Computation and Language
LCoT-GV: Graph Attention Networks for Verifying Long Reasoning Chains in Large Language Models
Bérénice Jaulmes and Mehwish Alam
Large
Reasoning Models produce Long Chains-of-Thought (LCoTs) which involve breaking down the problem into smaller
reasoning steps before reaching the conclusion. However, these steps often contain contradictions, unsupported inferences, or irrelevant steps, even when the final answer is correct. We propose Long Chain-of-Thought Graph Verifier (LCoT-GV), a graph-based framework that represents LCoTs as
reasoning graphs. Each node in the graph represents a
reasoning step and the edges encode semantic and logical relations. A Graph
Attention Network is then trained to predict chain-of-thought correctness from the
reasoning graph. We construct a new graph-oriented verification
dataset from multiple
reasoning benchmarks for question answering in various domains. The results show that our method is competitive with the most similar approaches.
Read the full abstract ▾
Computation and Language
OCR-MetaReasoning Benchmark: Evaluating the Meta-Reasoning Ability of MLLMs in Text-Rich Image Understanding
Gengxu Li, Yuan Wu and Yi Chang
Text-rich image understanding requires
multimodal large
language models (MLLMs) to organize OCR (Optical Character Recognition)-grounded evidence across words, layout, fields, charts, and visual correspondences. Existing evaluations often conflate extraction with
reasoning and rarely test whether models follow the required
reasoning direction: applying visible rules, abstracting hidden regularities, or recovering missing premises. We introduce OCR-MetaReasoning, a controlled single-image
benchmark that treats deduction, induction, and abduction as distinct directions and separates final-answer correctness from
reasoning-process compliance. The
benchmark contains 1,500 verified samples in a balanced \(3\times5\) taxonomy crossing three
reasoning types with five OCR-object categories, along with reference
reasoning steps, automatic answer scoring, the Meta-
Reasoning Macro Score (MRMS), and the
Reasoning Process Compliance Score (RPCS). Experiments with representative closed-source and open-source MLLMs show that OCR-grounded meta-
reasoning remains far from saturated: models struggle with visible-rule application and layout-sensitive inference, while process-compliant rationales can accompany incorrect final answers under exact-match evaluation. The code is available at https://github.com/gengxuli/OCR-MetaReasoning.
Read the full abstract ▾
Artificial Intelligence
MedAgent-R1: Faithfulness-Aware Reinforcement Learning for Evidence-Grounded Medical Reasoning
Jiangwang Chen, Chenghao Zhang and Hengxing Cai
When medical AI systems hallucinate clinical
reasoning, the consequences extend beyond incorrect answers: fabricated justifications that superficially reference retrieved evidence can mislead clinicians into unsafe treatment decisions. Medical
reasoning agents must therefore produce not only correct answers but also faithful justifications that clinicians can verify against cited evidence. We identify a systematic failure mode in RL-trained
retrieval agents: outcome-only rewards improve accuracy while degrading faithfulness, a phenomenon we term confident
hallucination. The
agent learns to answer from parametric
memory and backfill plausible but unsupported justifications; citation fabrication rates rise from 16.5% to 31.8% even as accuracy improves by 5 points over the supervised baseline. We address this with a faithfulness-gated reward design: accuracy credit is conditioned on evidence grounding via a hard gate, complemented by
retrieval validity and conciseness signals that close exploitation paths unique to agentic
retrieval. The resulting system, MedAgent-R1, reduces citation fabrication from 31.8% to 4.7% and raises evidence completeness from 58.7 to 82.6 while maintaining 75.1% accuracy, with 13.2-point gains on HealthBench Safety. Under the same agentic
retrieval setup, MedAgent-R1 outscores GPT-4o on faithfulness-specific dimensions (Factual Support 4.55 vs. 4.25; Overclaiming 4.40 vs. 4.15) while remaining below GPT-4o in overall accuracy, suggesting that explicit faithfulness training yields evidence-grounding gains not achieved by scaling alone.
Read the full abstract ▾
Machine Learning
CoMPASS: Collaborative Molecular Property Prediction via Adaptive Small-Large Model Synergy
Wentao Li, Jiangjie Qiu, Yijun Li et al. (+2 more)
Accurate molecular property prediction requires both statistical reliability and chemical
reasoning. Graph neural networks can be calibrated directly on labeled assays but remain limited by the coverage of their training data. Large
language models (LLMs) can compare molecular evidence and articulate chemical rationales, yet are unreliable as standalone quantitative predictors. The central challenge is therefore to determine when an LLM should influence a calibrated model and by how much. Here we present CoMPASS, a
retrieval-calibrated framework for small-large model collaboration. CoMPASS retains a graph
attention network (GAT) as the predictive anchor, retrieves locally relevant training molecules, provides
attention-grounded evidence to an LLM, and converts its proposal into a bounded correction through an agreement-aware gate. Across six classification and two regression
benchmarks, CoMPASS improves the GAT anchor in regions of correctable uncertainty while limiting LLM intervention in high-confidence regimes. Ablations show that the gains arise from validation-calibrated
retrieval and bounded fusion rather than prompting alone. These results suggest that generative
reasoning should augment calibrated prediction through evidence-grounded, controlled corrections rather than direct output replacement. Code is available at https://github.com/littlepeachs/CoMPASS.
