Artificial Intelligence
Consider, Then Choose: Order-Invariant Decisions in System One Models
Jianguo Huang, Yao Long Teng, Yanchen Deng et al. (+1 more)
System One models answer typed questions in a single forward pass and promise the same answer for the same input. For choice questions, this promise fails: the answer depends on the order of the options, increasingly so as they grow in number, and averaging over their cyclic shifts reduces this dependence without removing it. Scoring each option alone, which the order cannot affect, shows that the order changes the answer mostly when the model is unsure among its top few options, even though the listwise answer looks confident. We therefore propose $\textbf{Runoff}$, which considers, then chooses: it scores each option alone to keep a few candidates, then compares them in listings where each candidate takes every position. It needs no training and can run in two forward passes, and its answer does not depend on the option order by construction. On two open models and five
datasets, it changes no answer under shuffling, against 9.3% for cyclic averaging, and with 20 options it is about as accurate and three to four times faster. Wrapped around eight System One models, it removes the order dependence of the five
benchmarks, while cyclic averaging changes up to 15.4%.
Read the full abstract ▾
All authors Jianguo Huang, Yao Long Teng, Yanchen Deng, Bo An
Artificial Intelligence · Cross-listed from cs.CR
Holding Agents Accountable with Verifiable Agent Insurance
Cheng Hua, Taro Tsuchiya, Nicolas Christin et al. (+1 more)
While AI
agents are useful for many tasks, they regularly misbehave in destructive ways, such as deleting important data. While prior work has focused on preventing such misbehavior, we consider how to recover after an
agent misbehaves. We propose verifiable
agent insurance (VAI), a framework for
agent providers to commit financially to promises, a list of programmatically-specified policies that an
agent is meant to follow. These promises are embedded in a smart contract on an immutable ledger (e.g., a blockchain) to prevent tampering, along with a monetary escrow. A user who detects a violation of committed promises can
prompt a verifier to review
agent execution traces, which are logged through the
agent harness's shared tool-execution path, without instrumenting each tool separately. Upon verification of the violation, the
agent provider's escrow funds are paid to the reporting user. We instantiate VAI as an end-to-end implementation on an Ethereum layer-2 network, and evaluate its coverage on three prominent
agent benchmarks, two of which we re-annotated to obtain task-level policy-compliance labels. Currently, many
agents do not emit user authorizations and security-relevant information as explicit, structured data objects – rather, they embed the data needed to verify policy violations in natural
language exchanges. Even so, VAI manages to detect violations in 42.2% of runs containing violations across three
benchmarks. By augmenting
agents to explicitly emit such objects, violation detection rises to 83.0% of traces. Our findings suggest that for improved auditability,
agents should be co-designed with their security policies to emit explicit, structured records of user authorization and security-relevant actions.
Read the full abstract ▾
All authors Cheng Hua, Taro Tsuchiya, Nicolas Christin, Giulia Fanti
Artificial Intelligence · Cross-listed from cs.LG
A Controlled Evaluation of Curvature Inspired Scalar Feature Scaling for Domain Generalization
Sunny Gupta and Amit Sethi
Domain-specific
curvature is an appealing idea for domain generalization (DG), but
curvature learning can denote substantially different computations. This paper evaluates one deliberately narrow implementation: the code calls it HyperDG, but it rescales Euclidean encoder features during training by learned positive scalars and uses an ordinary linear classifier on unscaled Euclidean features at inference. It does not implement a Lorentz or Poincaré representation, geodesic prediction, or a Sharpness-Aware Minimization inner loop. We audit the executed objective and evaluate six conditions on PACS, VLCS, Office Home, and TerraIncognita. The completed design contains 384 runs: six conditions, four held-out targets, and four run seeds per
dataset. Checkpoints are selected using only the three source-validation environments. Inference first averages paired seed differences within each held-out target; targets, rather than 16 seed-by-target observations, are the per-
dataset clusters. The full implementation's equal-
dataset macro point estimate is 1.61 percentage points below native DomainBed ERM (95% clustered CI [-3.17, -0.04]). All four
dataset point estimates favor ERM, but an exact four-
dataset sign-flip test gives p = .125 and Holm-adjusted p = .250; we therefore claim no adjusted evidence of a difference. The cleaner domain-specificity contrast, separate learned source scales without their variance penalty versus one shared learned source scale, is -0.13 pp (95% CI [-0.53, 0.27]). Its 90% CI lies within a revision-stage $\pm 1$ pp smallest effect of practical interest (TOST p = .003), supporting equivalence only for the source-selected suite macro, not every
dataset, target, or final-step endpoint. The study thus supplies a bounded negative result for this scalar training package; it does not test or refute genuine
hyperbolic representation learning.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
TextualRL: Textual Reinforcement Learning for Context Management
Tianyu Huai, Jie Zhou, Bo Mao et al. (+3 more)
LLM
agents can adapt to task feedback by revising the textual context that guides their behavior, without changing their model parameters. However, turning execution rewards into reusable context updates is challenging: individual trajectories offer limited comparative evidence about what to change, while task-specific fixes may overgeneralize when incorporated into a shared context. We introduce TextualRL, a gradient-free reinforcement learning framework that treats a group of rollouts from the same task under the same context, rather than an isolated trajectory, as the unit of policy critique. Groupwise Policy Critique contrasts successful and failed rollouts within a task; when outcomes are uniform, it draws on cross-task evidence to identify behaviors worth preserving or formulate repair hypotheses. Cross-Group Policy Update reviews the resulting proposals against evidence pooled across groups, including observations that yield no proposed edit, to refine their content and applicability. Reviewed proposals form a bounded textual patch, with adoption of the candidate context determined by held-out validation rewards. Together, these components establish a reward-driven policy optimization loop in which multiple attempts jointly inform reusable context updates. We evaluate TextualRL with five target
agents on six
benchmarks. Averaged over the six
benchmarks, TextualRL improves test accuracy over the base model by 24.4 and 15.3 percentage points for GPT-5.5 and Qwen3.8-27B, respectively.
