Artificial Intelligence
AI Discovery in Combinatorics: From Problems to Solutions and Back to Bigger Problems
Eugenio Cainelli, Lorenzo Luccioli, Alessandro Iraci et al. (+1 more)
We introduce $qt$Bench, a
benchmark of 29 open problems in algebraic combinatorics. These problems ask for a simple combinatorial
algorithm that explains given
polynomial coefficients or identities. To help AI
agents search for such
algorithms, we provide a scaffold for playing with combinatorial objects, countering cheating attempts, and testing candidate solutions. To explore how far frontier AI systems can go on these problems, we collaborated with OpenAI, whose researchers obtained proposed solutions to several of them. This highlights bigger meta-problems: is AI discovery at scale ethical? How should these results be released? How should proof digestion be organized? We discuss these questions and give our views.
Read the full abstract ▾
All authors Eugenio Cainelli, Lorenzo Luccioli, Alessandro Iraci, Giovanni Paolini
Artificial Intelligence
Making Language the Low-Rate Code of Vision: Successive Refinement from Words to Pixels
Ruilin Gong and Hao Gong
An ordered visual code lets a short prefix stand in for an image, and the training loss decides what that prefix contains. Under pixel reconstruction the first bits go to the directions of highest variance, and we prove that a caption can then be independent of the entire first half of a code that is rate-optimal for pixels at every length. In the rate-distortion sense a caption is therefore not the low-rate code of its image, unless the code is built to make it one. We study that construction and what it costs. We cast captioning and text-to-image generation as successive refinement under a distortion measure that changes along the code, from caption log-loss in the early stages to pixel distortion in the last, so that each stage is compared with its own optimum. Putting words first then costs nothing among the caption stages exactly when the captions form a summarization chain, and it costs the pixels at most the caption uncertainty left in a pixel-optimal reconstruction, which is large for short prefixes and small at full length. We build RUNG, an ordered code whose prefixes are supervised by a summarization ladder of captions and whose full length reconstructs the image; generation extends the code past the
prompt and captioning truncates it. With data and capacity held fixed, ordering by
language instead of reconstruction raises prefix-caption information 2.9 times and GenEval from 0.76 to 0.83, at a measured cost of 2.8 dB PSNR at a quarter of the code and 0.1 dB at full length. RUNG-XL (3.4B) reaches 0.88 GenEval and 87.6 DPG-Bench in 32 network evaluations and 0.91 GenEval when errors are redrawn at the rung where they appear; its coarse and fine captions agree 94.1% of the time, and it edits images without inversion.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Heuristics are Not Enough: Calibrated and Corrected Caching for Video Diffusion Acceleration
Jiyue Jiang, Zhiyu Huo, Yuhan Chen et al. (+3 more)
Feature caching has become a mainstream training-free strategy for accelerating
video diffusion models by reusing intermediate outputs across denoising steps. However, existing adaptive methods rely on heuristic difference measures misaligned with actual generation quality, employ a single global threshold that ignores heterogeneous phase dynamics, and never validate their budget estimates against true approximation error, allowing systematic bias to propagate uncorrected. We propose AlignCache, a closed-loop caching framework that directly aligns scheduling decisions with their true influence on the final generated
video through three tightly coupled components: (1) phase-adaptive budget routing that partitions the denoising trajectory into structurally distinct phases, each governed by an independent threshold and a staleness-aware guard; (2) closed-loop threshold calibration that exploits counterfactual error measurement at the classifier-free guided output level to adjust decision boundaries online via an EMA feedback loop; and (3) momentum-augmented draft synthesis combining direction-magnitude gated residual extrapolation with anchor-guided unconditional correction. By transforming scheduling from a static risk accumulator into a feedback-driven, self-correcting controller, AlignCache consistently achieves superior acceleration-quality trade-offs across state-of-the-art
video generation models. Our code is available at https://github.com/jiangjyjy/AlignCache.
Read the full abstract ▾
All authors Jiyue Jiang, Zhiyu Huo, Yuhan Chen, Yanruisheng Shao, Gong Zhang, Lei Deng
Artificial Intelligence
Overtaught, Underlearned: Learner-Centered Distillation from Multi-Agent Discussion
Mengtao Zhou, Jianxiao Wang, Xiupeng Chen et al. (+2 more)
Multi-
agent discussion produces
reasoning collaboratively, while deployment still relies on a smaller student that must answer alone. Full-graph
distillation transfers such discussions by treating each correct solution as a separate training target, but what teachers provide need not match what the student learns. This mismatch appears in two ways: several correct solutions may amount to the same lesson in the student's representation (over-teaching), while some training questions remain missed after learning (under-learning). We quantify both with rates that are high on discussion graphs. To address them, we introduce FAR (Fold–Attempt–Revisit), a learner-centered
distillation procedure that organizes supervision around the student's own state. Before training, FAR folds solutions within each discussion state into representative lessons. After training, the student's own attempts identify missed questions, while poorly represented clusters indicate where folding may have lost useful variation; FAR then writes targeted lessons from retained discussion contexts. Across two students and four
reasoning tasks, FAR outperforms full-graph
distillation with far fewer training targets and lower under-learning. Further analyses examine the behavior of FAR and the sources of its gains. Overall, the results show that organizing discussion supervision around the student can make
distillation both more effective and more efficient.
