natural products, the frontier of the field, whose densely functionalized, polycyclic architectures demand precisely the inventive chemistry the record contains least. Whether a machine could reasonably design such syntheses like an expert chemist does has remained unclear. Here, we show that SynthEx, an agentic framework built on large language models, plans routes to complex natural products that lie beyond the reach of conventional design algorithms. SynthEx proposes competing strategies, assembles a sequence of routine and key steps into a cohesive route, and critiques and improves its own design; the chemistry it favours is more convergent than existing tools produce, and spans a region of reaction space that catalogue-based tools cannot match. Most notably, in blinded assessments, expert chemists judged its key steps comparable to those of published human syntheses and engaged with them as genuine synthesis plans, a response algorithmic route prediction has not previously accomplished. We release routes to more than a thousand natural products as SynthAtlas, an open, interactive database, and anticipate it will become a shared resource for a collection of complex target molecules that lack existing literature routes. --- ### SkillProx: Self-Evolving Agent Skills via Proximal Textual Gradient Descent Authors: Mingxuan Zheng, Yujin Zhou, Chuxue Cao, Boqin Yin, Yuyao Zhang, Jiapeng Sun, Shuaishuai Gong, Sirui Han, Yike Guo Published: 2026-08-07 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.07449v1 LLM agents increasingly adapt to recurring tasks by accumulating procedural knowledge in skills. These skills are lightweight, reusable textual artifacts that are loaded into the agent's context without weight updates. Recent methods refine skills through iterative task execution, failure diagnosis, and trajectory-guided text-space updates. However, existing frameworks lack explicit diagnosis--outcome feedback and treat deletion as a generic edit operation rather than a dedicated mechanism for consolidating accumulated knowledge. We introduce SkillProx, a proximal-gradient-inspired forward--backward framework that couples closed-loop diagnostic evolution with utility-aware proximal refinement. Motivated by a composite objective balancing task loss and skill complexity, the forward stage re-executes diagnosis-driven edits on the same task batch, rolls back regressions, and feeds measured outcomes into subsequent diagnoses. The backward stage decomposes the resulting skill into auditable knowledge units, estimates their contributions using a frozen leave-one-out utility audit, and applies validation-gated consolidation, demotion, or removal. Experiments on in-distribution and out-of-distribution benchmarks across multiple backbone LLMs show that SkillProx improves average accuracy by 3.0 percentage points over the strongest gradient-based baseline. Component ablations demonstrate the complementary effects of closed-loop diagnosis and proximal refinement. --- ### Taxonomy-Driven Analysis of Open-Source AI Risk Mitigation Tools Authors: Afreen Alam, Evgenija Popchanovska, Ana Gjorgjevikj, Maryan Rizinski, Lubomir T. Chitkushev, Irena Vodenska, Dimitar Trajanov Published: 2026-08-07 Categories: cs.SE, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2608.07446v1 Rapid adoption of large language models (LLMs) in enterprise settings has introduced operational, security, and governance risks. As generative AI applications move from pilot to production, manual harm identification and mitigation are becoming difficult to scale. Although many tools support model evaluation, adversarial testing, runtime guardrails, and observability, the tooling landscape remains fragmented. Tools are typically designed for specific engineering tasks and described in technical terms that do not align with governance frameworks or risk taxonomies, making it difficult to determine which tools address which risks and where critical gaps remain. This paper proposes a structured protocol to automate AI risk mitigation through a taxonomy-driven analysis of open-source LLM evaluation and security tools. We map the capabilities of 21 prominent open-source tools to the 32 subcategories of the extended MIT AI Risk Mitigation and Response Taxonomy. An LLM-assisted retrieval-augmented generation pipeline analyzes source code and documentation to extract capabilities for each taxonomy category. Reliability assessment yielded moderate agreement (Fleiss' Kappa = 0.509) among three independent reviewers. The analysis reveals a highly skewed landscape in which tools cluster around technical and operational controls, while governance, legal and regulatory, and financial and market controls remain largely unaddressed. This motivates a layered risk-mitigation architecture combining tool-based controls with organizational and regulatory processes. The mapping protocol achieved an F1 score of 75.5% after majority voting. Overall, the study provides a practical mapping between enterprise AI risk categories and open-source mitigation capabilities, identifies where human oversight remains necessary, and presents a taxonomy-driven framework applicable to open-source and proprietary solutions. --- ### RIS-Aided mmWave Localization Under Cross-Link Interference via Beam-Domain ML Fingerprinting Authors: Md Tarek Hassan, Dmitry Zelenchuk, Muhammad Ali Babar Abbasi Published: 2026-08-07 Categories: eess.SP, cs.ET, cs.LG arXiv: https://arxiv.org/abs/2608.07444v1 Accurate user equipment (UE) localization is critical for beam management in reconfigurable intelligent surface (RIS)-assisted millimeter-wave (mmWave) based sixth-generation (6G) networks, especially if the direct base-station-UE links are unavailable. This paper proposes a beam-domain fingerprint framework that maps the received signal-to-noise ratio (SNR) across a small set of predefined RIS reflection states to the UE azimuth angle and range, without requiring channel state information (CSI). Crucially, we extend the framework to a realistic interference-impaired scenario in which a nearby cross-link interferer (CLI) corrupts the clean SNR fingerprint, yielding a signal-to-interference-plus-noise ratio (SINR) fingerprint; an interference-to-noise ratio (INR)-constrained calibration strategy keeps the interference level physically interpretable. Four machine-learning (ML) regressors are evaluated under both conditions. Simulation results