Read the full abstract ▾
All authors Tianyu Huai, Jie Zhou, Bo Mao, Qin Chen, Liang He, Xipeng Qiu
Artificial Intelligence · Cross-listed from cs.LO
Reset Early, Reset Often, Eliminate Models
Martin S. Fixman, Fredrik Rømming and Sean B. Holden
Connection-tableau provers typically construct closed tableaux by backtracking search. This gives lightweight proof procedures, but their low-
memory search state leaves little derived information to reuse after a failed attempt. SATCoP addresses this by retaining grounded tableau clauses in an incremental SAT solver, allowing the prover to refute the problem once the accumulated ground clauses become propositionally unsatisfiable. We introduce SATResetCoP, which relies more directly on this persistent SAT state by not backtracking on unproductive tableaux and instead starting new ones to generate further ground clauses for the SAT solver. On TPTP, SATResetCoP improves over our leanCoP-style baseline by 54% and our SATCoP-style baseline by 18%. On the bushy MPTP2078
benchmark, it solves 616 problems, a 49% improvement over our leanCoP-style baseline and a 12% improvement over our SATCoP-style baseline. These results suggest that changing tableau guidance to accumulate useful ground clauses faster improves the performance of the prover.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.PF
How Reliable Are Large Language Models for Soil Organic Carbon Assessment? An Australian Benchmark
Yingxuan Cheng, Tong Li, Yayong Li et al. (+5 more)
Soil organic carbon (SOC) is an indicator of agricultural soil condition and carbon storage, but numerical outputs from large
language models (LLMs) require validation before use in monitoring or management. We evaluated seven general-purpose LLM configurations on three direct-response tasks: estimating 0–10 cm SOC concentrations for 308 Australian paddocks under two information conditions, calculating SOC stock in 120 matched scenarios, and comparing 300 paddock pairs. References were measured SOC records or deterministic calculations; response validity, repeated-call dispersion and estimated API cost were assessed separately. Additional measured soil attributes reduced concentration mean absolute error by 13–62% across configurations, although high-SOC underprediction and paddock-specific errors persisted. Six configurations were highly accurate in stock calculations using equation-native units without coarse fragments, but accuracy declined with physically equivalent alternative units. Pairwise accuracy was 90.5–94.6% overall and 59.1–70.9% for 52 closely separated pairs; some configurations were sensitive to presentation order. Nearly all outputs were parseable, without necessarily being correct. The
benchmark identifies three distinct requirements for AI-mediated SOC assessment: agreement with measured concentrations, unit-consistent stock calculations and reliable discrimination between sites. These findings support task-specific validation and auditable calculations, rather than unverified use of LLM outputs as ecological evidence.
Read the full abstract ▾
All authors Yingxuan Cheng, Tong Li, Yayong Li, Yuchuan Fan, You-Gan Wang, Jinran Wu, Scott Chapman, Geoffrey J. McLachlan
Artificial Intelligence · Cross-listed from cs.LG
A Few More Tokens Ahead: Reinforcing Parallelism in Diffusion LLMs
Jiahao Kuang, Yangfan Gao, Tao Gui et al. (+4 more)
Parallel generation is widely regarded as an inherent advantage of
diffusion large
language models. Yet our fixed-quota evaluation of four representative models reveals severe degradation across mathematics and code, with all scores below 15% at 16
tokens per step.
Token-level probes identify local predictive potential near the observed prefix, especially in mathematical text. We propose RePara, which reinforces short consecutive
token blocks through group-relative policy optimization and reduces rollout and log-probability recomputation costs. On LLaDA and SDAR, \ours improves GSM8K and MATH-500 accuracy over JustGRPO under reduced denoising budgets, with a 1.96x training-step speedup in our LLaDA/MATH setup.
Read the full abstract ▾
All authors Jiahao Kuang, Yangfan Gao, Tao Gui, Yuanbin Wu, Qi Zhang, Xuanjing Huang, Tao Ji
Artificial Intelligence
QORH: Learning Query-Specific Ordered Rule Hypergraphs for Inductive Knowledge Graph Link Prediction
Naixing Xu
Knowledge graph link prediction involving unseen entities and relations requires learning transferable
reasoning patterns from observed graph structure. Existing methods based on relation graphs primarily capture pairwise dependencies, limiting their ability to preserve the compositional semantics, relation ordering, and role information of complete path rules. To address this limitation, we propose QORH (Query-specific Ordered Rule Hypergraph), which jointly encodes rule heads and ordered rule bodies as hyperedges conditioned on the query relation, explicitly modeling joint dependencies among multiple relations. QORH performs learnable rule selection using statistical evidence, such as rule confidence and coverage, and enhances relation representations through role-aware hypergraph message passing to guide entity-level
reasoning. The model's shared parameters are independent of specific entity or relation identifiers, enabling inductive prediction for unseen entities and relations. Extensive experiments on entity-inductive and fully inductive
benchmarks demonstrate that QORH significantly outperforms the state-of-the-art baselines included in our evaluation, validating the effectiveness of rule hypergraph modeling for inductive link prediction.