Read the full abstract ▾
All authors Mengtao Zhou, Jianxiao Wang, Xiupeng Chen, Cailiang Liu, Jie Song
Artificial Intelligence · Cross-listed from cs.CL
PatTransBench: an ipc-stratified, multi-dimensional benchmark for patent machine translation evaluation
Xiaowei Su and Xusen Cheng
We present PatTransBench, a 12,000-item Chinese-English/Japanese/Korean patent machine translation (PatMT)
benchmark with a four-dimensional evaluation protocol. The
benchmark comprises 6,000 short-text (sentence/claim) and 6,000 long-text (paragraph) pairs, evenly split across three
language pairs and both translation directions, built via IPC-section-stratified sampling and dualthreshold quality gating from upstream patent-family parallel corpora. The evaluation protocol spans literal n-gram overlap (BLEU, ROUGE-L, chrF), cross-lingual semantic textual similarity (CLSTS), 38-probe-
language consistency testing, and serving performance under concurrency. A case study on PatMT2-7B and its fp8/AWQ4/AutoRound-4bit variants reveals direction-dependent quantization effects masked by aggregate scores and non-monotonic
language-failure patterns across quantization schemes that are invisible to single-metric evaluation. We plan to release the
benchmark, protocol, and case-study results upon publication to support reproducible PatMT evaluation.
Read the full abstract ▾
Artificial Intelligence
Does the Explanation Drift Before the Guarantee? Label-Free Early Warning on Evolving Graphs
Tomasz Szandała and Damian Raczkowski
Deployed models can fail silently as the world they describe evolves. Attribution drift has served as an early warning in tabular data; we ask whether, in graph streams, a model's own explanations can forewarn the loss of nominal conformal coverage. Doing so requires repairing the naive drift statistic twice. A vanishing edge loses mask mass regardless of whether the model relied on it, so we condition the importance on edge presence. Evolving graphs also break edge identity: a relabelling that changes nothing shifts the identity-based statistic by 0.69 on synthetic graphs and 0.83 on real ego-networks, whereas aggregating over structural roles brings both to 0.0 and stays well-defined when the support changes. We test six pre-registered regimes on thirty seeds each. A two-channel monitor, tracking conditional mask mass and its distribution over roles, precedes coverage collapse by 8 to 14.5 steps across four gradual regimes (node addition, removal, replacement, and edge thinning), all surviving Holm correction. A sudden knockout yields the expected zero lead, and a harmless change triggers no alarm. Leads track the length of the transitional phase (Spearman 0.79 over 150 runs). On real transaction ego-networks, the untuned mass channel forewarns staged drift by 27 steps and is the only channel, attributional or structural, that never alarms on a stationary stream. The main limitation is that the mass channel is blind to
covariate drift, which breaks the guarantee in every run; the distributional channel detects it and also rescues the rewiring regime, so we report the two channels separately rather than as a union.
Read the full abstract ▾
Artificial Intelligence
EAU: Environment-Agent-User Co-evolution for Training User-Centric Agents
Min Cai, Dan Zhang, Gao Xing et al. (+3 more)
Training LLM
agents to interact with users over multiple turns is challenging because the learning signal depends not only on the
agent, but also on the user simulator and environment, which jointly shape the
agent's experience. Simulated users can be
stochastic or inconsistent, while environments may contain unreliable tools, incomplete state coverage, and incorrect verifiers. Prior work mainly addresses the resulting instability through reward shaping or denser supervision, while treating these components as fixed. We instead introduce EAU, a meta-
agent framework for environment–
agent–user co-
evolution. During training, EAU monitors trajectories, tool traces, rewards, and training statistics; diagnoses failures and uninformative interactions; and proposes targeted modifications to the user simulator, environment, reward design, and RL configuration. Validated changes are hot-swapped into the ongoing run, allowing the training setup to evolve together with the policy. These adaptations also persist across runs, so later training can build on previously discovered improvements rather than restarting from a fixed setup. We enable this process through an editable symbolic representation of user and environment dynamics, while the
agent remains a neural LLM optimized with RL. Across three interactive-
agent benchmarks and two backbone models, EAU consistently outperforms prior RL methods, improving the overall score over the strongest baseline by 14.7–15.0% and increasing successful task completion on ColBench by up to 36.7%, showing that co-evolving the training system with the policy can substantially improve multi-turn RL.
Read the full abstract ▾
All authors Min Cai, Dan Zhang, Gao Xing, Libin Ma, Zhaohui Xu, Xi Ye
Artificial Intelligence
Boosting the Learning for Ranking Patterns
Nassim Belmecheri, Noureddine Aribi, Nadjib Lazaar et al. (+2 more)
Pattern mining is a valuable tool for exploratory data analysis, but identifying relevant patterns for a specific user is challenging. Various interestingness mea- sures have been developed to evaluate patterns, but they may not efficiently estimate user-specific functions. Learning user-specific functions by ranking patterns has been proposed, but this requires significant time and training samples. In this paper, we present a solution that formulates the problem of learning pattern ranking functions as a multicriteria decision making problem. Our approach uses Analytic Hierarchy Process (AHP) to elicit weights for different interestingness measures based on user preference. We also propose an active learning mode with a sensitivity-based heuristic to minimize user ranking queries while still providing high-quality results. Experiments show that our approach significantly reduces running time and returns precise pattern ranking while being robust to user error, compared to state-of-the-art approaches.