at 28 GHz with a 20x20 RIS show that k-nearest neighbors (KNN) achieves the lowest angle MAE of 0.37 degrees and range MAE of 4 cm under clean conditions, rising to 1.4 degrees and 7.6 cm under interference. A key finding is that interference degrades angle estimation substantially more than range estimation across all models, a consequence of the asymmetric encoding of location information in the beam-domain fingerprint. --- ### Blast Radius Authors: MY Pitsane, Hope Mogale Published: 2026-08-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.07440v3 Agentic coding faces growing problems of affordability and wasted tokens. We introduce Blast Radius, a predictive memory management layer that estimates an incoming prompt's reach through coupled context and code channels. NECROPHORESIS enables reversible eviction by archiving dead context verbatim, while Recurring Dead Matter (RDM) identifies and buries repeatedly occurring transcripts. We formulate reversible context eviction over a Polish context space, providing a measurable foundation for retention, recurrence, and eviction while connecting context entropy to resurrection probability. Across seven OpenAI models, Blast Radius reduced token consumption by 17-26%, achieved the lowest overflow rate among tested policies, and remained byte exact reversible. Of 450 buried bodies, 378 were recurring dead matter and zero were recalled. Blast Radius operates beneath HCRC, determining which records to bury and how far an incoming prompt may reach into the codebase. This work contributes to the broader goal of Algosophy: making large language models and agentic coding more reusable and sustainable. --- ### Blast Radius Authors: MY Pitsane, Hope Mogale Published: 2026-08-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.07440v1 Agentic coding faces growing problems of affordability and wasted tokens. We introduce Blast Radius, a predictive memory management layer that estimates an incoming prompt's reach through coupled context and code channels. NECROPHORESIS enables reversible eviction by archiving dead context verbatim, while Recurring Dead Matter (RDM) identifies and buries repeatedly occurring transcripts. We formulate reversible context eviction over a Polish context space, providing a measurable foundation for retention, recurrence, and eviction while connecting context entropy to resurrection probability. Across seven OpenAI models, Blast Radius reduced token consumption by 17-26%, achieved the lowest overflow rate among tested policies, and remained byte exact reversible. Of 450 buried bodies, 378 were recurring dead matter and zero were recalled. Blast Radius operates beneath HCRC, determining which records to bury and how far an incoming prompt may reach into the codebase. This work contributes to the broader goal of Algosophy: making large language models and agentic coding more reusable and sustainable. --- ### An Exploratory Evaluation of LLM-Assisted Rewriting of Moderate-Complexity Financial Sentences for DisCoCat-Based Sentiment Analysis Authors: Brian Llinas, Nikos Chrisochoides Published: 2026-08-07 Categories: cs.CL, quant-ph arXiv: https://arxiv.org/abs/2608.07439v1 Quantum natural language processing (QNLP) provides a grammar-aware framework for text modeling, and Distributional Compositional Categorical (DisCoCat) is one of its theoretically grounded formulations. Prior work on financial sentiment analysis has identified practical limitations of DisCoCat, including parser sensitivity, high simulation cost, and difficulty handling longer sentences. We study an LLM-assisted preprocessing workflow that uses controlled rewriting to compress, simplify, or decompose moderate-complexity financial sentiment sentences into parser-compatible, circuit-efficient variants while preserving sentiment-bearing meaning. We compare prompting strategies, language models, and filtering configurations with the low-complexity-only DisCoCat baseline of Stein et al. At the circuit level, the strongest compression variants reduce average qubit and gate counts by more than 70 percent relative to the raw moderate-complexity subset. Across repeated training runs, GPT-4.1-mini with Prompt B achieves the highest observed mean accuracy, $0.550 \pm 0.035$, compared with $0.521 \pm 0.050$ for the baseline. Larger training splits do not necessarily improve downstream performance; across evaluated configurations, training-split size has a moderately negative association with accuracy (Pearson $r=-0.446$). These results provide exploratory evidence that LLM-assisted rewriting can make some moderate-complexity inputs usable within the evaluated DisCoCat configuration, while highlighting prompt design, filtering, and circuit-aware preprocessing as considerations for more scalable QNLP-based financial sentiment analysis. --- ### PsychoAgent: An Affect-Sensitive Cognitive Architecture for Conflict-Aware Memory in LLM Agents Authors: Mohammad Amanlou, Parham Abed Azad, Farbod Davoodi, Mostafa Masumi, Behnam Bahrak, Abdol-Hossein Vahabie Published: 2026-08-07 Categories: cs.AI, cs.CL, cs.HC arXiv: https://arxiv.org/abs/2608.07438v2 Human-like cognition does not select past experience by topical similarity alone: affective significance and unresolved conflict also shape what becomes accessible. We present PsychoAgent, a cognitive architecture for LLM agents that separates factual and affective memory and integrates both through a conflict-aware executive controller. Affective memories are first filtered by semantic relevance and then re-ranked by salience, preserving topical fit while allowing emotionally important traces to enter the prompt. Across three controlled conflict scenarios, the full architecture retrieved more conflict-critical memories than semantic-affective and single-memory RAG baselines (0.933 vs. 0.500 and 0.667), with a small semantic-similarity cost. Five blinded raters evaluated 27 outputs. After within-rater standardization, the full architecture had the highest overall mean (+0.22 SD), but corrected pairwise differences were not significant. A three-day illustrative trace further shows persistent affect, offline memory recombination, and selective memory reweighting. The findings support affect-sensitive retrieval as an inspectable mechanism for modeling human-like conflict effects in LLM agents. --- ### PsychoAgent: An Affect-Sensitive Cognitive Architecture for Conflict-Aware Memory in LLM