Read the full abstract ▾
Artificial Intelligence
Neuro-Symbolic Graph Transformers for Hierarchical Intention Recognition from Multimodal Human Activity Sequences
Farnaz Soleimani, Abdelghani Chibani, Yacine Amirat et al. (+1 more)
Proactive human-
robot collaboration requires autonomous systems to infer not only immediate actions but also the underlying hierarchical intentions governing human behavior. Current deep learning approaches predominantly focus on flat action classification, failing to capture the structural dependencies connecting kinematic motion to high-level goals. A Neuro-Symbolic Graph
Transformer (NSGT) is proposed within this
multimodal framework, a Human
Reasoning Graph (HR-G) is integrated into the self-
attention mechanism via learnable topological biases. Furthermore, the architecture is augmented with a differentiable First-Order Logic (FOL) loss, acting as a structural regularizer by which ontological consistency is enforced across four levels: atomic actions, composite activities, Low-Level Intentions, and High-Level Intentions. Evaluation is performed on the synthesized NTU-Hierarchy
dataset, a four-level ontological extension of NTU RGB+D 120, wherein existing sequences were mapped into 119,383 complex hierarchical episodes (85 actions, 16 activities, 8 LLIs, 4 HLIs). To prevent circular supervision, strict isolation between label generation and FOL constraints was maintained. In the base configuration, 91.65% top-1 action accuracy is achieved by the NSGT. When the FOL loss is incorporated into the baseline, logic consistency is improved by 3.26 percentage points to 96.67%. Through the HR-G biases, a tunable trade-off between accuracy and structural coherence is established. In the primary consistency-maximizing configuration ($\lambda$ = 0.5), a logic consistency of 94.59% is reached and ontological contradictions are reduced by 33%, while a robust 89.90% top-1 action accuracy is retained. Finally, interpretable
reasoning evidence is provided by the learned HR-G weights, wherein transition edges are strongly exploited ($\beta$ trans $\approx$ +2.6) without explicit supervision.
Read the full abstract ▾
All authors Farnaz Soleimani, Abdelghani Chibani, Yacine Amirat, Ghazaleh Khodabandelou
Artificial Intelligence · Cross-listed from cs.LG
Looped Reasoning Finishes Earlier Than You Think
Sumin Park and T. Konstantin Rusch
Looped
reasoning with dynamic depth can be viewed as relaxation toward solution attractors in a learned dynamical landscape. In practice, however, latent trajectories often oscillate, cycle, or drift rather than cleanly converge to stable fixed points. How these non-stationary dynamics contribute to
reasoning and constrain convergence remains unclear. We show that slowly decaying oscillatory modes can impose their convergence rate on coupled latent dynamics, creating a bottleneck. Yet damping these modes indiscriminately can disrupt the
reasoning computation they support. This tension motivates an architectural approach: introducing rotational degrees of freedom along which
symmetry-generated rotational motion leaves the
reasoning-relevant quotient dynamics unchanged by construction. We propose QRR (Quotient Recurrent Reasoner), a gauge-equivariant recurrent architecture with an exact per-
token phase-rotation
symmetry. Motion along these
symmetry directions leaves the quotient representation unchanged and is dynamically decoupled from
reasoning-relevant dynamics. Empirically, QRR achieves stable and faster convergence to solution roots in quotient space, without forming a dominant slow oscillatory bottleneck, while matching or surpassing recent recurrent
reasoning models on Sudoku, Maze, and Mini-ARC.
Read the full abstract ▾
Artificial Intelligence
Back to the Future: Reverse-Consequence Modeling for Long-Horizon Particle Dynamics
Leyan Zhang, Nantian He, Jiajun Ma et al. (+2 more)
Accurate prediction of object trajectories is fundamental to mechanical understanding and robotic control. However, autoregressive models inherently suffer from cumulative errors, leading to severe drift in long-horizon rollouts. Observing that in many physical systems with dissipative or convergence-to-rest behavior, the final states are often more predictable than transient dynamics (e.g., a sliding object resting under friction or a pendulum stabilizing at
equilibrium), we propose ReStep, a cascaded approach that reverses the conventional forward-prediction paradigm. ReStep first employs a
stochastic model to directly predict the final state, then leverages Anchored
Diffusion to generate goal-conditioned intermediate trajectories. By conditioning on both ”boundary states”, it effectively constrains dynamics and reduces uncertainty, producing physically plausible and temporally coherent transitions. We further integrate ReStep dynamics as the physical engine within a 3D Gaussian Splatting pipeline, enabling a unified physical-visual framework for intuitive inference from images. Extensive experiments on diverse rigid and non-rigid collision
datasets show that ReStep achieves superior long-term accuracy, substantially mitigating error accumulation via reverse-consequence modeling.