Read the full abstract ▾
All authors Nassim Belmecheri, Noureddine Aribi, Nadjib Lazaar, Yahia Lebbah, Samir Loudni
Artificial Intelligence · Cross-listed from cs.LG
pi-Net: Empirical Latent Representations for Differentiable Physics Heads in Data-Scarce Systems
Akshay Dhalpe, Arnab Chattopadhyay, Shahriar Bakrani Balani et al. (+2 more)
Developing reliable predictive models for multi-physics systems often forces a compromise between computationally demanding physical simulators and data-hungry, opaque machine learning (ML)
algorithms. While incorporating dimensional analysis into directed computation graphs offers a structurally sound alternative to explicitly solving partial differential equations (PDEs), such formulations typically yield underdetermined systems that act as imperfect simulators. We introduce pi-Net, a physics-informed latent variable model that resolves these imperfect simulators. The hybrid pi-Net architecture consists of an encoder that maps inputs into physically normalized latent space, which are then decoded into final predictions by a differentiable physics head. Evaluated on a real-world, data-scarce Gas Metal Arc Welding (GMAW) case study, the framework achieves an R2 of 0.864 with only 60 experimental samples. The results demonstrate that pi-Net significantly outperforms purely data-driven baselines in data-scarce regimes while providing causal, process-level explainability.
Read the full abstract ▾
All authors Akshay Dhalpe, Arnab Chattopadhyay, Shahriar Bakrani Balani, Eric Cortanéa, Sasu Tarkoma
Artificial Intelligence · Cross-listed from cs.SI
From Caricature to Collective Artifact: How Persona Construction Drives Polarization in Generative Social Simulations
Dimitris Michailidis, Petter Törnberg and Fernando P. Santos
Generative Social Simulation (GSS) leverages Large
Language Models (LLMs) to create sophisticated personas that define
agents with demographics, emotions, and political opinions. While prior work shows that personas compress outputs into stereotypical caricatures, there is no comprehensive study of how these caricatures evolve into collective artifacts when they interact. Using a Twitter-like GSS platform with personas derived from the American National Elections Study (ANES), we ablate three layers of partisan identity: affective polarization markers, party identification, and vote choice, while retaining demographics, ideological positioning and important issues. We find that collective outcomes depend heavily on how survey responses are translated into personas. Removing a few explicitly partisan statements moves the network from near-complete segregation to cross-party ties approaching those of real Twitter networks. We argue that matching one outcome is not evidence for behavioral validity and point to salience as a possible explanation. Surveys ask for a position on every question regardless of its importance to the respondent, and persona construction turns each answer into a direct behavioral instruction. We conclude with a checklist for more comprehensive evaluation of personas in future works.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Drafting Agents, Not Just Tokens: Speculative Recursive Self-Improvement for Agentic Systems
Xin Xu, Ke Cheng, Hao Wang et al. (+11 more)
Improving an
agent through successive revisions requires balancing exploration and evaluation under a limited budget. A narrow search can miss useful sequences of edits, while fully evaluating every intermediate version can exhaust the budget before those sequences yield a verified improvement. We introduce Speculative Recursive Self-Improvement (SpecRSI), which drafts executable successor
agents before their predecessors are fully evaluated, while requiring complete verification before adoption. Verification-Aware Tree Search (VATS) allocates the budget between further edits and outstanding checks using the predicted verified return of a continuation. Group Verification Optimization (GVO) learns the improver from completed searches while keeping the real evaluator fixed. In the main scientific comparison, terminal gains exceed Janus by 33.3%–40.0%. Additional evaluations show that SpecRSI outperforms Janus in all 50 scientific backbone–task pairs and exceeds MetaRSI-v1 by 1.85%–2.38% in macro-average system score across twenty backbones. Coding-validation success reaches 69.4% versus HGM's 64.3% at a 20.8% lower target-cost index.
Read the full abstract ▾
All authors Xin Xu, Ke Cheng, Hao Wang, Yangru Huang, Yanghao Xiao, Zhichao Chen, Zhisheng Zhong, Xun Liu, Yi Li, Qian Li, Haibin Lv, Jun Zhang, Jie Jiang, Zhouchen Lin
Artificial Intelligence · Cross-listed from cs.LG
Growing and Transferring Pathways for LLM Reinforcement Learning
Haolin Tian, Yikang Li and Tonghan Wang
Reinforcement learning (RL) can substantially improve the
reasoning capabilities of large
language models, but an effective training run requires considerable resources. Reusing the computation acquired through RL across models would extend the value of that training. We propose GrowRL, an RL method that organizes learned updates into compact computational pathways through structural growth. GrowRL freezes the pretrained backbone and adds an independent causal
attention branch and a feed-forward network branch at each
Transformer layer. Zero-initialized output projections preserve the pretrained policy at initialization, and RL updates only the added pathways. The learned pathways remain explicit after training, allowing transfer to structurally compatible target models and subsequent adaptation with the target backbone frozen. The architecture also supports sequential transfer of additional pathways. By keeping the learned
attention and feed-forward computation separate from the pretrained weights, GrowRL provides an explicit structure for preserving and reusing the outcome of an RL run. Experiments across five backbones show competitive mathematical
reasoning and out-of-distribution performance with a small number of trainable parameters. Learned pathways provide immediate gains across all three transfer directions, with performance after only 10 target-side updates already close to that after 100 updates in every case. These results support computational pathways as parameter-efficient and reusable units of reinforcement learning adaptation.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
SLEM: Spectrum-Aware Latent Expert Merging
Dohyeon Kim, Bedionita Soro, Bruno Andreis et al. (+1 more)
Mixture-of-Experts (MoE) models scale model capacity efficiently by activating only a small subset of experts for each input, while still requiring all parameters to be stored in
memory, resulting in substantial
memory overhead. Expert merging techniques have recently emerged as a promising compression paradigm that reduces this overhead by consolidating multiple experts into a smaller set. However, existing approaches have two key limitations: (i) direct convex interpolation in parameter space is not generally guaranteed to yield meaningful interpolation of expert functions; and (ii) estimating expert similarity or merging coefficients often relies on calibration data, introducing dependence on the calibration distribution. To address these limitations, we propose Spectrum-Aware Latent Expert Merging (SLEM), a calibration-free expert merging framework that occurs in a structured latent representation of expert weights using a VAE. SLEM groups experts within and across layers based on latent similarities and derives merging coefficients from expert weight spectra. It then performs geometry-aware latent interpolation and decodes the resulting representations into merged expert weights. Compared with existing expert merging methods, SLEM achieves comparable or better performance on general knowledge
benchmarks and higher average performance on generation
benchmarks involving mathematical
reasoning and code generation.
