Artificial Intelligence
Meta-ethics and AI: exploring the novel meta-ethical questions in the era of AI
Shang Lu
With the development of artificial intelligence (AI), the landscape of meta-ethics, which has largely centred on human ethics, faces pressures that may significantly reconfigure it. In particular, if future AI systems were to exhibit sufficiently integrated capacities for moral
reasoning, moral intentionality, and moral reflection, novel meta-ethical questions would arise concerning what I call "AI's own ethics", as distinct from ethical principles merely imposed on AI by human designers. This paper offers a conditional and methodological framework for identifying the questions that would emerge if such AI systems were to arise. On that basis, the paper distinguishes four domains of meta-ethical inquiry in the era of AI: questions about the nature of human ethics from the human perspective; questions about the nature of AI's own ethics from the human perspective; questions about the nature of human ethics from the AI perspective; and questions about the nature of AI's own ethics from the AI perspective. The paper then considers how some existing mainstream meta-ethical theories (such as cognitivism and non-cognitivism, error theory and success theory, relativism, and objective realism) might illuminate these domains, while arguing that many familiar human-centred formulations of those theories may not transfer straightforwardly to AI cases without substantial revision. The overall conclusion is that the emergence of AI's own ethics would place significant pressure on current frameworks and may require substantial refinement, reconstruction, or reconceptualisation.
Read the full abstract ▾
Computer Vision
FORGE: Forward-Only Test-Time Adaptation for Integer-Only Vision Models on Microcontrollers
Muhammad Rehan, Haider Ali, Muhammad Ali Munir et al. (+1 more)
Vision models deployed on microcontrollers (MCUs) are quantized to integer-only arithmetic and run in inference-only runtimes that do not carry the machinery backpropagation needs: the standard tool for adapting a model to the distribution shift (sensor noise, blur, lighting) it meets in the field. Existing forward-only test-time adaptation (TTA) methods either run only on server- or edge-GPU-class models (not true microcontroller integer execution), or require the batch-normalization (BN) layers that integer deployment fuses away. We present a forward-only TTA method that operates on deployed, BN-folded, integer-only convolutional networks. The key observation is that fusing BN into the preceding convolution, a mandatory step for integer inference, destroys the statistics that normalization-based adaptation relies on. We restore adaptation by re-normalizing each folded convolution's per-channel output to its clean training statistics, using only forward-pass estimates. The method (i) recovers most of gradient-based TENT's accuracy gain (+20.9 vs. +24.9 points) and matches forward-only BN adaptation, while being the only method that runs on a folded integer-only model; (ii) needs to adapt only 3 of 21 layers (selected without seeing the test corruptions) to recover 93% of the benefit; (iii) survives single-sample streaming with a batch-size-scaled momentum; and (iv) generalizes across three
datasets (up to 200 classes) and two architectures. We validate bit-exact int8 convolution execution and deploy on an ESP32-S3, where, measured with a Nordic PPK2 power profiler, the forward-only adaptation (a lightweight fp32 recalibration around the int8 convolutions) costs only 8.3 mJ (6.8% of inference energy) and 21.9 ms on the deployed SIMD-optimized model: forward-only adaptation is cheap on a real microcontroller.
Read the full abstract ▾
All authors Muhammad Rehan, Haider Ali, Muhammad Ali Munir, Moaz Amjad
Computational Geometry · Cross-listed from math.CO
A Proof of Albertson's Conjecture
Ankan Sadhu
Albertson's
conjecture states that every graph of chromatic number r has crossing number at least that of the complete graph K_r. We prove the
conjecture for all r. The proof combines new clique-sensitive edge bounds for critical graphs, maximum-clique sampling, and a reserved immersion construction. For graphs of order close to r, we construct edge-disjoint routes while preserving a complete bipartite subgraph whose forced crossings compensate for those introduced when the immersion is smoothed into a drawing. For larger orders, we derive explicit edge bounds using independent-triple deletion and structural properties of critical graphs, then combine them with sampling inequalities that account for crossings within a maximum clique. The remaining numerical inequalities are certified using exact rational arithmetic, with a reproducible certificate and standalone Python verifier.