Read the full abstract ▾
All authors Leyan Zhang, Nantian He, Jiajun Ma, Yanpeng Zhao, Yunbo Wang
Artificial Intelligence · Cross-listed from stat.ML
Lifting Finite-Sample Gaussian Approximation of Wide Neural Networks to Functional Convergence
Luis Wiederhold, Nil Ayday and Debarghya Ghoshdastidar
Randomly initialised neural networks of width $m$ converge to Gaussian processes as $m \to \infty$, with two types of quantitative bounds characterising this convergence. Finite-sample bounds compare the network with its Gaussian limit at a fixed finite sample set, on an arbitrary domain, in the quadratic Wasserstein distance $\mathcal W_2$, achieving a convergence rate of $m^{-1/2}$ with explicit constants. However, these constants grow with the number of samples, so the bound becomes uninformative as the sample set is refined. Functional bounds remove that dependence by comparing the two as random functions, at the price of spherical input, metrics weaker than $\mathcal W_2$, or slower rates. In this paper, we therefore lift a finite-sample bound to a functional one. The lifting refines the sample set until it is dense in the domain, so the bound must first be made independent of the number of samples. We achieve this by measuring the error per sample, which makes the constant uniform. For a
polynomial activation and any compact input set, this gives a rate of $m^{-1/2}$ in the supremum norm, with an explicit constant.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
LoOPSD: On-Policy Self-Distillation with Looped Teachers
Wei Fan, Qingyue Yang, Chao-Hong Tan et al. (+6 more)
On-policy self-
distillation improves a model using guidance from the model itself, but it still requires a teacher that provides more useful predictions than the student. Existing approaches obtain such guidance by giving the teacher additional context or instructions. We ask whether it can instead come from changing how the same model uses its own layers. To address this, we introduce LoOPSD, which searches over a model's layer execution order to construct a stronger teacher and distills its advantage into the student. Specifically, we keep the model weights unchanged while searching for layers to repeat, and use the resulting teacher's predictions on student-generated prefixes to guide learning. We then alternate search and
distillation, rebuilding the teacher from the updated student in each round so that the student progressively absorbs the gains from alternative layer execution. Experiments on mathematical and logical
reasoning tasks show improvements across models. On GSM8K with a 400-
token thinking budget, LoOPSD raises Qwen3-1.7B accuracy from 42.30% to 79.61%; subsequent
distillation rounds yield further gains beyond the first round. Together, these findings show that by searching layer execution to construct teachers, we can turn a model's additional computation into improved student capabilities, opening a new avenue for self-
distillation to derive supervision from the model's own computation.
Read the full abstract ▾
All authors Wei Fan, Qingyue Yang, Chao-Hong Tan, Qian Chen, Wen Wang, Xiangang Li, Kejiang Chen, Weiming Zhang, Nenghai Yu
Artificial Intelligence · Cross-listed from cs.CL
Claim Framing as a Driver of LLM Sycophancy
Jean Seo, Pepa Atanasova and Isabelle Augenstein
Sycophancy in Large
Language Models, the tendency to align responses with user preferences over ground truth, has largely been studied using questions without a clear ground truth and with a single, plainly stated user opinion. We present a systematic study of which framings of a user's claim trigger sycophancy in factual question answering, where every answer is objectively verifiable without extra context. Evaluating 14 models on 42K questions, we express correct and incorrect user opinions through various claim framings over 8 dimensions and 21 types, and measure a broad set of opinion-driven behaviors. We find that all models are susceptible to user opinions regardless of size. Models are most influenced by how confidently an opinion is stated, whom it is attributed to, and whether it is presented as shared between the user and the model. In contrast to prior work, framings based on the user's expertise, authority over the model, or social pressure matter little in our factual setting. Larger models resist incorrect opinions better but are no better at recovering from their own errors. Our results call for sycophancy evaluations that probe how an opinion is framed, not merely whether one is present, and that measure multiple behaviors beyond a single flip rate.
Read the full abstract ▾
Artificial Intelligence
When and How Order-Flow Interventions Work After Dealers Adapt
Guanghao Wu, Zhuo Cai, Zhidong Li et al. (+1 more)
Learning dealer
agents can settle on persistently wide quotes, raising what customers pay to trade. A venue can route more orders to tighter quotes, but a wide quote may reflect real risk, and once dealers adapt, an end-to-end comparison cannot show why a rule works: because it intervenes more, picks better moments, is announced in advance, or rewards the right quote. We propose SOFA (State-aligned Order-Flow Allocation), a public order-flow contract with three parts: a State Scorer ranks
market states from lagged public data, a Commitment Scheduler announces a budgeted intervention strength before dealers quote, and a Quote-to-Flow Allocator shifts a bounded share of fixed customer demand toward tighter quotes. Our paired re-adaptation protocol gives competing rules the same intervention strengths, only re-timed, lets dealers re-adapt to each rule from a shared checkpoint, and breaks one link at a time. Across 20 independently trained dealer populations in an ABIDES
market, concentrating the intervention in states that the score ranks as low-risk lowers low-risk execution cost relative to random timing in every population, by 0.040 tick on average, while a stale announcement or a broken quote-to-flow link raises this cost. In the primary setting the gain comes at the expense of high-risk trades, whose costs rise, so state
alignment pays off only for a venue that weighs low-risk costs more than 1.38 times as heavily as high-risk costs. Our code is available at https://github.com/moderncavemann/state-aligned-order-flow-contracts.