Read the full abstract ▾
All authors Dohyeon Kim, Bedionita Soro, Bruno Andreis, Sung Ju Hwang
Artificial Intelligence
PXRD-Bench: How Close Are We to Determining Crystal Structures from Powder Diffraction?
Dongyeop Woo, Nofit Segal, Nayoung Kim et al. (+3 more)
Determining
crystal structures from powder X-ray diffraction (PXRD) would enable routine characterization of newly synthesized materials, including those absent from reference databases. Generative models offer a promising approach, but existing evaluations remain fragmented and largely assume single-phase samples with known composition. To fill this gap, we introduce PXRD-Bench, a unified
benchmark that extends evaluation to unknown per-element atom counts and recovery of both structures in two-phase mixtures. It provides approximately 4.1 million training structures with simulated PXRD, tests generalization to unseen compositions and structural prototypes, and evaluates recovery from experimental PXRD after excluding structurally matching training entries. To provide a strong reference baseline, we also introduce Bragglite, a PXRD-to-structure model developed through a systematic study of PXRD modeling choices. It achieves a 44.2% Top-1 match rate on experimental RRUFF patterns with known composition, 24.6% above the strongest prior baseline. Further analysis yields several key findings: some models fail to benefit from experimental PXRD, while generalization to unseen structural prototypes and recovery from two-phase mixtures remain challenging. Together, our
benchmark, systematic studies, and Bragglite clarify the capabilities and limitations of current PXRD-to-structure models.
Read the full abstract ▾
All authors Dongyeop Woo, Nofit Segal, Nayoung Kim, Minkyu Kim, Rafael Gomez-Bombarelli, Sungsoo Ahn
Artificial Intelligence
XAI-Guided Fourier Domain Generalisation for Pure-Simulation Sim-to-Real Deep Reinforcement Learning
Wei Yao, Chuyao Wang, Ziwei Wang et al. (+1 more)
Deep reinforcement learning has shown strong potential for
vision-based autonomous driving, but policies trained in simulation often suffer severe performance degradation when deployed in the real world. Existing sim-to-real methods commonly address this gap through image-transfer-based domain adaptation or policy-agnostic domain randomisation. However, the former requires laborious acquisition of target-domain data and is often limited to the deployment domain, whereas the latter introduces unguided perturbations that may not reflect the underlying sim-to-real discrepancy, leading to suboptimal transfer performance. To overcome these limitations, we propose XFD, an explainable artificial intelligence (XAI)-guided
Fourier domain generalisation framework for pure-simulation sim-to-real reinforcement learning. The proposed framework extracts explainability attribution maps from simulated observations, and converts these attributions into policy-conditioned
Fourier-domain interventions. By perturbing appearance-sensitive spectral components while preserving task-defining spatial structures, XFD constructs robustness-enhancing visual domains entirely within simulation. Subsequently, the proposed robust policy optimisation guides the policy towards attending to task-critical features while suppressing sensitivity to irrelevant visual information. Extensive experiments in simulation and zero-shot real-world deployment demonstrate that XFD consistently improves traveled distance and reward over standard policy and randomly domain-randomised baseline, especially on unseen maps with cluttered backgrounds. Attribution-based analysis further proves that the proposed policy preserves more consistent task-relevant visual evidence across simulation and real-world observations.
Read the full abstract ▾
All authors Wei Yao, Chuyao Wang, Ziwei Wang, Nabil Aouf
Artificial Intelligence · Cross-listed from cs.CL
PATMT2: Two-stage domain adaptation for multilingual patent translation
Xiaowei Su and Xusen Cheng
We present PatMT2 (Patent Machine Translation, v2), a two-stage LoRA pipeline that adapts the Hy-MT2-7B dedicated translation model to four-
language (Chinese/English/Japanese/Korean) patent translation. On six translation directions, the Stage-2 checkpoint reaches a macro-average BLEU of 43.39 (BF16) to 43.57 (AWQ INT4), improving over the Hy-MT2-7B base by up to +8.8 BLEU and also exceeding Qwen3-32B and several external systems on the same average. We then measure the cost of adaptation: probing 38
languages absent from the fine-tuning data, the model still produces correct, fluent output on 34, while four low-resource
languages collapse into distinct, reproducible failure modes. We treat these as diagnostic cases rather than retention rates, and report their mechanisms without attributing them to a single cause. Paired bootstrap tests confirm the translation gains over all baselines (p < 0.001).