Agents Authors: Mohammad Amanlou, Parham Abed Azad, Farbod Davoodi, Mostafa Masumi, Behnam Bahrak, Abdol-Hossein Vahabie Published: 2026-08-07 Categories: cs.AI, cs.CL, cs.HC arXiv: https://arxiv.org/abs/2608.07438v1 Human-like cognition does not select past experience by topical similarity alone: affective significance and unresolved conflict also shape what becomes accessible. We present PsychoAgent, a cognitive architecture for LLM agents that separates factual and affective memory and integrates both through a conflict-aware executive controller. Affective memories are first filtered by semantic relevance and then re-ranked by salience, preserving topical fit while allowing emotionally important traces to enter the prompt. Across three controlled conflict scenarios, the full architecture retrieved more conflict-critical memories than semantic-affective and single-memory RAG baselines (0.933 vs. 0.500 and 0.667), with a small semantic-similarity cost. Five blinded raters evaluated 27 outputs. After within-rater standardization, the full architecture had the highest overall mean (+0.22 SD), but corrected pairwise differences were not significant. A three-day illustrative trace further shows persistent affect, offline memory recombination, and selective memory reweighting. The findings support affect-sensitive retrieval as an inspectable mechanism for modeling human-like conflict effects in LLM agents. --- ### Fisher-R1: Training LLM Agents for Reliable Hypothesis Testing Authors: Jiacheng Miao, Jin Mu, Guanhua Chen, James Zou Published: 2026-08-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.07437v1 Reliable hypothesis testing is the foundation of many empirical scientific claims. Large language model (LLM) agents are increasingly used to automate this process, as they can inspect datasets, generate code, and produce analyses end-to-end. However, we show that they frequently make subtle inferential errors that lead to incorrect conclusions despite correctly executed analyses. Existing benchmarks fail to capture this failure mode, as they rarely assess whether a reported p-value is statistically valid given the assumptions underlying the data. We address this gap by building P-Bench, a benchmark comprising 425 open-ended, realistic hypothesis-testing tasks spanning economics, biology, and medicine. Each task requires an agent to select a statistical method, compute a p-value, and draw a conclusion given only a scientific hypothesis and a dataset. We further introduce Fisher-R1, an open-weight LLM agent trained for rigorous hypothesis testing using synthetic tasks and reinforcement learning. On P-Bench, Fisher-R1-14B substantially improves over its backbone and outperforms strong proprietary and open-source baselines, including GPT-5.4 and DeepSeekV4-Pro, achieving a 21% average relative improvement in single-trial success over DeepSeek-V4-Pro, with gains up to 26% on the most challenging tasks. Our results demonstrate that current LLM agents lack reliable statistical reasoning for hypothesis testing and that reinforcement learning on tasks with verified statistical reward substantially improves reliability. --- ### Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers Authors: Ali Janati, Kaoutar El Maghraoui, Andrei Kanavalau, Anass Belfatmi Published: 2026-08-07 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.07436v1 Under the standard split, Muon gets hidden matrices and AdamW embeddings/output head. Muon groks modular addition faster, but its solutions do not hold. All nine configurations on $(a+b) \bmod 113$ grok and later lose generalization. Across five seeds the selected AdamW reference falls below threshold on four, reaching 27.59%. Instability persists across two moduli, two widths, two training fractions, subtraction, and depth. The failure arises at the representation-readout interface, identified only jointly up to an invertible map unselected by the loss. After solving the training set, the gradient falls to order $10^{-6}$ and the optimizers respond differently: step-size elasticity is -0.03 for Muon versus +1.5 for AdamW, and the Muon group moves 8.0 times faster per parameter. From bit-identical states, freezing either group prevents failure. Freezing embeddings/readout removes it in five runs over 451,400 post-grokking steps and five paired seeds: unfrozen arms record 137-321 sub-threshold evaluations, frozen arms none. Removing Muon's normalization and orthogonalization is no substitute: it collapses representation from 326 effective conjugate pairs to 4, shows no recurrent collapse, and fails terminally. Fourier filtering separates circuit failure from masking. Across 43 checkpoints over five seeds and three regimes, the task-aligned family reaches exactly 100% alone. In circuit failure it no longer solves the task; in masking it remains perfect while the full model reaches 45.85%, giving a positive margin on every example, including errors, but being outvoted by a near-equal adversarial remainder. Rescaling it restores 99.9%; grokking is the same condition resolving upward. The task selects the family, swapping $(k,k)$ for $(k,-k)$ under subtraction. Across an abrupt collapse, standard Fourier support is unchanged and the power-distribution cosine remains 0.9899. --- ### SABRE: Scalable and Automated Benchmarking of VLMs under Stress Authors: Zixuan Lan, Luzhe Sun, Matthew R. Walter, Jiawei Zhou Published: 2026-08-07 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.07435v1 Vision-language models (VLMs) are improving rapidly, but benchmark development lags behind, making weaknesses hard to identify. Building stress tests is costly: samples must satisfy controlled conditions, remain answerable, and challenge current models. We present SABRE, a scalable, automated pipeline that converts a Test Primer (a Markdown Task Design with Data Schema) into structured specifications, generated or edited images, and question-answer pairs. Automated filtering removes candidates solved by a Filtering VLM, while human review verifies candidate validity and supports annotation correction and localized image repair. We instantiate SABRE-Prior to test whether VLMs follow visual evidence instead of relying on world priors -- learned expectations about familiar objects and scenes. Its 600 images and 1,000 questions span Context (unexpected entities in familiar scenes), Texture (counterfactual materials), Attribute (noncanonical