Read the full abstract ▾
All authors Wentao Li, Jiangjie Qiu, Yijun Li, Leyi Zhao, Xiaonan Wang
Robotics
CIG-RL: Curiosity-Driven Information-Guided Reinforcement Learning for Source Term Estimation in Uncertain Environments
Junhee Lee, Seunghwan Kim, Hongro Jang et al. (+4 more)
Source term estimation (STE), which aims to estimate key properties of the gas source, is essential for identifying hazardous gas releases. Information-theoretic approaches have been adopted for autonomous STE using mobile sensors due to robustness in noisy environments, yet their online action selection incurs substantial computational cost. Deep reinforcement learning (DRL) provides a promising alternative with its fast decision-making capability. In DRL-based STE, the
agent selects actions based on belief states of the source term updated from noisy measurement sequences. However, existing methods rely on random exploration or solely on belief uncertainty reduction without an effective exploration strategy in DRL, which can limit policy robustness in noisy environments. To address this, we propose a curiosity-driven information-guided reinforcement learning for robust and efficient STE. The proposed method promotes active exploration of novel belief state transitions that have not been sufficiently explored during training. We further introduce an uncertainty-adaptive active perception reward to guide efficient source search under uncertainty. Simulations under high-noise conditions and real-world experiments demonstrate the robustness and feasibility of the proposed framework, highlighting its potential for practical STE problems.
Read the full abstract ▾
All authors Junhee Lee, Seunghwan Kim, Hongro Jang, Hyungjin Kim, Hyoungho Park, Changseung Kim, Hyondong Oh
Artificial Intelligence
HiRS-Agent: A Hierarchical Multi-Agent System for Reliable Long-Horizon Remote Sensing Task Solving
Boyang Mu, Zhiwei Wei, Mugen Peng et al. (+1 more)
Recent advances in large
language models and
multimodal models have pushed remote sensing (RS) processing from simple perception models to agentic systems designed to tackle complex, long-horizon RS tasks. However, existing systems often rely on monolithic decision-making frameworks, which fail to accommodate the multi-stage, interdependent nature of RS tasks. This centralized approach leads to challenges such as unstable task execution, incorrect tool usage, and error propagation across stages. To address these issues, we propose HiRS-
Agent, a hierarchical multi-
agent system for long-horizon RS task solving. HiRS-
Agent adopts a two-level collaborative architecture: the Manager Layer handles dynamic routing, step-level verification, replanning, and termination control, while the Specialist Layer organizes domain-specific tools according to the RS workflow and is responsible for subtask
reasoning and tool execution. To further enhance the system's capability, we introduce a two-stage supervised tuning strategy and a verification-guided hierarchical reinforcement learning stage to jointly optimize coordination and tool-use policies. Experiments on Earth-
Agent Benchmark and ThinkGeo show that HiRS-
Agent substantially improves long-horizon tool-use capability and final-task correctness, demonstrating the effectiveness of structured multi-
agent collaboration for reliable RS
agents. The code is publicly available at https://github.com/IntelliSensing/HiRS-
Agent.
Read the full abstract ▾
All authors Boyang Mu, Zhiwei Wei, Mugen Peng, Wenjia Xu
Game Theory
Reaching Fairness by Reallocating Goods
Robert Bredereck, Eva Deltl, Tanmay Inamdar et al. (+3 more)
Fair allocation of indivisible goods has largely been studied under the assumption that no prior allocation exists. Motivated by practical settings with pre-existing (and possibly unfair) allocations, we study how to achieve
fairness through limited reallocations. Building on recent work on reformability/reallocations, we consider three
fairness notions—envy-freeness (EF), envy-freeness up to one good (EF1), and envy-freeness up to any good (EFX)—and optimize the number of goods reallocated. We analyze both the classical and parameterized complexity of these problems, providing a comprehensive analysis across multiple
fairness notions.
Read the full abstract ▾
All authors Robert Bredereck, Eva Deltl, Tanmay Inamdar, Pallavi Jain, Pranjal Pandey, Bin Sun
Data Structures and Algorithms
The (Parameterized) Complexity of Ordering a Graph While Avoiding a Forbidden Pattern
Thomas Depian, Simon D. Fink, Alexander Firbas et al. (+3 more)
In this paper, we study the Pattern Avoidance problem of determining whether a given graph $G$ admits a linear vertex order which avoids a given pattern $P$, i.e., a vertex sequence with some forced and forbidden edges, on every suborder. Such patterns form a natural ordered counterpart to induced subgraphs in the order-invariant setting, and it is known that Pattern Avoidance captures a broad variety of graph problems including Bandwidth, Vertex Coloring, Queue Number, and extends to vertex-deletion problems such as Odd Cycle Transversal. We show that Pattern Avoidance is $\Sigma_2^{\textsf{P}}$-complete and furthermore remains intractable (in both the classical and parameterized sense) even under a variety of severe restrictions to both the pattern $P$ and the graph $G$. As our main contributions, we complement these lower bounds with the following tractability results, which provide a unifying framework for recognizing pattern-definable graph classes: - a fixed-parameter
algorithm w.r.t. the vertex integrity of $G$ plus $|V(P)|$, - a fixed-parameter
algorithm w.r.t. the neighborhood diversity of $G$ plus $|E(P)|$, and - a
polynomial algorithm for Pattern Avoidance on forests for almost all constant-sized patterns.