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
StructZO: Structured Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning
Xuanlin Yang, Jia Li and Zhouchen Lin
Fine-tuning large
language models at scale is increasingly limited by the
memory cost of backpropagation. Zeroth-Order (ZO) optimizers reduce this burden by relying only on forward function evaluations, but they still exhibit a substantial performance gap to first-order (FO) optimizers such as Adam. We argue that this gap does not arise solely from the absence of explicit gradients: FO fine-tuning also benefits from informative low-rank optimization geometry, large-scale signal aggregation, and well-conditioned update directions. Motivated by this, we introduce StructZO, a structured Zeroth-Order optimization framework for
memory-efficient LLM fine-tuning. StructZO performs large-query ZO estimation within an activation-induced informative subspace and applies spectral control to the resulting reduced-space update before mapping it back to the original parameters. This lets ZO aggregate useful directional signals in a compact, geometry-aware space while avoiding the activation and optimizer-state
memory costs of backpropagation. We show theoretically that, when the induced subspace captures concentrated optimization-relevant directions, StructZO reduces the effective ZO estimation dimension from $mn$ to $mr$, with the remaining projection error governed by the spectral tail of the activation Gram
matrix. Empirically, across OPT-series and Llama3.1-8B on diverse downstreamtasks, StructZO improves over the strongest existing ZO baselines by up to $8.7%$ relative on average and up to $26.9%$ relative on individual tasks, while remaining within $1.5%$ of FO-Adam on average. These results suggest that structured and spectrally controlled ZO updates can substantially narrow the gap between ZO and FO optimization.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
CryptoFlowBench: Benchmarking Multi-Hop Reasoning on Blockchains for Cryptocurrency Fund Tracing
Runang He, Tongya Zheng, Jing Cao et al. (+7 more)
Pseudonymous accounts and complex smart-contract ecosystems substantially hinder the tracing of illicit cryptocurrency fund flows. Existing Graph Neural Networks (GNNs) have achieved promising performance in blockchain fraud detection, yet their static node- or edge-level predictions do not naturally generalize to multi-hop fund tracing. Meanwhile, existing tracing methods mainly rely on predefined heuristics to capture multi-hop relationships, limiting their adaptive
reasoning capabilities. To bridge this gap, we introduce CryptoFlowBench, a
benchmark constructed from authoritative reports on cryptocurrency-related illicit incidents, with four tasks spanning local to multi-hop fund tracing. These tasks pose substantial challenges to existing learning- and heuristic-based methods, particularly in complex multi-hop scenarios. We therefore propose ChainSleuth, a graph-tool-augmented
agent that iteratively reasons, invokes graph tools, and updates its tracing trajectory, enabling adaptive information acquisition and recovery from erroneous paths. Experiments show that no baseline consistently dominates all four tasks, revealing substantial gaps between local fraud detection and multi-hop fund tracing. ChainSleuth achieves notable improvements on multi-hop tasks, demonstrating the potential of agentic graph
reasoning for cryptocurrency fund investigation.
Read the full abstract ▾
All authors Runang He, Tongya Zheng, Jing Cao, Yucheng Ying, Shunyu Liu, Bingde Hu, Yang Gao, Zeyuan Hu, Jianrong Zhang, Mingli Song
Artificial Intelligence
RAP-WAM: Learning World-Action Models through Predictive Rehearsal and Action Perturbations
Yuanpeng He, Ceyao Zhang, Fangjing Li et al. (+8 more)
Recent world action models draw on
video generation priors to jointly predict future observations and
robot actions. Adapting these priors to control requires determining how future predictions should guide policy learning. RAP-WAM combines predictive Rehearsal and Action Perturbations (RAP) with future-supervised queries and Coupled Action Projection for policy learning. Predictive rehearsal trains on model-generated inputs while retaining recorded targets, and accumulates recurring errors into a spatial prior. We perturb actions and measure changes in
video predictions. Action-response-based spatiotemporal credit assignment combines these responses, prediction error, and the rehearsal prior to allocate visual supervision; spatially aggregating the responses determines supervision intensity across future action steps. No separate scoring network or deployment-time probe is required. The base learns from a
video-pretrained backbone without intermediate pretraining on external embodied data. We evaluate the fixed base and its
agent-refined, task-conditioned system. On 42 RoboDojo tasks, their average success rates are 12.85% and 15.62%, with Scores of 17.86 and 20.59. Across 15 real-
robot tasks, the complete system achieves 89.00% task-macro-average success, exceeding the strongest of five baselines by 37.67 percentage points. Across 315 fixed-output simulation windows, 45.21% of response-top20 positions fall outside error-top20, revealing information beyond prediction error.
Videos and further details are available on the project website: https://rapwam.github.io/.