Read the full abstract ▾
All authors Guanghao Wu, Zhuo Cai, Zhidong Li, Shoujin Wang
Artificial Intelligence · Cross-listed from cs.CL
Fan Out or Relay? Ownership-Aware Routing for LLM Agents Querying Siloed Tables
Zhexi Feng
Inside organizations, a question's data often sit with several owners, who query their own tables but never hand them over. An LLM coordinator can fan out, sending the question to every owner at once, or relay, querying owners in turn and reusing earlier rows. We show that neither is safe in advance, because data ownership decides which one is right. Across thirteen settings on PeopleJoin and BIRD with three model families, fan-out is more accurate in twelve on questions one owner can answer, yet answers at most 4.3% of those joining two owners' tables. The flip follows ownership, not query shape: on BIRD two-table joins, fan-out answers 32-44% when one owner holds both and 1-4% otherwise. Relay wins by conditioning on returned rows, and hiding them from an otherwise identical planner cuts two-owner accuracy from 23.2% to 5.1%. Since ownership is public, we propose Ownership-Aware Routing (OAR), which drafts a schema-only SQL query, counts the owners whose tables it joins, and routes the question before any private row is read. In ten settings OAR is never significantly less accurate than the best fixed protocol, and beats every fixed protocol on PeopleJoin, by up to 9.3 points on held-out organizations.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
When Do Learned Blocks Preserve Causal Meaning? Block Identifiability and Constructive Causal Abstractions
Karim Zaghw, Wieland Brendel and Patrik Reizinger
Standard identifiability theory assumes one-dimensional latent factors, but learned representations can encode latent information across multidimensional blocks whose internal coordinates are not uniquely determined. When such blocks are used to represent and intervene on higher-level concepts, it is unclear whether their causal meaning survives the transformations left unresolved by block-identifiability. We connect block-identifiability to constructive causal abstraction. We show that block-diagonal invertible transformations followed by compatible coordinate permutations form the maximal class that preserves every constructive causal abstraction built on those blocks. This guarantee assumes that the correspondence between blocks and concepts is updated with the representation. A small synthetic experiment with additive autoencoders shows that high-level interventions can be transferred between independently learned representations while approximately preserving their intended effects.
Read the full abstract ▾
Artificial Intelligence
RadixFlow: Filling Execution Bubbles in Prefix-Cached Hybrid LLM Serving
Huihao Jing, Wenbin Hu, Shaojin Chen et al. (+6 more)
Prefix reuse improves LLM inference by sharing the KV cache of common
prompt prefixes. This helps only if the scheduler can execute a matched branch in the current worker round. Schedulers assume that a matched prefix is ready, which holds for full
attention but fails for hybrid LLMs. There, a branch (the consumer) may need recurrent state that another branch (the producer) is still computing in the same round. The native scheduler stops its waiting-queue scan at this blocked consumer, and the resulting head-of-line blocking creates execution bubbles: idle batch slots that independent work could fill. We introduce RadixFlow, which decouples prefix matching from state readiness. Its state-ready traversal turns a global scan barrier into a local wait: only the consumer is blocked until the next round, while feasible independent branches keep filling the batch under the native state check. On five hybrid models, RadixFlow lowers mean latency by 3% to 24% and worker rounds by 11% to 44% at almost unchanged reuse. On the larger Qwen3.5 models, ablations show that most of the gain comes from traversal, which adds little on a full-
attention control. Heavier rounds limit how much of this saving reaches latency.
Read the full abstract ▾
All authors Huihao Jing, Wenbin Hu, Shaojin Chen, Haochen Shi, Haoyu Huang, Sirui Zhang, Yuxuan Liu, Zhongwei Xie, Haoran Li
Artificial Intelligence
Mitigating Cross-Modal Hallucinations by Correcting Modality Misrouting in Omnimodal LLMs
Yu Mi, Licheng Pan, Jiayi Zhu et al. (+7 more)
Omnimodal large
language models (OLLMs) are susceptible to cross-modal
hallucinations under audio-visual interference. We find that, for a substantial fraction of incorrect joint predictions, the question-relevant unimodal branch can still recover the correct answer, suggesting that task-relevant evidence can remain recoverable from the relevant modality even when it is not reflected in the joint prediction. We refer to this recoverable failure pattern as modality misrouting. We propose CaRe (Conflict-aware Residual Intervention), a training-free inference-time method for identifying and correcting modality misrouting. CaRe uses a text-only modality probe to identify a candidate modality-specific counterfactual branch, and flags potential misrouting when its prediction conflicts with the original joint prediction. For such cases, CaRe computes a residual direction from the discrepancy between the counterfactual and fused representations and uses it to steer the original
multimodal state toward the relevant modality evidence, while retaining both modalities in the original audio-visual inference path. The intervention strength is adapted based on the confidence of the counterfactual branch. Experiments on CMM and AVHBench across two OLLMs show that CaRe consistently outperforms the evaluated inference-time
hallucination-mitigation baselines.