component counts), and Language Elicitation (answers suggested by language but unsupported by the image). Across six VLMs, macro-average accuracy ranges from 17.8% to 31.3% (22.6% mean). A real-image Attribute control is comparably difficult for the Filtering VLM. SABRE-Counting and SABRE-Spatial pilots show that the workflow supports other stress-test settings. These results establish SABRE as a reusable framework for constructing and refreshing VLM stress tests rather than a single fixed benchmark. --- ### Conformal Coverage Guarantees for Any Video Temporal Grounder Authors: Aseel Mohamed, Rasul Khanbayov, Erchin Serpedin, Hasan Kurban Published: 2026-08-07 Categories: cs.CV, cs.IR arXiv: https://arxiv.org/abs/2608.07434v1 Event boundaries in continuous video are ambiguous: re-annotate the same query-video pair and independent annotators mark moments that overlap by less than half on a large fraction of samples. The ground truth for video temporal grounding is therefore a distribution over intervals, yet every grounder returns a single interval with no statement of reliability, so at deployment a wrong interval is indistinguishable from a right one. COVER changes the output object: a post-hoc, model-agnostic wrapper that turns any grounder, a trained localizer or a black-box video--language model, into one that emits a temporal region containing the true moment with probability at least $1-α$, by calibrating the quantile of a temporal nonconformity score on held-out labels and widening the base prediction by that amount. The guarantee is finite-sample and distribution-free under exchangeability, and requires neither retraining nor white-box access. We give two score families, a two-sided boundary-widening score for grounders that emit an interval and a super-level-set score for grounders that emit a relevance signal, and develop theory specific to grounding that bounds how large the certified region becomes, when coverage survives conditioning on event length, and how it degrades when moments from one video break exchangeability. Across three benchmarks and five grounders, realized coverage tracks the target, and calibration exposes what point metrics hide. --- ### Wasserstein Policy Gradient for Entropy-Regularized Linear-Quadratic Control Authors: Zhaoyu Zhu, Rui Gao, Shuang Li Published: 2026-08-07 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2608.07433v1 Wasserstein policy gradient (WPG) updates state-conditional action laws by transport in the action space. We study entropy-regularized discounted linear-quadratic (LQ) control. A Bellman verification argument shows that the unrestricted problem has a linear-Gaussian optimal policy, and the discounted-occupancy-weighted statewise Wasserstein gradient is tangent to this policy class. WPG therefore reduces exactly to a finite-dimensional ODE for the feedback gain and action covariance. We prove that this ODE is globally well posed and converges exponentially from every admissible initialization. For each fixed LQ problem, the exponent has a positive limit as the entropy temperature tends to zero and contains no perturbative factor of the form $\exp(-c/τ)$, while retaining the usual dependence on the conditioning of the control problem. --- ### Diffusion LLMs as Targets and Adversaries: Mechanistic Safety Exploits Authors: Elena Dumitrescu, Gert Lek, Lydia Y. Chen, Jérémie Decouchant Published: 2026-08-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.07430v1 Diffusion Large Language Models (DLLMs) replace autoregressive next-token prediction with iterative parallel denoising, yet their internal safety mechanisms remain poorly understood. In this work, we investigate DLLMs both as targets and as adversaries, exposing mechanistic vulnerabilities in diffusion-based alignment. We first show that safety alignment in DLLMs remains sparse and transferable across architectures. DLLMs initialized from autoregressive predecessors inherit the same mechanistic safety footprint as their source models, enabling transfer attacks via direct safety neuron mapping and pruning. Self-pruning increases attack success rates (ASR) from 2.6% to 73.8% on LLaDA and from 1.9% to 86.6% on Dream, while transfer pruning from Qwen2.5 increases ASR from 1.9% to 73.2% on Dream and from 7.0% to 86.3% on Fast-dLLM. Building on these findings, we introduce SN-Guided Diffusion, a fully offline black-box jailbreak framework that steers the diffusion process away from safety-triggering regions using a weighted safety neuron loss, which achieves near-perfect prompt separability (AUROC = 1.0 for benign-vs-jailbreak discrimination). Across multiple open and proprietary targets, our method achieves a transfer ASR of up to 77.1% on Llama-3-8B-Instruct, 86.9% on Qwen2.5-7B-Instruct, and 74.3% against Gemini-2.5-Flash-Lite, while requiring only 20 generation episodes per prompt. Compared to prior jailbreaking frameworks, our method achieves competitive transferability with orders-of-magnitude lower generation cost. Our codebase is available at https://github.com/ellyoana/sn-guided-diffusion. --- ### TEPA: Revoking Stale Memories for Conflict-Robust Language Agents Authors: Yan Zhou, Yue Ouyang, Kaiyang Zheng, Suncheng Xiang Published: 2026-08-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.07429v2 Long-term memory enables language agents to reuse past facts, preferences, and task experience. Persistence also creates a central falsifiability problem: when the world changes, stale memories can remain retrievable and pollute the prompt. We characterize this failure mode as memory pollution: degradation caused by active memories that newer conflicting evidence has superseded. We introduce TEPA, a revocable evidence-memory mechanism that makes validity an explicit state of memory. TEPA represents observations as keyed precedents and revokes active precedents when fresh evidence contradicts them under the same key, allowing retrieval to draw from current evidence while preserving revoked history for audit. Across controlled hidden-regime drift, real file-backed executable drift, and preference-update streams, revocation prevents stale active memory from remaining in the retrieval set after reversal. In controlled drift over 50 seeds, append-only and last-write-wins memory fell below no memory during full reversal (append-only and last-write-wins both 0.210, no memory 0.309, TEPA 0.950), and the same pattern reproduced