Read the full abstract ▾
All authors Yuanpeng He, Ceyao Zhang, Fangjing Li, Kefei Zhu, Lijian Li, Yueheng Li, Tianjia He, Wenpin Jiao, Zhi Jin, Yaodong Yang, Yuanpei Chen
Artificial Intelligence · Cross-listed from cs.CV
VisExMEM: Visual Evidence-Based Explainable Multimodal Evaluation Metric
Subhadeep Roy, Christoph Leiter and Steffen Eger
Current image-text evaluation often relies on a global score, which gives limited insight into which semantic details are supported by the image. Explainable metrics provide rationales, but the visual evidence supporting those rationales can still be difficult to verify. We introduce VisExMEM, a reference-free evaluator that decomposes captions into atomic claims, localizes visual evidence, verifies each claim, and averages claim-level support into a global score. Explanations use the same evidence and decisions. We train Qwen3.5-based 4B and 9B models on 100K samples with multi-task SFT, counterfactual refinement, and evidence-aware GDPO. Across eight
benchmarks, VisExMEM-9B achieves the highest descriptive composite among open-source evaluators in our comparison, exceeding VQAScore by 11.7 points while remaining competitive with GPT-5.6 Sol. We also introduce AGITA-Bench, containing 600 human-annotated image-text pairs and 8.7K atomic claims for global and claim-level evaluation. For untuned Qwen3.5 and GPT-5.6 Sol controls, decomposed prompting raises the same composite by 3.6-5.1 points relative to holistic prompting. Human evaluation shows that VisExMEM explanations outperform prior explainable metrics and approach GPT-5.6 Sol.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
ARMED: Adaptive Retrieval-Augmented Medication Recommendation
Kyungkeon Chung, Se Un Park, Hyejin Lee et al. (+1 more)
Medication recommendation requires jointly considering diagnoses, comorbidities, longitudinal patient history, and treatment interactions. Although recent
retrieval-augmented generation approaches using
language models have shown promise for clinical recommendation, most existing systems rely on fixed
retrieval pipelines that cannot adapt to diverse clinical
retrieval scenarios and may introduce noisy or irrelevant evidence. We propose ARMED, an adaptive clinical RAG framework that dynamically expands
retrieval according to
retrieval sufficiency and current-admission relevance. ARMED first observes the initial
retrieval outcome and selectively performs supplementary or fallback multi-query
retrieval when additional evidence is needed. The framework also incorporates a relevance gate that activates only clinically relevant same-patient history and organizes retrieved evidence into structured query-level clinical evidence. Experiments on MIMIC-IV demonstrate that ARMED consistently outperforms previous static
retrieval baselines and improves overall medication recommendation quality. By combining locally runnable small
language models with adaptive
retrieval, ARMED supports medication recommendation without relying on external
language model APIs or task-specific fine-tuning.
Read the full abstract ▾
All authors Kyungkeon Chung, Se Un Park, Hyejin Lee, Junyoung Park
Artificial Intelligence
AuthGateBench: Benchmarking LLMs as Authorization Gate
Zhixiong Zhuang, Jin Jia, Zhiwei Shang et al. (+1 more)
Automated approval systems let coding
agents execute high-risk actions with minimal human oversight by delegating the authorization decision to a classifier, typically a large
language model (LLM). Such systems, adopted in tools like Claude Code and Codex, remain vulnerable to failure modes such as scope escalation, where the
agent takes actions exceeding what the user authorized. Existing
benchmarks focus mainly on malicious requests, evaluating refusal under an implicit policy. We introduce AuthGateBench, the first policy-guided
benchmark for authorization gating under benign requests. We implement a novel pipeline where an LLM generates contrast pairs with identical action and trajectory but differing request, flipping the label between block and allow. This allows us to assess whether models reason over context rather than the action alone. We further examine whether auxiliary environment signals can help models make better decisions. The resulting
benchmark comprises 1,400 instances spanning five failure modes drawn from real-world Claude Code incidents. Evaluations show accuracy degrades unevenly across failure modes as models over-rely on internal safety
alignment, and models still block most actions even when explicitly authorized, revealing unstable rather than deterministic decisions; retrospectively retrieved environment signals, however, substantially improve authorization accuracy.
Read the full abstract ▾
All authors Zhixiong Zhuang, Jin Jia, Zhiwei Shang, Ziyu Wang
Artificial Intelligence
Chain Dimension Scaling: Communication-Efficient Loop-Style Scaling for Industrial Short-Video Ranking
Zhimeng Jiang, Yuening Li, Ruixiao Sun et al. (+4 more)
Industrial recommendation rankers keep scaling in width and depth to billions of parameters, but this increasingly incurs costs in parameter growth, distributed communication overhead, and training inefficiency. We introduce \underline{C}hain \underline{D}imension \underline{S}caling (CDS), a scaling strategy orthogonal to width and depth. CDS repeatedly applies a single feature-interaction block with parameters shared across iterations, so the number of iterations (the chain length) becomes a new scaling dimension that adds no parameters. A lightweight intra-chain residual connection stabilizes optimization and improves quality. CDS enables two regimes. In the compression regime, shallow blocks with a longer chain match deeper baselines with fewer parameters and faster training; in the quality-scaling regime, increasing chain length under a fixed parameter budget yields consistent offline and online gains, suggesting the chain dimension adds modeling capacity beyond parameter reuse. We evaluate CDS in a large-scale multi-task short-
video ranking system in production. In the compression regime, CDS stays within $0.03\%$ of baseline offline quality while reducing trainable parameters by 26.6% and improving training throughput by 6.4%, with neutral-to-positive online participation. In the quality-scaling regime, quality improves monotonically with chain length. Wall-clock analysis shows the efficiency gain comes mainly not from reduced FLOPs but from lower cross-device synchronization overhead and reduced optimizer update cost. These results position parameter-shared iterative computation as a practical, communication-efficient scaling axis for industrial ranking systems.