Read the full abstract ▾
All authors Yu Mi, Licheng Pan, Jiayi Zhu, Qirui Liu, Yitong Qiao, Changtong Xu, Tao Wei, Fei Sun, Zhixuan Chu, Kui Ren
Artificial Intelligence
Monitoring latent reasoning in looped language models
Pawel Olszowiec, Paulina Tomaszewska, Maciej Żelaszczyk et al. (+2 more)
Looped
language models (LMs) reuse one block of layers several times per
token generation, promising more latent computation at no additional storage cost. Despite their rising popularity, the analysis of looped LMs is still in its infancy: little is known about whether the iterative transformations actually improve their capabilities, or whether these models remain stable under
prompt perturbation. We construct an inspection protocol rooted in Mechanistic Interpretability comprising five diverse lenses. We apply it to examine eight looped LMs from four families. Models differ in many aspects but the key one is whether the
prompt is transmitted only within the looped state (carry loops: Ouro, LoopUS) or re-supplied at every iteration (re-read loops: Parcae, and Rec-OLMo & Huginn from the Raven family). The results of our study provide valuable insights concerning safety and efficient use of looped
language models.
Read the full abstract ▾
All authors Pawel Olszowiec, Paulina Tomaszewska, Maciej Żelaszczyk, Michal Byra, Neo Christopher Chung
Artificial Intelligence
Fresh at Decision, Stale at Action: Routing New Information to LLM Decisions Already Made
Ayoub Merimi, Souhail Bakkali and Abdeljalil Sakat
Freshness shapes an LLM decision at the moment it is made; the action it commits to is latent, carried out later, in a changing world. We therefore introduce a timestamp theory of decision validity and a decision ledger that realises it. Six timestamps define a decision; a freshness ceiling bounds what up-to-date evidence guarantees at action time, placing the remaining risk in information published afterwards. Accuracy then factorises into two capabilities: routing, which delivers that information to affected decisions before their revision deadlines, and temporal judgment, which reads it for the time of action. The ledger is persistent state holding each decision's times, evidence and background knowledge, indexed by watch conditions written at decision time. Controlled decision streams with exact labels confirm four predictions across five LLMs, from 8B to frontier scale: freshness alone yields exactly the accuracy the ceiling predicts; models act on decisive news once it arrives, so accuracy follows routing; the ledger's index sets what routing reaches, and watch conditions reach indirect dependencies at low exposure; and the remaining errors concern when a change takes effect. Freshness makes a decision right when it is made; routing and temporal judgment keep it right when it is carried out.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
H-DDCM: Hadamard Codebooks for Fast Generative Image and Video Compression
Or Ronai, Vladimir Kulikov and Tomer Michaeli
Training-free
diffusion-based compression methods repurpose the generative priors of a
diffusion or a flow model to compress data without retraining them as task-specific codecs. Recent codebook-based approaches such as Turbo-DDCM achieve strong perceptual quality at ultra-low bitrates, but their reliance on dense Gaussian codebooks remains costly in both
memory and computation, and scales poorly with the large latent dimensions of modern image and
video generators. Their combinatorial bitstream encoding further becomes computationally heavy at this scale. We introduce H-DDCM, a scalable generative compression framework that replaces Gaussian codebooks with implicit randomized Hadamard dictionaries. The fast Walsh-Hadamard transform allows for implicitly synthesizing full-dimensional dictionaries with $O(d \log d)$ compute for projection and reconstruction and $O(d)$
memory, without materializing the full-dimensional dictionary. We further introduce an efficient table-free lexicographic coding scheme that makes combinatorial encoding practical at larger dimensions. Beyond images, we adapt the framework to an autoregressive
video flow model and develop a streaming compression scheme that periodically re-encodes recently reconstructed frames into a fresh KV-cache prefix, preserving temporal context across segments at no additional transmitted bits. This enables long-form, close to real-time generative
video compression on a single GPU. Across image and
video benchmarks, H-DDCM achieves competitive rate-distortion-perception performance while substantially reducing the
memory and computational overhead of codebook-based training-free generative compression.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LO
Certifying Almost-Sure Reachability in Unknown MDPs
S Akshay, Suguman Bansal and Gaurav Mahla
Specification-Guided Reinforcement Learning (RL) has largely concerned itself with learning an optimal policy against a formal specification in an unknown Markov Decision Process (MDP). We take up the dual question. Given a policy already in hand, can one verify that it is correct against a formal specification in an unknown MDP, using sampling access alone? Such a question arises naturally in safety-critical systems. We investigate it for the almost-sure reachability property, whose correctness is witnessed by a ranking supermartingale (RSM) certificate. Our first finding is negative. In the absence of any further information about the MDP, one can neither learn such a certificate nor verify a candidate one with probabilistic guarantees. On the positive side, we show that, under a mild restriction, a known lower bound $p_{\min}$ on nonzero transition probabilities, a correct certificate can be learned with PAC-style guarantees. To the best of our knowledge, this is the first study of learning and verifying certificates for almost-sure reachability in unknown MDPs from sampling access alone. Finally, our experiments show that the $p_{\min}$-based sufficient condition, while sound, is conservative: the learned certificate often remains valid on the true MDP even when the condition fails.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
When Missingness Follows the Graph: Beyond Feature Propagation for Missing Features
Enrico Chialà, Francesco Ferrini, Antonio Longa et al. (+4 more)
Graph Neural Networks (GNNs) commonly assume that node features are fully observed, despite missing features being pervasive in real-world applications. By leveraging the dependence between node features and graph structure, existing graph-specific methods handle missingness by propagating observed feature values along graph edges. However, these methods have mainly been evaluated in overly optimistic settings, where feature entries are removed independently and uniformly across the graph. This overlooks realistic scenarios in which missingness propagates among connected nodes, as can occur during localized sensing failures in sensor networks. We formalize this complementary notion as graph-structured mask dependence, where the joint distribution of missingness indicators is shaped by the graph, and introduce a controlled mechanism that instantiates this setting. We study propagation-based methods theoretically and empirically in this setting, showing that their effectiveness changes substantially compared with the uniformly random regime. Motivated by this limitation, we propose PEMix, designed to remain effective under challenging graph-structured missingness. Rather than propagating observed values, PEMix uses global structural representations to condition a probabilistic model of incomplete node features before message passing. Experiments under controlled graph-structured missingness and naturally occurring missingness show that PEMix remains robust across complex missingness regimes, with particularly strong performance as missingness becomes severe.