Read the full abstract ▾
Machine Learning
Reinforcement Learning and Rule-Based Peer-to-Peer Pricing in Residential PV-BES Communities
Pablo Benalcazar, Maciej Kalka, Wilian Guamán et al. (+1 more)
This paper compares rule-based and learning-based pricing mechanisms for peer-to-peer (P2P) electricity trading in residential photovoltaic communities. The rule-based
benchmarks comprise bill-sharing as an ex post allocation mechanism, the mid-
market rate, and supply-demand-ratio pricing. The reinforcement-learning (RL) formulation is implemented through a Deep Q-Network and evaluated under multiplier-based and learnable SDR-shaped pricing, with a fixed-parameter SDR variant as a non-learning control. Performance is assessed through community savings together with complementary financial and operational indicators. In the base PV-only configuration, the rule-based
benchmarks outperform the best RL policy. With battery energy storage, evaluated for the RL policies only, community savings under the best RL policy increase from EUR 734.23 to EUR 978.52. Across the learning-based modes and in both configurations, SDR-shaped pricing outperforms the multiplier-based parameterization considered. The results indicate that rule-based pricing remains highly competitive wherever the two families are compared directly, and that storage substantially improves the learning-based outcomes under this accounting, while the distribution of benefits remains heterogeneous across households.
Read the full abstract ▾
All authors Pablo Benalcazar, Maciej Kalka, Wilian Guamán, Jacek Kamiński
Machine Learning
A Survey on Self-Improving Test-Time Intelligence: Feedback-Driven Adapting, Learning, and Scaling at Inference
Shuaicheng Niu, Guohao Chen, Yaofo Chen et al. (+14 more)
The ability of AI systems to improve their behavior during deployment is becoming increasingly important. As inference moves beyond the static execution of a fixed trained model, a growing body of work studies how models can refine their behavior on the fly by exploiting test-time information and additional computation. These developments have largely evolved along two directions: methods that modify the model's state using test-time signals, and methods that improve predictions through extra inference-time resources such as more sampling and tool use. However, these directions are often studied in separate communities with different terminology, making their connections harder to see. In this survey, we present feedback-driven Test-Time Intelligence (TTI) as a unified perspective for understanding such deployment-time improvement. We use this view to relate test-time adaptation, test-time learning, and test-time scaling, highlighting both their distinctions and their growing overlap in hybrid systems. This unified framework helps connect previously fragmented ideas and provides a clearer conceptual foundation for studying inference-time self-improvement. We review major methodological paradigms, representative applications, and open challenges across
vision,
language,
multimodal learning, generative models, robotics, and healthcare. Our goal is to provide a coherent foundation and research roadmap for the study of self-improving AI systems at test time.
Read the full abstract ▾
All authors Shuaicheng Niu, Guohao Chen, Yaofo Chen, Zhiquan Wen, Jinwu Hu, Zeshuai Deng, Deyu Chen, Shuhai Zhang, Renjie Chen, Zihao Lian, Shoukai Xu, Gang Dai, Yunbei Zhang, Wei Luo, Yifan Zhang, Mingkui Tan, Cheng Deng
Cryptography and Security
Skill-as-API: Confidential Multi-Agent Coordination for Agentic Software Engineering
Ziwei Zhao, Yu Gu, Haojun Liang et al. (+2 more)
AI coding
agents are evolving from solitary tools into collaborative teammates that discover and invoke one another's specialized skills. But the coordination channel itself can leak a skill's intellectual property. Protocols such as MCP and A2A run implementations server-side, yet they still publish each skill's description and typed schemas to every peer, offer no way to hide a skill's existence, and cannot guarantee that a wrapped system
prompt stays off the wire. Application-layer
privacy filters help, but act only after the model has decided to emit sensitive text. We take a complementary, protocol-layer route: Skill-as-API, a coordination protocol whose public view of a skill is limited to its name, description, typed input/output schemas, and trust tier. The skill body is closure-captured in the owner's process and never crosses the wire. Four layers add access control and narrow the
prompt-injection surface structurally rather than by filtering content. We provide an open-source Python implementation over XMTP with 1.8-2.9 s cross-continent hot-reconnect latency, and a software-engineering case study in which three
agents coordinate a pull-request review while each retains ownership of its proprietary analysis
prompts.