Read the full abstract ▾
All authors Thomas Depian, Simon D. Fink, Alexander Firbas, Robert Ganian, Martin Nöllenburg, Marie Diana Sieper
Computational Complexity
Upper and lower bounds on the OBDD-width of a special integer multiplication
Tong Qin
We consider the Boolean function ${\rm SMul}_{n-1}^n(\boldsymbol{x},\boldsymbol{y})$, which computes the middle bit of the multiplication of two natural numbers represented as $n$-bit binary strings $\boldsymbol{x}$ and $\boldsymbol{y}$, drawn from a restricted domain. We investigate the width of OBDDs computing ${\rm SMul}_{n-1}^n$. We introduce a combinatorially defined function $s_*(n)$ and show that the width of such OBDDs is $\Theta(2^{s_*(n)})$.
Read the full abstract ▾
Computation and Language
MURANO: Design, Run, and Reproduce Mechanistic Interpretability Experiments as Composable Pipelines
Alireza Bayat Makou, Emirhan Böge, Phu Gia Hoang et al. (+5 more)
This paper presents Murano, an open source framework for designing, running, and reproducing mechanistic interpretability studies of large
language models, intended for researchers across disciplines. These studies often combine loading, recording, attribution, intervention, and evaluation, while existing libraries tend to focus on different parts of this workflow. As a result, researchers using several libraries may need to adapt outputs from one for use by another. To bridge this gap, Murano represents operations from these five areas as composable steps. Steps exchange named result artifacts and declare the inputs they require and the outputs they produce. A pipeline executes its steps in the order supplied, and Murano uses canonical addresses when component identities pass between operations. Murano builds on existing interpretability and machine learning libraries. We demonstrate Murano through two reproductions of established interpretability studies and one illustrative sparse autoencoder case study.
Read the full abstract ▾
All authors Alireza Bayat Makou, Emirhan Böge, Phu Gia Hoang, Federico Tiblias, Jingcheng Niu, Subhabrata Dutta, Richard Eckart de Castilho, Iryna Gurevych
Computation and Language
SwarmBench: Can Large Language Models Act as Agent Swarm Orchestrators?
Jinshan Gao, Zhuoran Jin, Tianyi Men et al. (+2 more)
Large
language model-based multi-
agent systems are evolving from fixed interaction
topologies toward dynamically orchestrated
Agent Swarms. However, existing
benchmarks are still largely based on single-
agent or general-purpose
agent tasks, making it difficult to systematically evaluate key orchestration capabilities. We propose SwarmBench, a
benchmark that evaluates model performance from multiple perspectives, including accuracy, efficiency, cost, and process quality. Experimental results show that current models exhibit substantial differences in orchestration capability. These differences are reflected not only in final accuracy, efficiency, and cost, but also in the overall quality of the orchestration process itself. Based on these findings, we further propose SwarmExp, a simple yet effective method based on experience extraction and experience replay, which consistently improves the orchestration performance of large
language models.
Read the full abstract ▾
All authors Jinshan Gao, Zhuoran Jin, Tianyi Men, Kang Liu, Jun Zhao
Hardware Architecture
LLM-based Hardware Development with Hierarchical IRs and End-to-End Multi-Agent Workflow
Chenyang Yin, Agasthi Haputhanthri, Aditya Anirudh Jonnalagadda et al. (+7 more)
Large
language models (LLMs) are increasingly used in software development, but their use in complex hardware design remains limited. This gap stems from both the scarcity of public hardware training data and the fundamentally different methodologies used in hardware design. In particular, applying LLMs to hardware requires more than direct RTL generation: the model must understand module boundaries, inter-module connections, and verification requirements. In this paper, we present an LLM-based hardware development framework with hierarchical intermediate representations (IRs) and an end-to-end multi-
agent workflow. The core idea is to provide an abstraction of hardware design to LLMs through two structured IRs: Architectural Sketch, which captures module
topology and interconnection, and Operational Specification, which defines per-module functionality and interfaces. Our framework uses these IRs to decompose a complex design into sub-modules, specify the per-block functionality, and derive how each module should be tested and verified. We incorporate a multi-
agent debug loop in the framework, allowing
agents to get the error feedback and control the debug details such as the signals to be probed for simulation. We evaluate our framework on Verilog-Eval
benchmark, achieving a pass@5 rate of 95.5%, which surpasses current state-of-the-art LLM generation frameworks. To better assess performance on complex, realistic designs, we introduce a new case study spanning applications from general-purpose processors to digital signal processing systems. Experimental results indicate that such complex designs exceed the capabilities of existing approaches, whereas our framework is the only one capable of producing functional end-to-end design. Our generated RTL follows all industry-standard design rules, is lint-clean, functionally correct and fully synthesizable.