under real file execution (append-only 0.203, no memory 0.298, TEPA 0.950). On clean MemoryAgentBench SH-6k, TEPA matches a strong last-write-wins cache, confirming that current-key replacement is the decisive operation for single-hop fact consolidation. Boundary tests on multi-hop and very long-context MemoryAgentBench settings expose retrieval-chain and context-selection bottlenecks beyond fact-level validity tracking. Together, these results establish lifecycle revocation as a core memory operation for agents that must falsify, audit, and later re-promote evolving knowledge. --- ### TEPA: Revoking Stale Memories for Conflict-Robust Language Agents Authors: Yan Zhou, Yue Ouyang, Kaiyang Zheng, Suncheng Xiang Published: 2026-08-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.07429v1 Long-term memory enables language agents to reuse past facts, preferences, and task experience. Persistence also creates a central falsifiability problem: when the world changes, stale memories can remain retrievable and pollute the prompt. We characterize this failure mode as memory pollution: degradation caused by active memories that newer conflicting evidence has superseded. We introduce TEPA, a revocable evidence-memory mechanism that makes validity an explicit state of memory. TEPA represents observations as keyed precedents and revokes active precedents when fresh evidence contradicts them under the same key, allowing retrieval to draw from current evidence while preserving revoked history for audit. Across controlled hidden-regime drift, real file-backed executable drift, and preference-update streams, revocation prevents stale active memory from remaining in the retrieval set after reversal. In controlled drift over 50 seeds, append-only and last-write-wins memory fell below no memory during full reversal (append-only and last-write-wins both 0.210, no memory 0.309, TEPA 0.950), and the same pattern reproduced under real file execution (append-only 0.203, no memory 0.298, TEPA 0.950). On clean MemoryAgentBench SH-6k, TEPA matches a strong last-write-wins cache, confirming that current-key replacement is the decisive operation for single-hop fact consolidation. Boundary tests on multi-hop and very long-context MemoryAgentBench settings expose retrieval-chain and context-selection bottlenecks beyond fact-level validity tracking. Together, these results establish lifecycle revocation as a core memory operation for agents that must falsify, audit, and later re-promote evolving knowledge. --- ### A Picture is Worth a Thousand Tokens: How Vision Language Models Cut AI Energy Costs While Improving Accuracy Authors: Bhavika Jalli, Nikhil Korati Prasanna, Jayanta Choudhury Published: 2026-08-07 Categories: cs.AI, cs.PF arXiv: https://arxiv.org/abs/2608.07427v1 LLM inference accounts for over 90% of AI operational energy, scaling directly with input token count---a critical inefficiency for telecom network analytics and numerical time-series data analysis (NTSDA), where raw multivariate KPI windows from 4G/5G cell sites expand into thousands of floating-point tokens. Vision-Language Models (VLMs) eliminate this mismatch by encoding time-series as 2D plots, achieving 3.6-10.4x input token reduction across Llama-3.2-90B, Qwen2.5-VL-72B, and Pixtral-12B architectures. This translates to 1.8-2.5x measured inference energy reduction, saving approximately 7.2 MJ/day at telecom edge deployments and CloudRAN that monitor 200 cells per 15-minute interval. Critically, efficiency gains do not sacrifice accuracy: a fine-tuned Llama-3.2-90B-Vision VLM achieves 220.7% higher precision than its text-only counterpart and outperforms LSTM and ARIMA baselines by over 144% on telecom anomaly detection. On public benchmarks, Pixtral-12B achieves a 20.6x improvement in J/F1 score at mean F1 = 0.82. At 24 KPIs, text representations exceed the 128K context window of most production LLMs, rendering text-only processing infeasible without truncation, while visual representations remain within standard limits. These results establish VLMs as an energy-efficient and accuracy-superior modality for numerical time-series workloads, providing empirical grounding for AI inference systems that treat energy consumption as a first-class engineering constraint. --- ### CoBa: Cost-Effective Test-Time Scaling via Compute-Balanced Routing Authors: Yan Zhou, Yue Ouyang, Kaiyang Zheng, Suncheng Xiang Published: 2026-08-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.07424v2 Test-time scaling is often implemented by spending more compute along one axis: sampling more solutions, extending a chain of thought, or applying a stronger evaluator. Under a fixed inference budget, these choices compete. This paper formulates test-time reasoning as a compute-allocation problem in which a system must decide whether the next unit of compute should be spent on generation, verification, or stopping. We introduce CoBa, a compute-balanced routing policy that first obtains a small set of candidates, applies cheap verification broadly, and routes uncertain or high-value candidates to stronger verification. On 3,129 example-generator evaluations spanning MATH-500, AIME 2024/2025, AMC 2023, and procedural symbolic reasoning, CoBa-Routed-Strong reaches 85.13% macro accuracy, statistically matching a self-evaluation weighted-voting proxy at 85.20% while using 49.1% fewer parameter-weighted tokens. It also matches best-of-16 majority voting within 0.01 macro-accuracy points while using 58.9% fewer parameter-weighted tokens; paired tests retain a small best-of-16 edge at substantially higher cost. Paired bootstrap tests show significant gains over single-sample decoding, while the remaining gap to the pool oracle exposes headroom for sharper routing. For local reasoning systems, test-time scaling becomes a question of where the next computation is most valuable. --- ### CoBa: Cost-Effective Test-Time Scaling via Compute-Balanced Routing Authors: Yan Zhou, Yue Ouyang, Kaiyang Zheng, Suncheng Xiang Published: 2026-08-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.07424v1 Test-time scaling is often implemented by spending more compute along one axis: sampling more solutions, extending a chain of thought, or applying a stronger evaluator. Under a fixed inference budget, these choices compete. This paper formulates test-time reasoning as a compute-allocation problem in which a system must decide whether the next unit