Read the full abstract ▾
All authors Ziwei Zhao, Yu Gu, Haojun Liang, Chen Zhang, Xizhi Ding
Machine Learning
Sim2Signal: Sim-to-Real Benchmarks for Traffic Signal Control
Ferdous Al Rafi, Susrik Mukherjee, Latika Liladhar Dekate et al. (+6 more)
Reinforcement learning achieves strong traffic signal control performance in simulation, yet policies trained in simulators often fail once deployed in the real world, a failure known as the Sim-to-Real gap. When RL is applied to traffic signal control, this gap arises from several sources: sensing, action execution, traffic dynamics, and the control objective. Their relative impact and the reliability of existing Sim-to-Real mitigation methods remain insufficiently understood, and the field lacks a standard
benchmark for systematically measuring the gap and evaluating mitigation methods. We present Sim2Signal, a
benchmark that decomposes the Sim-to-Real gap into observation, action, transition, and reward gaps, corresponding to mismatches in the four components of the underlying MDP, and induces each gap in isolation under a shared protocol. We evaluate 18 mitigation methods on 2 base controllers, across 33 gap settings and 10 calibrated networks built from 5 real-world locations. We find that direct transfer consistently degrades performance across all four gap sources, but the severity of the degradation does not predict the effectiveness of mitigation. Instead, mitigation effectiveness depends strongly on the network and gap setting: outside the action gap, a method that helps in one case may fail in another. The most effective methods generally estimate what the gap changes, rather than make the policy insensitive through domain randomization or invariant representations. Our code is available at https://github.com/DaRL-LibSignal/Sim2Signal
Read the full abstract ▾
All authors Ferdous Al Rafi, Susrik Mukherjee, Latika Liladhar Dekate, Jennifer Yawa Lavoe, Huaiyuan Yao, Shlok Mohanty, Longchao Da, Xuesong Zhou, Hua Wei
Machine Learning · Cross-listed from stat.AP
Random Forest-Informed Cellular Automaton for Large-Scale Wildfire Spread Modelling
Siyu Chen, Esha Saha and Hao Wang
Accurate large-scale wildfire spread modelling requires models that capture both the environmental conditions associated with fire occurrence and the local dynamics of fire propagation. We propose a three-stage framework that combines a Random Forest (RF) model with a cellular automaton (CA). First, an RF model trained on the 2021 Canadian fire season estimates daily pixel-level fire-occurrence probabilities. Second,
quantile gradient boosting models provide optional spread-rate priors for sensitivity analysis. Third, an RF-informed CA combines the RF probability layer with neighbourhood-driven spread on a 5 km grid. The RF model achieved AUC values of 0.725–0.795 on the 2022–2024
datasets, while the RF-informed CA achieved substantially higher spatial overlap than the evaluated CA-only baselines in the 2023 simulation. A higher-resolution simulation provides an additional qualitative assessment of local spatial errors. These results suggest that combining RF-derived probabilities with local CA spread can improve large-scale wildfire simulations under the tested conditions.
Read the full abstract ▾
Machine Learning
CliffRank: A Dual-Branch Framework for Activity-Cliff Ranking Prediction
Kewei Li, Rongying Zhang, Peiyu Yang et al. (+4 more)
Activity-cliff ranking remains difficult because local structural changes can cause large activity differences, while high-quality data that resolve the underlying mechanisms remain limited. To use available activity labels more effectively, we combine absolute-activity regression with ranking-consistency learning. CliffRank trains two parallel predictors with mean squared error, a thresholded listwise loss, and Pairwise Preference Consistency (PPC), which aligns relative ordering in the preference-probability space. On three antimicrobial peptide
datasets, CliffRank with ESM2-t12 achieved the highest mean Spearman correlation of 0.5393 and mean Recall@50 of 21.4, although the leading method varied across individual
datasets. On three small-molecule
datasets, CliffRank with PNA, where PPC was activated after 120 epochs, achieved the highest mean Spearman correlation of 0.6890, while its mean Recall@50 of 30.4 matched that of ACANet-PNA. The PPC results also define its practical limits. Asymmetric initialization improved the MolCLR-GIN averages but did not improve every target. For PNA without pretrained weights, delayed PPC improved selected metrics, but no schedule was best for both mean Spearman correlation and mean Recall@50. Future work should evaluate more targets and antimicrobial peptide systems, develop adaptive PPC schedules, and incorporate
protein or membrane context when available.