Read the full abstract ▾
All authors Zhimeng Jiang, Yuening Li, Ruixiao Sun, Yuanzhen Lin, Kun Jin, Chuan He, Liang Liu
Artificial Intelligence
SLS-Bench: A Benchmark for Incident Log Summarization with Synthetic Observability Data
Valerii Iakovlev, Markus Spanring and Martin Flechl
As IT systems grow in complexity, automated
agent-driven incident response becomes increasingly critical. A key capability for these
agents is summarizing large log streams into human-readable reports. Further progress requires meaningfully evaluating this function, yet existing
benchmarks leave end-to-end summarization from large log streams underexplored due to the prohibitive cost and complexity of collecting real-world data. We introduce SLS-Bench, a
benchmark for incident log summarization featuring 90 tasks grounded in real-world incident reports, each with a synthetic log stream and a reference summary. To construct SLS-Bench, we developed a data generation pipeline that converts incident reports into structured incident models, which guide the generation of synthetic logs and reference summaries. This pipeline combines narrative grounding, explicit incident modeling, generator-verifier loops, and statistical comparisons with real-world log streams to produce realistic and controllable observability data. Our evaluation of 14 LLMs on SLS-Bench shows that while frontier models can produce useful summaries, they do so at substantial cost and latency, and open-weight models lag significantly. SLS-Bench provides a framework for systematic evaluation of log analysis
agents and a scalable blueprint for future synthetic observability
benchmarks.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
Estimating the Causal Impact of Social Navigation Signals in Corridor Scenarios
Francesco Baldo, Luca Castri, Gloria Beraldo et al. (+1 more)
Deploying
robots in human-shared environments requires deciding not only how to navigate, but also when dedicated social signals are worth emitting. Classic observation-based inference can be misleading in such settings: confounding factors may bias the estimated relationship between a signal and the task outcome, leading to incorrect decisions. Causal inference provides a framework for disentangling these relationships by modelling the mechanisms linking observations, actions, and outcomes, and by estimating interventional effects after accounting for confounding paths. We study a human-
robot interaction scenario in a corridor and use a causal model to estimate whether a social navigation signal causally improves transit success. We represent the interaction as a causal DAG involving
robot action, pedestrian occupancy, available space, task outcome, and a controlled confounder (static obstacles). We compare the interventional estimate with the observational estimate obtained by conditioning only on the
robot action, which does not explicitly model interventions. Our results show that accounting for confounding variables can reverse the conclusions drawn from naive observational analysis: the observational estimate wrongly suggests that the social signal is detrimental, whereas the causal estimate shows that it is beneficial. This discrepancy highlights how failing to account for confounding can lead to incorrect conclusions and demonstrates the importance of causal models for context-aware signalling decisions in social
robot navigation.
Read the full abstract ▾
All authors Francesco Baldo, Luca Castri, Gloria Beraldo, Nicola Bellotto
Artificial Intelligence
EvoWeb: A Benchmark for Coding Agents on Evolving Web Applications
David Nukrai, Bar Alon, Nativ Levy et al. (+6 more)
Web application development often proceeds through successive requests that extend an existing implementation. Yet web-generation
benchmarks primarily evaluate development toward fixed specifications. We introduce EvoWeb, a novel
benchmark comprising 320 cumulative requests over 32 web applications, grounded in real-world product features and structured by functional dependency graphs.
Agents iteratively modify a persistent codebase, while a
multimodal web
agent tests each intermediate application in a live browser, assessing newly requested functionality, cross-request integration, and previously requested functionality. To characterize reliability throughout development, we integrate trajectory performance across user-tolerance thresholds rather than impose a fixed stopping criterion. Experiments across open- and closed-source frontier models show that EvoWeb reveals clear performance differences between models, with cross-request integration emerging as a key challenge. Further analysis shows that later requests with deeper or more numerous dependencies are solved less accurately, while runtime errors become more frequent over successive requests. EvoWeb provides a testbed for evaluating and improving coding
agents in long-horizon, multi-request development.
Read the full abstract ▾
All authors David Nukrai, Bar Alon, Nativ Levy, Ido Andrew Atad, Ido Cohen, Itamar Zimerman, Lior Wolf, Eli David, Ilan Naiman
Artificial Intelligence
Recursive Environment Scaling for General Long-Horizon Agents
Lingxiao Jing, Zhengbo Jiao, Yichen Xiang et al. (+10 more)
We study environment scaling as a way to increase
agent-
benchmark difficulty while holding core task objectives fixed. Our framework, Recursive Environment Scaling (RES), transforms existing
benchmark environments while preserving their objectives and completion requirements. A proposer changes information access, resource relations, and execution dependencies; execution-grounded checks validate the resulting candidate, and accepted changes are inherited across rounds. This produces related environments for paired evaluation and training-trajectory collection. Experiments on 294 initial tasks from three
benchmarks show lower task success for all six evaluation models, with decreases of 57.14–77.14 percentage points on Claw-Eval-Live. With equal trajectory counts and identical optimization settings, fine-tuning on RES trajectories outperforms original-trajectory SFT in all nine model–
benchmark comparisons by 7.00–14.61 percentage points. Ablations identify recursive inheritance and dependency composition as important contributors to increased difficulty. Together, these results support environment scaling for both
agent evaluation and training.