of compute should be spent on generation, verification, or stopping. We introduce CoBa, a compute-balanced routing policy that first obtains a small set of candidates, applies cheap verification broadly, and routes uncertain or high-value candidates to stronger verification. On 3,129 example-generator evaluations spanning MATH-500, AIME 2024/2025, AMC 2023, and procedural symbolic reasoning, CoBa-Routed-Strong reaches 85.13% macro accuracy, statistically matching a self-evaluation weighted-voting proxy at 85.20% while using 49.1% fewer parameter-weighted tokens. It also matches best-of-16 majority voting within 0.01 macro-accuracy points while using 58.9% fewer parameter-weighted tokens; paired tests retain a small best-of-16 edge at substantially higher cost. Paired bootstrap tests show significant gains over single-sample decoding, while the remaining gap to the pool oracle exposes headroom for sharper routing. For local reasoning systems, test-time scaling becomes a question of where the next computation is most valuable. --- ### Cloud-Boosted Low-Compute Multi-Channel Speech Enhancement Authors: Xulin Fan, Juan Azcarreta, Ashutosh Pandey, Jesus Alvarez, Ke Tan, Jacob Donley, Ritwik Giri, Buye Xu Published: 2026-08-07 Categories: cs.SD, cs.LG, eess.AS arXiv: https://arxiv.org/abs/2608.07423v1 Low-latency, low-compute speech enhancement is essential for wearable devices with real-time communication requirements, but strict computational constraints significantly limit on-device performance. Knowledge Boosting has been proposed as an effective approach to improve edge model performance by leveraging a more capable server-side model, but performance gains for speech enhancement have been limited. We propose a collaborative framework incorporating three techniques: (1) delayed server output as additional input, (2) layerwise feature boosting that transfers intermediate server representations to guide edge inference, and (3) collaborative multichannel Wiener filtering, which fuses weighted covariance matrices estimated from both server and edge models for improved beamforming. Experimental results demonstrate that the proposed collaborative framework significantly outperforms the edge-only baseline with minimal additional computational overhead. --- ### Beyond Myopic World Models: Long-Horizon End-to-End Training for Direct Future Prediction Authors: Xinyi Li, Zaishuo Xia, Chenjie Hao, Yubei Chen Published: 2026-08-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.07420v1 World models are expected to support imagination over extended temporal horizons, yet most are still trained through local few-step prediction objectives and deployed by recursively rolling out their own predictions. This creates a fundamental mismatch: few-step losses optimize local transition fidelity, while long-horizon prediction depends on how errors and gradients propagate through the entire trajectory. As a result, transitions with different downstream influence on the endpoint are treated uniformly during training, and small local errors are amplified through recursive inference. We argue that long-horizon accuracy is better achieved by optimizing directly, through an end-to-end endpoint prediction objective. To instantiate this paradigm, we introduce the Direct Prediction World Model (DPWM), a non-recursive architecture that compresses an action sequence of arbitrary length into a single embedding and predicts the endpoint observation in a single forward pass. This design avoids recurrent rollout in both prediction and gradient propagation, making long-horizon end-to-end training practical at horizons where unrolled autoregressive training becomes unstable. Empirically, DPWM substantially improves long-horizon endpoint prediction over recursive world-model baselines on continuous-control and pixel-based benchmarks, with larger gains as the prediction horizon increases. We further show that recurrent baselines benefit similarly when retrained with the same long-horizon endpoint objective, supporting our central claim that the training objective, rather than the particular backbone choice, is the main driver of long-horizon prediction accuracy. Our results suggest that world models can benefit from being trained and evaluated at the temporal scales where they are ultimately used, shifting the focus from local transition modeling toward long-horizon predictive accuracy. --- ### Beyond Post-Hoc Temperature Scaling: Bilevel Optimization for LLM Calibration Authors: Ruochen Jin, Zhanliang Wang, Zongyu Dai, Jiancong Xiao, Bojian Hou Published: 2026-08-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.07419v1 Preference alignment often makes large language models (LLMs) overconfident and poorly calibrated. Traditional post-hoc temperature scaling is inherently domain-dependent: a temperature fitted on one domain does not generalize across domains. This motivates us to modify model parameters during training to improve calibration. We propose maximizing the entropy of predictive distributions as the calibration objective, which directly targets overconfidence by discouraging overly concentrated predictions. Inspired by temperature scaling, we realize this through a bilevel optimization formulation, where the lower level trains the model under a parametric loss and the upper level selects loss hyperparameters to maximize entropy. To make the framework practical at LLM scale, we adopt an efficient first-order approximation that avoids explicit second-order computation. Across both multiple-choice and open-ended generative question answering, experiments demonstrate that our method yields well-calibrated LLMs with particular advantages in out-of-domain generalization. --- ### ResidencyRL: Reinforcement Learning in Simulated Clinical Environments Authors: Valentin Liévin, Samuel Schmidgall, Tim Strother, Alex Bijamov, Akshay Goel, Anil Palepu, Chunjong Park, Vahid Balazadeh, Min Woo Sun, Marius Guerard, Justin Chen, Dave Steiner et al. Published: 2026-08-07 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.07418v1 In medical education, physicians convert academic knowledge into clinical expertise through residency: years of training across thousands of encounters, with diverse sources of feedback and progressively greater autonomy. Much of clinical reasoning relies on the patient encounter, a dialogue in which a clinician elicits history, refines diagnostic hypotheses, and