Read the full abstract ▾
All authors Chenyang Yin, Agasthi Haputhanthri, Aditya Anirudh Jonnalagadda, Zhenyu Bai, Yuanming Song, Saranyu Chattopadhyay, Mohammad Fadiheh, Tom Zelazny, Subhasish Mitra, Tulika Mitra
Computer Vision
InfraOcc: An Infrastructure Occupancy Benchmark with Static-to-Dynamic Reasoning
Lei Yang, Xiaokai Bai, Boqi Li et al. (+8 more)
Fixed-viewpoint infrastructure sensors repeatedly observe the same traffic space, making roadside 3D occupancy structurally different from ego-vehicle perception: a near-persistent static scaffold is overlaid with sparse, short-lived dynamic events. Existing occupancy
benchmarks and methods, however, are built around moving ego vehicles and neither measure nor exploit this structure, instead treating occupancy as flat one-shot voxel classification. We address this gap from both data and model perspectives. We build InfraOcc, to our knowledge, the first real-world infrastructure-side semantic occupancy
benchmark, with dense voxel annotations for 290 multi-modal sequences in a fixed roadside frame, a static-dynamic decoupled annotation pipeline, unified camera-only,
LiDAR-only, and multi-modal evaluation, and diagnostics for static and dynamic occupancy. InfraOcc shows that static infrastructure fills 97.3% of occupied voxels and persists across frames, whereas dynamic participants have a median occupied-frame ratio of only 1.8% per location, revealing a structural static-dynamic asymmetry beyond semantic long-tailedness. We further propose ProSD-Occ, which reformulates occupancy as progressive static-to-dynamic evidence
reasoning: it explains persistent layout, exposes residual dynamic evidence under static-confidence guidance, and recomposes static, dynamic, and free-space evidence into a unified field. ProSD-Occ ranks first in overall, dynamic, static, and
geometric occupancy on every track, e.g., a 23.5% relative camera-only dynamic-mIoU gain over the strongest baseline and 65.87 multi-modal overall mIoU, establishing fixed-viewpoint roadside occupancy as a distinct problem with its own
reasoning paradigm. The
benchmark and code will be publicly available at https://github.com/yanglei18/InfraOcc
Read the full abstract ▾
All authors Lei Yang, Xiaokai Bai, Boqi Li, Chunmian Lin, Li Wang, Ziying Song, Jiahuan Zhang, Enhui Ma, Haibao Yu, Jiaqi Ma, Kaicheng Yu
Computer Vision
APT: Anchor-aligned Perturbations for Tamper Localization in Fully Regenerated Images
Suhyeon Ha, Woo Jae Kim, Joonsung Jeon et al. (+2 more)
Proactive tamper localization embeds an imperceptible signal into an image prior to distribution, enabling pixel-level manipulation detection. Existing methods assume a spliced (SP) setting, where synthesized regions are composited onto the original background, leaving embedded signals intact. However, real-world
diffusion-based inpainting operates in a fully regenerated (FR) setting, where the entire image undergoes denoising, disrupting background signals and rendering existing frameworks ineffective. We propose APT, a semi-fragile latent-space perturbation that embeds a dense, vector-wise localization signal. By aligning each spatial feature vector toward a fixed anchor direction, APT localizes tampering via the
alignment disparity between synthesized foreground and anchor-aligned background features after inpainting. The proposed hard negative mining loss and noisy perturbation branch further enforce uniform
alignment. Experiments on COCO demonstrate that APT achieves an FR IoU of 0.92, outperforming the strongest baseline (WAM, 0.84), while existing methods collapse to near-random performance (AUC 0.5), establishing APT as a practical forensic framework generalizable across tampering types unknown at test time.
Read the full abstract ▾
All authors Suhyeon Ha, Woo Jae Kim, Joonsung Jeon, Sooel Son, Sung-eui Yoon
Machine Learning
Seasonality-Aware Hybrid Convolutional Transformer for Antarctic Sea Ice Concentration Forecasting
Danyang Li, John Taylor, Thang Bui et al. (+1 more)
Antarctic sea ice concentration (SIC)
forecasting is an important yet challenging task due to the coexistence of complex spatial structure, long-range temporal dependencies, and strong seasonal variability. Conventional convolution-based models are effective at capturing local spatial patterns, but often have limited ability to model long-term temporal
evolution. To address these challenges, we build on a hybrid convolutional
transformer forecasting framework for monthly Antarctic SIC
forecasting. This framework combines convolutional encoding for spatial feature extraction with space-time factorised self-
attention for SIC modelling. We further introduce two season-based mechanisms: a month-aware positional encoding that injects calendar-month information into the
token representation, and a seasonal temporal bias that encourages
attention to periodically related historical states. Experimental results show that the proposed framework achieves better performance than convolutional and recurrent baselines as well as ECMWF's physics-based dynamical model SEAS5 under both classification and regression metrics. Ablation studies further indicate that the seasonality-aware components provide consistent additional gains in both short- and long-horizon prediction. These results demonstrate the value of combining convolutional structures,
attention mechanisms, and periodic prior information for Antarctic SIC
forecasting.