Read the full abstract ▾
All authors Lingxiao Jing, Zhengbo Jiao, Yichen Xiang, Bofan Zhu, Lingbei Meng, Yan Ni, Haorui Chen, Ran Ran, Zhirong Shen, Yuheng Yang, Chenhang Cui, Yaosong Du, Rui Huang
Artificial Intelligence
RetroPlanner: Multi-Route Expansion and Multi-Objective Reasoning for LLM-Based Retrosynthesis Planning
Ye Rin Kim, Yongjun Jeong, Seongjun Yun et al. (+4 more)
Multi-step retrosynthesis planning is often considered solved once a route to purchasable starting materials is found, but such a route should also be practical in real-world chemistry. Recent LLM-based planners formulate this process as sequential decision-making over an AND-OR graph, yet typically expand a single molecule per turn and are optimized for solvability alone, leaving alternative routes uncompared across the multiple objectives that determine practicality before the search budget is committed. We introduce RetroPlanner, an LLM-based planner that jointly compares multiple routes to steer the search toward higher synthesizability, as measured by reaction plausibility, round-trip consistency, and starting-material price. RetroPlanner is trained to reason over chemical evidence: structural progress from the target molecule, bond changes and reaction classes, where candidate routes diverge from one another, and how they rank across multiple objectives. Experiments on multi-step retrosynthesis
benchmarks demonstrate that RetroPlanner recovers more alternative routes than prior LLM-based planners while improving synthetic route quality and maintaining a high success rate.
Read the full abstract ▾
All authors Ye Rin Kim, Yongjun Jeong, Seongjun Yun, Hanbum Ko, Soohyun Oh, Sungbin Lim, Sungwoong Kim
Artificial Intelligence · Cross-listed from cs.LG
LoopQuant: Accurate and Efficient Post-Training Quantization for Looped Transformers
Zhixiong Zhao, Zukang Xu, Xing Hu et al. (+3 more)
Looped
Language Models (LoopLMs) improve parameter efficiency by recursively reusing shared
Transformer modules, yet their repeated computation over evolving recurrent states poses new challenges for low-bit deployment. Existing post-training quantization (PTQ) methods, largely designed for feed-forward
Transformers, fail to account for cross-loop activation dynamics, heterogeneous loop sensitivity, and recursive error propagation, leading to substantial performance degradation at low precision. To address these challenges, we propose LoopQuant, a loop-aware PTQ framework for accurate and efficient low-bit quantization of LoopLMs. LoopQuant is built on three core components: 1) Cross-Loop Distribution Canonicalization (CLDC) learns a shared quantization-friendly representation across recurrent states while preserving parameter sharing; 2) Interaction-Aware Loop-wise Precision Allocation (ILPA) allocates activation precision under a fixed bit budget by modeling task-level loop sensitivity and cross-loop interactions; and 3) Loop-Conditioned Task Calibration (LCTC) further aligns quantized inference with the low-bit recursive trajectory through lightweight task-space calibration. Extensive experiments across LoopLM architectures demonstrate that LoopQuant consistently outperforms existing low-bit PTQ methods. On Ouro-2.6B, LoopQuant under W4A4 surpasses all W4A8 baselines in performance, while reducing model
memory by 65.3% with only 3.4% additional storage overhead over naive INT4 and achieving a 1.7 times decoding speedup over BF16. These results demonstrate a strong balance among accuracy, compression, and inference efficiency, providing a practical and deployment-friendly solution for low-bit LoopLM inference. The code is available at [https://github.com/Kishon-zzx/LoopQuant].
Read the full abstract ▾
All authors Zhixiong Zhao, Zukang Xu, Xing Hu, Lifeng Liu, Guangyu Sun, Dawei Yang
Artificial Intelligence
World Models Need a Physical Registry: Learning Internal Predictive States for Physically Plausible World Models
Shinseong Kim, Jaeseok Jeong, Jianlong Fu et al. (+1 more)
Video world models must generate physically plausible futures, not just realistic frames. Existing approaches typically use semantic, physical, or predictive information to guide the visual generation stream, leaving a fundamental question: where inside the generator should predictions of scene
evolution live? Standard
video tokens jointly encode appearance and dynamics, but provide no distinct state for learning and reading predictive dynamics. We answer this question with the Physical Registry: temporally grounded registry slots inside a
video DiT that are initialized from an observation-conditioned forecast, co-evolve with
video tokens, and receive future-representation supervision, making predictive dynamics an explicit, readable state of the generator. In a controlled comparison of predictive-state interfaces on Physics-IQ Verified, Physical Registry improves vanilla fine-tuning by 9.9/8.7 points on I2V/V2V, the largest gain among the interfaces we compare. Across all Cosmos and WAN backbones, Physical Registry improves Physics-IQ Verified scores. With only 0.45% additional parameters, it enables Cosmos 3 Nano 16B to surpass the published I2V score of Cosmos 3 Super 64B (43.56 vs. 42.7). On WorldModelBench, it also improves physical adherence and the total score for all four evaluated backbones. Because the registry becomes candidate-specific while remaining readable, the Physical Registry Selector (PRS) ranks emerging futures by how far their intermediate registry readouts depart from the shared forecast before full denoising is complete. Across four backbones, this selection improves I2V scores by 5.6-15.9% without completed-
video external scoring. Together, these results support a broader principle: dynamics prediction should live as an explicit model state that co-evolves with the
video representation. Project page: https://grainsack.github.io/physical-registry/
Read the full abstract ▾
All authors Shinseong Kim, Jaeseok Jeong, Jianlong Fu, Youngjung Uh