decides management under uncertainty. While large language models (LLMs) excel on static medical benchmarks, methods to optimize the full sequence of clinical decisions remain underdeveloped. We present ResidencyRL, a reinforcement learning (RL) method for training clinical artificial intelligence (AI) agents through simulated multi-turn clinical encounters (up to 60 dialogue turns and 8 tool calls per trajectory). ResidencyRL pairs the policy agent with LLM simulators capable of complex, adversarial behaviors, training against a structured reward aligned to diagnostic accuracy, management quality, communication, documentation, and safety. On held-out evaluations, the ResidencyRL agent improves diagnostic accuracy by 7.0% under adversarial conditions (88.0% vs. 81.0%) and reduces missed red flag rates by 31%, demonstrating rigorous mitigation of premature closure. Blinded expert clinicians validated these gains, preferring the trained agent in 87.6% of side-by-side comparisons. The procedural competencies transfer to unseen benchmarks: the agent outperforms the base model across all six clinical axes of the AMIE multi-visit benchmark, and shows consistent directional improvements on AgentClinic and CRAFT-MD. Our findings demonstrate that sequential clinical decision-making can be effectively learned through multi-turn RL in simulation, yielding robust, generalizable capabilities, paving the way towards clinical mastery. Prospective validation with real-world workflows remains necessary to establish clinical utility. --- ### I Seek You in Videos: Identity-Conditioned Queries for Person-Centric Video Reasoning Authors: Shibo Gao, Chongxiao Wang, Chenglong Huang, Jie Ma, Haolin Shi, Fei Ding, Jing Li, Qiang Lyu, Yangyang Liu, Yang Liu, Jun Liu, Linlin Huang et al. Published: 2026-08-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.07417v1 Real-world video reasoning often involves multimodal, multi-source inputs, whereas existing video reasoning tasks typically assume a simplified video-text setting, limiting identity matching and person-centric reasoning. To bridge this gap, we introduce the Identity-conditioned Queries (ICQ) task, in which models are required to jointly associate and interpret an input video and a reference image of a person, and leverage this conditioning to address identity grounding, behavior understanding, and temporal reasoning, among other challenges. Building on ICQ, we present ISYV (I Seek You in Videos), a systematic solution comprising three components: (1) ISYV-Bench, a challenging evaluation benchmark with 1,377 real-world complex videos and 1,377 question-answer pairs, organized into six difficulty levels spanning capabilities from identity recognition to causal reasoning; (2) ISYV-75K, a large-scale training set of 75K high-quality samples constructed via automated annotation, multi-stage verification, and manual review; and (3) ISYV-Framework, containing an ICQ-oriented model and training strategy for learning to exploit informative video shots without additional shot-level annotations. Extensive experiments show that both mainstream closed-source and open-source MLLMs struggle on ISYV-Bench, especially in cross-domain identity matching and long-horizon tracking. ISYV-Model outperforms strong baselines and in some aspects approaches closed-source performance. Overall, ISYV provides a unified task definition, scalable datasets/benchmarks, and modeling insights for person-centric video reasoning. --- ### GeoBenchLLM: A Comprehensive Benchmark for Evaluating LLMs on Geo-Related Tasks Authors: Rodrigo Ferreira Rodrigues, Karim Radouane, Jose G Moreno, Lynda Tamine Published: 2026-08-07 Categories: cs.AI, cs.CL, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2608.07411v1 In the context of geodata, existing Large Language Models have often been studied in a homogeneous setting, which has considerably limited insights into their generalization capabilities. In this paper, we present \benchName, a comprehensive benchmark for probing LLMs on geo-related tasks. We leverage a careful selection of twelve publicly available datasets from diverse geo-related tasks and domains, and evaluate a set of LLMs on geo-spatial and temporal understanding using our benchmark. Our results show that reasoning and size have a strong impact on overall performance. GeoBenchLLM is publicly available at https://github.com/Rfr2003/GeoBenchLLM. --- ### UniJEPA: A Unified Joint-Embedding Predictive Architecture for Task-Agnostic Visual World Modeling Authors: An Lanji, Dawei Liu, Jin Li, Haoran Xu, Mei Chen, Yu Tian Published: 2026-08-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.07409v1 Joint-Embedding Predictive Architectures (JEPAs) have emerged as a principled framework for self-supervised learning of world models in compact latent spaces, yet existing methods are fragmented: some predict masked parts of a single image in latent space (I-JEPA), others learn to predict global photometric transformations (Image World Models), while video-scale JEPAs predict future temporal states and are post-trained for action-conditioned planning (V-JEPA~2, DINO-World, DINO-WM). These objectives are treated as distinct recipes with separate encoders, predictors, and anti-collapse regularizers, hindering a single model from unifying image-level and video-level world modeling. We present UniJEPA, a unified JEPA that jointly learns photometric prediction (image-level transformations) and temporal prediction (video-level next-state dynamics) in one shared latent space. A single end-to-end objective, composed of a next-embedding prediction loss and a Gaussian regularizer, yields a provably anti-collapse encoder-predictor pair trainable from raw pixels without EMA, stop-gradient, or pre-trained encoders. We show that the same latent space supports controllable abstraction: photometric prediction learns invariant structure while temporal prediction learns equivariant dynamics. After action-conditioned post-training on offline trajectories, UniJEPA enables zero-shot planning by treating goal features as prediction targets. On image, video, and control benchmarks, UniJEPA matches or surpasses task-specific JEPAs while requiring a single loss hyperparameter, and plans up to tens of times faster than generative world models at comparable accuracy. --- ### Addressable Memory for Video World Models Authors: Xindi Wu, Sven Elflein, James Lucas, Olga