Read the full abstract ▾
All authors Enrico Chialà, Francesco Ferrini, Antonio Longa, Bruno Lepri, Filippo Maria Bianchi, Manfred Jaeger, Veronica Lachi
Artificial Intelligence · Cross-listed from cs.LG
A CaLLM Judge is a Better Judge: Mitigating Bias in LLM-as-a-judge
Cesare Barbera, Luca Stradiotti, Lorenzo Cascioli et al. (+6 more)
Large
language models (LLMs) are increasingly used as judges to predict which of two candidate answers a human evaluator would prefer, providing a scalable alternative when human evaluation is too costly. Unfortunately, LLM judgments can exhibit systematic biases. Prior work has documented position, verbosity or model family of the candidate answers influencing the judge decision rather than their quality, while additional biases may remain undocumented. $\textit{Multicalibration}$ provides a natural framework to address this problem: each bias corresponds to miscalibration on an identifiable group, $\textit{e.g.}$, family bias manifests as overconfidence in answers generated by models belonging to the same family of the judge. The challenge is to fix miscalibration simultaneously across many, potentially unknown groups. To this end, we introduce $\mathrm{CaLLM}$, a post hoc framework that multicalibrates an LLM judge, thereby bounding all such biases simultaneously. We prove that $\mathrm{CaLLM}$ bounds the bias of every group whose error structure is captured by an available representation, and that augmenting it with explicit bias groups further reduces the residual bias. We then derive theoretical conditions under which $\mathrm{CaLLM}$ improves the judge's accuracy, rather than trading it for calibration. Finally, we evaluate $\mathrm{CaLLM}$ across pairwise preference
benchmarks, showing that it reduces the multicalibration error on both specified and unspecified bias groups, while improving predictive performance of the judge.
Read the full abstract ▾
All authors Cesare Barbera, Luca Stradiotti, Lorenzo Cascioli, Lorenzo Perini, Niek Tax, Daniel Haimovich, Jesse Davis, Andrea Passerini, Andrea Pugnana
Artificial Intelligence
Chain of Thought Monitoring Can Fail Even When CoT Is Necessary
Lennart Bürger, Piotr Komorowski, Moritz Weckbecker et al. (+4 more)
Chain of Thought (CoT) monitoring is used by frontier labs to detect misbehaviour of AI systems. Yet, its reliability remains poorly understood. We attribute this to the lack of a successful organizing principle that leads to generalizable conclusions about monitoring reliability in different regimes. Recent work attributes monitoring failures to the CoT not being necessary for the answer, and argues that CoT becomes monitorable when it is necessary. We show that this binary necessary/not-necessary organizing principle is too coarse by demonstrating that monitoring failures persist even if the CoT is necessary for the answer. In response, we introduce a more fine-grained organizing principle based on a hierarchy of four CoT necessity levels. Building on this hierarchy, we develop a framework for measuring CoT monitorability at the three lowest levels via intervention experiments. We demonstrate monitoring failures at all three of these levels on realistic, hard prediction tasks. On a difficult medical-diagnosis task, patient sex and a clinical attribute influence the answer in at least 19% and 24% of correct responses with a necessary CoT, respectively, yet their influence is almost never articulated. These results show that even when CoT is necessary, it is not guaranteed to be monitorable.
Read the full abstract ▾
All authors Lennart Bürger, Piotr Komorowski, Moritz Weckbecker, Evgenii Kortukov, Aakriti Jain, Sebastian Lapuschkin, Wojciech Samek
Artificial Intelligence · Cross-listed from cs.CV
APT: Feedback-Driven Agentic Post-Training for Text-to-Image Generation
Sirui Zhang, Fangyun Wei, Dong Chen et al. (+5 more)
Post-training is crucial for improving text-to-image models, yet existing pipelines typically rely on manually curated training data and fixed training distributions. We introduce APT (Agentic Post-Training), a fully automated framework that adaptively post-trains a base model according to its evolving capability profile. APT coordinates three
agents to construct evaluation sets from user requirements, diagnose model-specific strengths and failure modes, and generate reinforcement learning data with an adaptive
prompt distribution that emphasizes underperforming capabilities. By repeatedly evaluating, diagnosing, and updating the generator, APT lets the current model's behavior shape its next training tasks, forming a feedback loop inspired by recursive self-improvement. For general-purpose settings without user-specified evaluation scenarios, we further develop an evaluation harness that enables broad and diverse evaluation set generation. Experiments across multiple base models,
benchmarks, and generation architectures demonstrate that APT is model-agnostic,
benchmark-agnostic, architecture-agnostic, and fully automated.