Read the full abstract ▾
All authors Danyang Li, John Taylor, Thang Bui, Quanling Deng
Computer Vision
Joonki Min, Chaeyun Kim, Hyungwook Choi et al. (+4 more)
Multimodal Large
Language Models (MLLMs) are increasingly deployed in multi-image scenarios requiring complex
reasoning across visual contexts. However, current MLLMs remain fundamentally limited by object
hallucination-generating plausible yet factually inconsistent descriptions about objects. Existing
benchmarks, designed primarily for single-image settings or providing only high-level multi-image assessments, cannot systematically diagnose how visual complexity and
reasoning demands trigger
hallucination. To address this gap, we introduce MIOH, a fine-grained multi-image object
hallucination benchmark that systematically evaluates object
hallucination across four foundational tasks (existence, counting, attribute, position) through three multi-image
reasoning patterns (comprehensive, comparative, selective) under three controlled
adversarial pressures (visual context scale, perceptual difficulty, contextual bias). Through evaluation of 29 models, we reveal that even state-of-the-art systems like GPT-5 and Gemini-2.5-Pro exhibit distinct failure patterns across different
reasoning patterns and tasks. Our evaluation reveals that
hallucination stems not merely from perceptual failures but from integration-stage limitations when maintaining object representations across multiple images. MIOH provides a controlled framework for analyzing multi-image object
hallucination and serves as a critical evaluation tool for developing more reliable
multimodal AI systems.
Read the full abstract ▾
All authors Joonki Min, Chaeyun Kim, Hyungwook Choi, Yejin Kim, Kihyun Kim, Yohan Jo, Joonseok Lee
Artificial Intelligence
PyKEEN-NSX: A Modular Framework for Static, Dynamic and Schema-Aware Negative Sampling in PyKEEN
Ivan Diliso, Nicola Fanizzi and Claudia d'Amato
Embedding methods have become popular due to their scalability on link prediction and/or triple classification tasks on Knowledge Graphs (KGs).
Embedding models are trained relying on both positive and negative samples of triples. However, since KGs generally contain only positive assertions, negative samples are artificially generated through negative sampling strategies, ranging from simple random corruption to more sophisticated approaches that exploit structural, semantic, or
embedding information. The design and implementation of advanced negative samplers remains challenging, as most popular Knowledge Graph
Embedding (KGE) libraries provide support only for basic strategies and lack a unified framework for developing more advanced and customized solutions. To address this gap, we introduce PyKEEN-NSX, an extension of PyKEEN, the popular KGE framework, that provides a modular engineered abstraction for negative sampling. The proposed architecture separates the generation of candidate negative pools, conditioned on an explicit context, from the selection strategy, enabling the development and integration of static, schema-aware and dynamic approaches within a consistent framework. Based on this abstraction, we implement six negative samplers, while remaining fully compatible with existing PyKEEN workflows and pipelines. As a proof of concept, we study negative availability across four
datasets, showing that constrained pools frequently fall below the requested number of negatives, so that the encoded criterion is to a large extent replaced by the random fallback that supplements them.
Read the full abstract ▾
Artificial Intelligence
Geometry of Divergence: Tracking Hidden-State Trajectories for Adaptive Multi-Turn Reasoning
Jie Liang, Zhengxin Yu, Hamid Nasiri et al. (+1 more)
LLM
agents need to sustain goal-consistent
reasoning across long multi-turn interactions under strict resource constraints. However, as the multi-turn context accumulates, it can destabilize the underlying LLM's internal representation of task-relevant information from earlier turns, blurring the boundary between constructive
reasoning and representation drift. We formulate multi-turn
reasoning as a hidden-state trajectory of the underlying LLM that is characterized via two complementary signals: temporal
curvature that captures the directional consistency of turn-to-turn updates, and variance slope which measures the expansion or contraction of the exploration space. Across four tasks and three underlying LLMs, we observed that these
geometric signals distinguish between correct and incorrect episodes prior to completion. We further decompose each episode into three-action chains formed from four actions (Read, Write, Respond, Transfer) and show that separability is action-dependent, with different signals distinguishing various chain patterns. Our experiments demonstrate that trajectory geometry can identify critical turns in the
reasoning process, increasing task success rates on $\tau$-Bench from 24.1% to 39.6% while reducing
token cost by 11.2%.
Read the full abstract ▾
All authors Jie Liang, Zhengxin Yu, Hamid Nasiri, Peter Garraghan
Computation and Language
Where Identity Lives: Localized, Retain-Free Identity Unlearning in Multimodal Large Language Models
Kangwook Ko, Jaehyuk Jang, Wonjun Lee et al. (+2 more)
Removing a specific individual's information from
multimodal large
language models (MLLMs) is often needed after deployment, but existing methods rely on a retain set, which is hardest to obtain at that point, and rebuilding it recreates the
privacy exposure that unlearning aims to remove. Forgetting from the forget set alone instead damages the shared visual-
language computation, harming perception. We cast retain-free unlearning as a localization problem: causal tracing, weight transplant, and Fisher overlap all point to early-to-mid decoder MLPs as the layers where identity information is stored and, unlike other module families, can be modified without substantially disrupting
vision. We turn this into Pathway-Aware Visual-attribute Anchoring (PAVA), which confines updates to these layers and pairs a forget loss with a visual-attribute anchor that preserves image-grounded behavior by distilling the model's own pre-unlearning answers from the forget images alone. On MLLMU-Bench and ReMem, PAVA gives the strongest forget-retain trade-off among forget-set-only methods and remains competitive with retain-based baselines.