Russakovsky, Laura Leal-Taixé, Despoina Paschalidou, Jonathan Lorraine, Aljoša Ošep Published: 2026-08-07 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.07408v1 We study visual persistence in interactive video world models. These models rely on a Key-Value (KV) cache as a growing visual memory to carry forward previously generated frames. However, we find that models can no longer reliably address stored content once rollouts extend beyond the training horizon, because temporal Rotary Positional Embeddings (RoPE) offsets then fall outside the range seen during training and the model struggles to retrieve the relevant visual information through attention. Moreover, naively compressing the cache in the RoPE-rotated space corrupts memory by averaging together incompatible positional phases. To address this, we propose WorldTrace, a training-free memory framework for long-horizon visual persistence. WorldTrace keeps compressed memory addressable by assigning each summary slot a distinct, in-distribution virtual position. Within this addressable cache, we study two memory compression approaches: WorldTrace-Field compresses history for temporal coherence, while WorldTrace-Landmark stores verbatim scene traces at detected transitions for episodic recall. We further introduce LoopBench, a benchmark evaluating whether a compressed cache can reconstruct a previously visited scene after a long detour. WorldTrace-Field improves temporal consistency by +15.5%, and WorldTrace-Landmark improves episodic recall by +19.5% on LoopBench, extending visually persistent generation without retraining. --- ### GeoDistill-Refine: Silhouette-First Geometry Distillation for Annotation-Free Spacecraft Segmentation Authors: Yonglong Zhang, Zongwu Xie, Yang Liu Published: 2026-08-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.07405v1 Foundation segmentation models can provide supervision for spacecraft imagery without manual training masks, but their predictions vary with textual prompts and may contain geometric errors that are amplified during distillation. This paper presents GeoDistill-Refine, a two-stage framework that transfers offline SAM 3 pseudo-masks to a compact segmentation network. Six fixed prompts are fused by an unweighted 50% vote to stabilize the teacher output. The student first learns the foreground silhouette and is then refined with signed-distance-field, skeleton, and area objectives derived from the pseudo-mask. A sample-level gate, computed from prompt agreement, the valid-prompt ratio, and pseudo-mask area plausibility, reduces the influence of unreliable pseudo-geometry. On the SpaceSense-Bench HJM lockbox set, GeoDistill-Refine improves Image IoU and Boundary F1 by 0.0456 and 0.1380, respectively, over a plain pseudo-label student. External evaluations on the SPEED+ Lightbox and Sunlamp domains and on TANGO show competitive regional overlap together with gains in boundary quality or foreground precision. The deployed TinyUNet contains 0.263 M parameters and requires approximately 1.1 ms per image on an RTX 4090; SAM 3 pseudo-mask construction and the auxiliary geometry branches are used only during training. --- ### DynaCrys: Crystal Generation with Dynamic Space-Group Diffusion Authors: Zhuotao Jin, Xiaoyun Wang, Nicholas Brawand, Roman Zubatyuk, Atul Thakur, Eric Qu, Boris Kozinsky, Justin Smith Published: 2026-08-07 Categories: cond-mat.mtrl-sci, cs.LG arXiv: https://arxiv.org/abs/2608.07401v1 The search for new crystalline materials spans an enormous compositional and structural space. Generating candidates in this space requires jointly modeling discrete crystallographic symmetry, elemental composition, and continuous geometry. We introduce DynaCrys, a generative model for crystals in which the space group co-evolves with Wyckoff occupations and elements through a coupled symbolic diffusion process. The structured space-group transitions follow crystallographic group-subgroup relations. As the space group changes, a shared, pretrained symmetry codebook provides both the legality-constrained stochastic decoder and the symmetry-constrained crystal-geometry model with a common representation of the corresponding Wyckoff vocabulary. Across large-scale evaluations using two independent relaxation-and-evaluation engines, DynaCrys achieves best-in-class performance in symmetry-aware discovery of stable, unique, and novel crystals, both overall and under the additional requirement of nontrivial post-relaxation symmetry. It also enables fast sampling while generating structures with consistently low relaxation-induced structural displacements. --- ### FinRank: An Evidence-Grounded Benchmark for Financial Question Answering and Retrieval over SEC Filings Authors: Sasan Mansouri, Daniel Saad, Mark Wahrenburg, Manu Weissel, Fabian Woebbeking Published: 2026-08-07 Categories: cs.AI, cs.DB, econ.GN, q-fin.GN arXiv: https://arxiv.org/abs/2608.07400v1 Financial question answering is typically evaluated by answer correctness, yet in SEC filings a plausible and even numerically correct answer can be grounded in the wrong evidence. Similar facts and disclosures recur across sections of a filing, across reporting periods of the same firm, and across comparable firms. FinRank targets this provenance-sensitive retrieval problem by requiring systems to identify evidence for the intended entity, reporting period, and disclosure context. The benchmark contains 1185 manually authored question-answer records over the 10-K and 10-Q filings of 22 companies. Each record includes a reference answer, gold supporting passages, and hand-curated hard negatives drawn from confusable passages within filings, across reporting periods, and across comparable firms. FinRank evaluates passage retrieval, reranking, and hard-negative discrimination as separately measured tasks. Baseline results demonstrate the difficulty of this setting: among the evaluated systems, even a 7B instruction-tuned embedder reaches only 44.8% Recall@10 on the pooled evidence corpus; sub-billion-parameter encoders gain at most 3.5 points over BM25, a finance-adapted embedder trails BM25 by 9.7 points, and pairwise accuracy falls by 13.0-20.5 percentage points when random negatives are replaced with the curated hard negatives. FinRank provides an evidence-first benchmark for developing financial question answering systems that are not only accurate but also grounded in the correct disclosure. ---