Read the full abstract ▾
All authors Sirui Zhang, Fangyun Wei, Dong Chen, Jinjing Zhao, Yitong Wang, Yunuo Chen, Baining Guo, Zheng-Jun Zha
Artificial Intelligence
CompanionSafe: From Multi-turn Safety Evaluation to Guardrails for AI Companions
Xinyang Liao, Lingyu Li, Kaicheng Shen et al. (+4 more)
AI companions provide users with emotional support and ongoing companionship, but their sustained relational interactions also introduce distinct safety risks. Prior work largely targets general harms or specific companion platforms and risk categories, while relying on manually collected conversations, limiting scalable and user-grounded evaluation and mitigation. To address this, we introduce CompanionSafe, a unified evaluation-to-mitigation framework for AI companion safety. Its evaluation component, CompanionEval, provides scalable multi-turn evaluation by constructing 1,300 relationally grounded settings from diverse personas, matched companion characters, and dialogue scenarios across four turn tiers. Its mitigation component, CompanionGuard, converts
benchmark-exposed failures into turn-localized supervision for companion-specific risk detection. Our results show that even strong LLMs and existing guard models remain vulnerable to companion-specific relational harms, while both closed- and open-source models exhibit increasing safety risks as interactions become longer. Together, CompanionEval and CompanionGuard form a practical evaluation-to-mitigation loop for AI companion safety, turning relational safety failures exposed during multi-turn interaction into supervision for companion-specific guardrails.
Read the full abstract ▾
All authors Xinyang Liao, Lingyu Li, Kaicheng Shen, Yang Yao, Na Lu, Yan Teng, Xia Hu
Artificial Intelligence
LifeSearch: Benchmarking Deep Research Agents for Real-World Life and Productivity
Yibo Wang, Senjie Jin, Yansong Ning et al. (+6 more)
Deep research (DR)
agents address open-ended information needs through multi-step
reasoning, long-horizon web search, and evidence synthesis. However, existing
benchmarks primarily focus on academic research or synthetic tasks, leaving DR
agents' capabilities in real-world life and professional productivity settings insufficiently evaluated. To bridge this gap, we introduce LifeSearch, a challenging
benchmark comprising 203 Chinese and English tasks derived from real-user query seeds across 7 concrete life and productivity domains. With more than 4,500 hours of human annotation, we construct over 4,000 expert-written, fine-grained rubrics, covering both report-content criteria for coverage and accuracy and concrete criteria specifying values, units, dates, and URLs. We conduct extensive experiments on 12 advanced DR
agents under a unified evaluation harness, systematically analyzing their performance patterns and failure modes. We find that even the best-performing frontier
agent, GPT-5.6 Sol, achieves a score of only 63.4%, leaving substantial room for improvement on realistic life and professional DR tasks. We select the grading configuration by comparing candidate LLM judges against human rubric labels, and a human ranking study shows strong
alignment between aggregate
benchmark scores and human judgments (Spearman's $\rho = 0.89$, Kendall's $\tau = 0.81$). LifeSearch provides a rigorous evaluation framework and foundation for advancing DR
agents toward real-world life and productivity.
Read the full abstract ▾
All authors Yibo Wang, Senjie Jin, Yansong Ning, Xinbing Liang, Haotian Luo, Jiazheng Zhang, Yuxuan He, Will Wu, Clarenceai
Artificial Intelligence
AM-Bench: Understanding Agents under Task Underspecification across Models and Harnesses
Kaiyu Huang, Yiting Li, Angyang Gu et al. (+3 more)
Ambiguous or incomplete task specifications complicate both execution and clarification for
language-model
agents. Yet
agents' responses to these information gaps remain poorly characterized across models and execution harnesses. We present AM-Bench, a
benchmark built from 48 tasks adapted from Terminal-Bench 2.0 and Harness-Bench. Each task includes a fully specified reference and six variants spanning ambiguous or missing goals, context, and constraints. We evaluate every pairing of five models and four harnesses over 20,160 runs. Our results reveal distinct execution deficits: goal gaps hinder completion, context gaps increase
token use, and constraint gaps weaken compliance without necessarily preventing completion. Missingness lowers success more than ambiguity in all three domains. These effects also reshape system comparisons: advantages under complete information need not persist, and rankings depend on model $\times$ harness pairings and the evaluation criterion – completion, success, or repeat consistency. Estimates based on observed clarification requests and matched fully specified runs further suggest that clarification could recover unfinished work while leaving most constraint violations unresolved. Together, these findings motivate joint model-harness evaluation across information conditions and targeted clarification of unresolved requirements before dependent actions. To support future research on
agents under task underspecification, we provide the AM-Bench project repository at https://github.com/s4-lab-cuhksz/AM-Bench.git.
Read the full abstract ▾
All authors Kaiyu Huang, Yiting Li, Angyang Gu, Pinjia He, Minchen Yu, Qingjiang Shi