Read the full abstract ▾
All authors Kangwook Ko, Jaehyuk Jang, Wonjun Lee, Hee-Seon Kim, Changick Kim
Cryptography and Security
Lie to Me: Finding Bugs in ZK DSL Toolchains with Adversarial Witness Injection
Sebastian Watzinger, Christoph Hochrainer, Valentin Wüstholz et al. (+1 more)
Zero-knowledge domain-specific
language (ZK DSL) toolchains compile programs into constraint systems and generate witnesses for cryptographic proofs. Bugs in these toolchains can leave the enforced constraints weaker than the source-program semantics, admitting proofs for invalid executions. Such soundness bugs may remain invisible to valid-execution testing because all valid executions still behave correctly. We present Liezz, a testing framework that generates ZK DSL programs and exposes these bugs through
adversarial witness injection. For each generated deterministic program, Liezz executes two public input assignments with different outputs and splices their witnesses, combining the input of one execution with the output of the other. The resulting witness is invalid by construction. A correct toolchain must reject it; acceptance exposes a soundness bug. Controlled divergence and multiple witness-splicing strategies preserve enough consistency to expose missing constraints. Liezz also generates parameterized standard-library calls to reach complex functionality. Liezz supports Circom, Corset, Gnark, and Noir. It finds 13 bugs, including seven with soundness impact. Several are reachable only through generated standard-library calls. Under the same testing budget, a valid-execution baseline does not expose any of the soundness failures revealed by accepted injected witnesses, showing that
adversarial witness injection reaches failures missed by valid-execution testing.
Read the full abstract ▾
All authors Sebastian Watzinger, Christoph Hochrainer, Valentin Wüstholz, Maria Christakis
Computation and Language
What It Costs to Compose, Rebuild, and Correct Precomputed Memory
Asa Shepard
Language models can answer from precomputed
memory, a model's saved reading of a body of material, reused across requests instead of read again at each. This paper maps where that practice preserves correctness and the conditions under which it fails. Across experiments on Llama-3.1-8B-Instruct using both saved key-value caches and trained compressions of them, precomputed
memory degrades when assembled from separately prepared parts, stays current only through rebuilds costing a large fraction of full preparation in our measurements, and ignores corrections served beside it conditional on phrasing. If precomputed
memories can be served alongside one another, be cost-efficiently rebuilt, and be superseded by new information arriving in real-time, they can serve as a way to avoid re-feeding context to a model over repeated queries. The implication of our results for a deployed system that deals with a variety of queries is that precomputed
memories are best rebuilt on the cadence at which new information changes what the
memory was originally computed from. Both warm-rebuilding trained compressions of key-value caches and serving specifically-phrased updates beside a
memory, as pasted text or injected cache state, show particular promise for keeping precomputed
memories current, the latter as an interim measure between rebuilds, and we measure the cost and name the remaining questions associated with each.
Read the full abstract ▾
Computation and Language
BiG-SURE - Bipartite Graph for Semantic Uncertainty and Reliability Estimation of LLMs
Debarpan Bhattacharya, Malay Phadke and Sriram Ganapathy
Reliable uncertainty estimation is a crucial requirement for deploying large
language models (LLMs) and
vision-
language models (VLMs) in safety-critical settings, especially when the model parameters are not accessible (black-box). We propose BiG-SURE, an uncertainty
estimator based on cross-temperature semantic agreement. The method samples low-temperature responses as stable semantic anchors and high-temperature responses as probes under meaning-preserving input transformations. It then constructs an anchor-probe Bipartite Graph (BiG) using NLI-based entailment scores and defines confidence through the normalized squared spectral energy of this
matrix, with uncertainty given by its complement. This bipartite graph-based Semantic Uncertainty and Reliability Estimation (SURE) score measures whether high-temperature probes remain semantically aligned with the model's stable low-temperature belief or not. We evaluate BiG-SURE on text QA,
multilingual QA, and
multimodal QA tasks across multiple model families. In these experiments, BiG-SURE improves average abstention AUROC over prior black-box uncertainty
estimators, while remaining simple, unsupervised, and applicable to black-box model settings.
Read the full abstract ▾
Robotics
Temporal Forcing: 4D Representation Alignment for Vision-Language-Action Models
Xingyu Ding, Yuzhong Zhao, Chunhai Zhao et al. (+3 more)
Long-horizon robotic manipulation requires
vision-
language-action (VLA) models to track scene states and their
evolution beyond the current observation. However, simply conditioning policies on observation history does not guarantee that the history is effectively utilized: action supervision constrains what the policy should do, but only indirectly constrains what its history representations should retain. To resolve this, we present Temporal Forcing, a 4D representation
alignment framework that explicitly supervises latent temporal states and their transitions. Specifically, we first introduce a history pathway that compresses past observations into compact latent
tokens. We then align these
tokens and current-frame features with
geometric targets from a pretrained 4D foundation model, providing direct supervision at both the state and transition levels. The 4D foundation model and
alignment heads are used only for training-time supervision. Temporal Forcing improves average success from 96.6% to 98.8% on LIBERO, with the largest gain on LIBERO-Long (93.8% to 97.2%), and from 53.5% to 62.8% across twelve RoboTwin 2.0 tasks. Furthermore, Temporal Forcing increases full-task success from 20.0% to 43.3% on a physical multi-stage hidden-placement task. Controlled experiments show that 4D representation
alignment is crucial for making observation history beneficial to the model. Code will be publicly available.
Read the full abstract ▾
All authors Xingyu Ding, Yuzhong Zhao, Chunhai Zhao, Yinghuan Shi, Chaoyang Zhao, Yifan Zhang
Machine Learning
Three Steps at a Time: Learning Representations from Action Sequences in Contrastive RL
Michal Korniak, Kamil Dybek, Benjamin Eysenbach et al. (+2 more)
While self-supervised approaches to reinforcement learning have achieved strong results by learning representations of states and actions, a key open question is the time scale over which actions should be modeled. Departing from the standard formulation relying on single-step actions, we extend contrastive reinforcement learning (CRL), a prototypical self-supervised method, to operate over action chunks, and find that this results in large, pervasive gains across established offline and online
benchmarks: +31.7% and +93.1% across 18 and 11 environments respectively. While action-chunking-driven gains are generally explained through the ability to model non-Markovian, temporally extended policies, and to propagate unbiased multi-step returns, interestingly, we find that these arguments only partially apply to CRL. Our empirical studies suggest that, in the context of CRL, an action chunk carries more information about the goal than a single action, measurably improving the critic's representations, and rendering the
algorithm significantly more effective.
Read the full abstract ▾
All authors Michal Korniak, Kamil Dybek, Benjamin Eysenbach, Marco Bagatella, Michał Bortkiewicz
Machine Learning
MolLedger: An Additive Graph Neural Network with Chemically Grounded ADME Attributions
Christina X. Ji
Optimizing absorption, distribution, metabolism, and excretion (ADME) is an important part of small molecule drug discovery. Many machine learning models have been built to predict ADME properties to facilitate this optimization process, but explaining model predictions is challenging. We propose a new graph neural network architecture with built-in atom attributions. Our model MolLedger learns a global context vector for each molecule and a per-atom head to output atom scores that sum to the predicted property. The atom scores are regularized to align with relevant chemical properties. We prove that MolLedger is a universal approximator and demonstrate empirically that the new architecture obtains explainability with little effect on performance. We show that the interpretations from MolLedger are faithful, concordant with held-out physical properties, and align with the changes between matched molecular pairs. Our case studies comparing interpretations from multiple methods on molecular pairs reveal that MolLedger is much better at producing sensible explanations for predicted property changes.
Read the full abstract ▾
Game Theory
Test-time Reinforcement Learning in Imperfect Information Games
Ondrej Kubicek, Viliam Lisy and Tuomas Sandholm
Test-time
reasoning has significantly improved performance in domains ranging from games to
language models. However, test-time policy changes with formal guarantees on the performance of the resulting strategy remain a challenge in two-player zero-sum imperfect-information games. Existing solutions are limited to tabular methods or single gradient step updates. In this work, we investigate policy-gradient
algorithms as a method for scalable test-time
reasoning. We extend the concept of gadget game, tabular technique for test-time search, to the reinforcement learning setting. Unlike prior approaches, we represent the gadget game implicitly by modified sampling and neural policy rather then explicitly by constructing it, thereby removing constraints on subgame size. Furthermore, we formally prove that, unlike prior tabular
algorithms, regularized policy-gradient
algorithms limit possible strategy degradation caused by test-time
reasoning, even without the gadget games. Our evaluation across small- and large-scale games confirms that additional test-time training often substantially improves performance relative to the blueprint strategy.
Read the full abstract ▾
Computer Vision
Quantum-Grassmann-Plucker Token Mixing for Deep Learning-Based Post-Disaster Damage Assessment
Kooroush Farahkhah, Umut Lagap, Taha Rezaei et al. (+1 more)
Timely post-disaster building damage assessment from satellite imagery is a critical engineering decision support task, yet it remains constrained by class imbalance, ambiguous intermediate damage states, and limited cross-event transferability. This study presents, to our knowledge, the first application of Grassmann-Plucker (GP)
token mixing to computer
vision and introduces two extensions for image classification: the
Quantum-inspired Grassmann-Plucker (QGP) head and the Hybrid
Quantum Machine Learning Grassmann-Plucker (HQML-GP) head. The GP head represents multiscale relationships among image patch
tokens by encoding subspaces formed by
token pairs with Plucker coordinates; QGP enriches these coordinates with amplitude-derived probability features, whereas HQML-GP incorporates expectation values generated by a simulated
quantum circuit into the
geometric token representation. Paired pre- and post-event image patches from the xBD tornado
dataset were processed using a frozen six-channel
Vision Transformer base encoder with 16 x 16-pixel patches. The three GP-based heads were compared with multilayer perceptron and
Transformer baselines under identical training, checkpoint selection, and evaluation protocols. Joplin and Moore tornado samples were used for model development and seen-event testing, while Tuscaloosa was reserved for unseen-event evaluation. QGP led both test sets in accuracy and macro-F1: 83.46% and 64.50% for the seen events, and 66.45% and 52.70% for the unseen event. Although HQML-GP obtained the highest validation macro-F1 of 65.63%, it did not surpass QGP on either test set and required substantially more training time per epoch. These results establish GP
token mixing as a competitive
attention-free alternative to conventional
Transformer-based
token mixing for paired satellite image damage classification.
Read the full abstract ▾
All authors Kooroush Farahkhah, Umut Lagap, Taha Rezaei, Saman Ghaffarian
Computation and Language
GMTS: Gradient Magnitude-based Token Selection Improves RLVR Training for LLM Reasoning
Outongyi Lv, Yuanwei Zhang and Xiaoqun Zhang
Reinforcement learning (RL), particularly RL with Verifiable Rewards (RLVR), has recently emerged as a central paradigm for enhancing large
language models' (LLMs)
reasoning abilities, demonstrating remarkable effectiveness across
reasoning tasks. Recent studies suggest that high-
entropy tokens play an exceptionally important role in model training, since training with only the highest 20%
entropy tokens yields significant performance gains. However, why such high-
entropy tokens are beneficial remains insufficiently understood. In this work, we find that although high-
entropy tokens within one answer tend to correlate with large gradient magnitude,
entropy alone fails to consistently reflect
token importance across different answers, considering the variations in the answer-level reward signals. Based on this observation, we introduce the Gradient Magnitude-based
Token Selection (GMTS) method to quantify
token importance, which leverages the
entropy-gradient connection to approximate gradient-magnitude rankings for
token selection. We find that training on the top 20%
tokens ranked by GMTS consistently outperforms
entropy-based
token selection across three
reasoning domains and various model sizes, suggesting that GMTS provides a more fine-grained estimate of
token contribution for RLVR training.
Read the full abstract ▾
Data Structures and Algorithms · Cross-listed from quant-ph
Gate-Efficient Implementation of the Query-Optimal Time-Dependent Hamiltonian Simulation
Boyang Chen, Minbo Gao, Zhengfeng Ji et al. (+3 more)
The query-optimal
algorithm of [CGWZ26] for general time-dependent
Hamiltonian simulation uses $$ q = O\left( \alpha T + \frac{\log(1/\varepsilon)}{\log\left(e + \log(1/\varepsilon)/(\alpha T) \right)} \right) $$ queries to $\mathrm{HAM\mbox{-}T}$ within $\varepsilon$ error for a Lipschitz-continuous time-dependent
Hamiltonian $H(t)$ on $[0,T]$ satisfying $\left\lVert H(t)\right\rVert\leq\alpha$. However, its direct
circuit implementation incurs a substantially larger gate overhead. In this note, we give an implementation of the same
algorithm that retains its optimal query complexity and uses $$ O\left[ q \left( a + \log\left(1 + \frac{T(\alpha + \beta T)}{\varepsilon} \right) \right) \right] $$ one- and two-
qubit gates, where $a$ is the number of block-encoding ancilla
qubits and $\beta$ is the Lipschitz constant of $H$. The main ingredient is an exact dyadic factorization of the ordered update product in the underlying one-query transducer.
Read the full abstract ▾
All authors Boyang Chen, Minbo Gao, Zhengfeng Ji, Tongyang Li, Xinzhao Wang, Shuo Zhou
Computation and Language
REER-PT: Reverse-Engineered Reasoning for Perplexity-Guided Pre-training Data Augmentation
Haoran Que, Jiajun Shi, Ting Huang et al. (+7 more)
As
language-model compute continues to scale, high-quality training data is becoming an increasingly important bottleneck. Conventional next-
token prediction supervises what follows a context but leaves the intermediate
reasoning behind that continuation implicit. We introduce REER-PT, a scalable framework that extends Reverse-Engineered
Reasoning (REER) to raw pre-training data. REER-PT identifies continuations that are difficult to predict but can still be inferred from the preceding context, and inserts concise
reasoning annotations that reconstruct the missing connection between context and continuation. Candidate annotations are generated and refined offline, with perplexity serving as the optimization signal. Constraints on length and target leakage filter out unhelpful or trivial annotations. This sparse transformation preserves the source text and remains compatible with standard next-
token prediction, avoiding online
reasoning rollouts during pre-training. We apply REER-PT to transform a source pre-training corpus into an augmented one. Across augmented-data, original-
token, and selected-continuation comparisons, perplexity reductions range from 0.42 to 7.29, and only about 0.05% of annotation 13-grams appear verbatim in the source text. We then train two 680M-parameter models with the same architecture and training configuration on the source and augmented corpora, respectively. The augmented-data model gains up to 2.07 percentage points on several knowledge and
reasoning benchmarks. Together, the perplexity analysis indicates improved continuation predictability, while the controlled pre-training experiments suggest that this augmentation can improve model performance without changing the standard pre-training objective.
Read the full abstract ▾
All authors Haoran Que, Jiajun Shi, Ting Huang, Renming Pang, Jiaheng Liu, Ge Zhang, Wenhao Huang, Shen Yan, Wei Ye, Shikun Zhang