Read the full abstract ▾
All authors Kewei Li, Rongying Zhang, Peiyu Yang, Zhongjian Wang, Qiuchen Zhao, Lan Huang, Fengfeng Zhou
Cryptography and Security
Ranked by the Matcher: A Reproducibility Audit of Knowledge Graph Extraction from Threat Reports
Safayat Bin Hakim and Houbing Herbert Song
Security teams and researchers choose knowledge-graph extraction tooling for threat reports on the strength of published triple-F1 scores, yet those scores depend on how predicted triples are matched to gold annotations. We could reimplement the stated matching rule for only five of twelve inspected systems. Re-scoring ten system outputs on shared documents under eight protocols reverses eleven of forty-five pairwise orderings; one fixed prediction set spans 0.16–0.70 F1. On an external, human-adjudicated set, no mechanical matcher—lexical,
embedding, or entailment—agrees with the reviewers more than seven times in ten; an LLM judge agrees far more often. To separate component effects from matcher rewards, we build CTIForge, whose deterministic validation layer can vary while extraction is held byte-identical. Across seven tested deployment configurations, no hosted backbone loses precision under validation and every offline one does. Backbone, decoding, and prompting covary across those configurations; on the one backbone we could serve both ways, serving alone reproduces the split. It coincides with a roughly 2.8-fold increase in actions explicitly disputing entity type, consistent with hand-written rules encoding the conventions of the extractor against which they were developed. We release the pipeline, protocol suite, and per-triple audit records.
Read the full abstract ▾
Software Engineering
Barriers to Using Static Application Security Testing (SAST) Tools: A Literature Review
Zachary Wadhams, Clemente Izurieta and Ann Marie Reinhold
Developers face a challenging problem with no clear solution. Modern software breaches can wreak havoc on businesses and individuals alike. With code vulnerabilities being a leading cause, securing applications must be a priority for developers. Static Application Security Testing (SAST) has the potential to harden applications by assisting in the identification and resolution of security vulnerabilities. Despite this, many development teams have not adopted SAST tools into their environment. In this paper, we survey the recent literature to uncover why some developers are apprehensive towards SAST and identify what specific problems they encounter when using it. We found a variety of usability problems developers face when using SAST. Some are inherent of the tool and ultimately require some level of developer investment while others are tool shortcomings that SAST tool creators must address. Ultimately, we argue that in order to drive widespread adoption and consistent SAST usage, developers will need to embrace that some investment is required. Simultaneously, developers will be more likely to integrate SAST tools into their workflows if the creators of SAST tools simplify many aspects related to tool usage. Surmounting the primary obstacles preventing the adoption of SAST requires full consideration of both the technical and human factors.
Read the full abstract ▾
Cryptography and Security
Private Computation Space: Experience with Trusted Multi-Cluster Federated Learning for Agriculture
Shuangyu Lei, Muhammad Salman Abid, Jacob Belding et al. (+17 more)
Artificial Intelligence has shown to help improve agricultural practices, yet adoption remains limited: 69% of U.S. farmers have
privacy concerns with sharing their data, and these concerns must be addressed before adoption is widespread. While
Federated Learning has been demonstrated to protect
privacy at scale for other sectors, deploying a system for agriculture comes with its own set of challenges; the problem necessitates a system that can protect farmer data and identities while preserving model utility, runs on commodity hardware, and is resilient to fragile rural infrastructure. To address these concerns, we introduce the Private Computation Space (PCS), a deployed, open-source Machine Learning system to provision and process farmer data securely. We design a system tailored to an agricultural setting, with multi-cluster orchestration for reliability in rural areas with asynchronous
Federated Learning (FL), Differential
Privacy (DP), and Trusted Execution Environments (TEEs), to allow farms to participate in the framework while keeping their data private. We evaluate the system on two deployed workloads: monitoring nitrogen with living plant sensors in NY for six months and predicting evapotranspiration from weather stations in CA for ten months. Our evaluation finds a Dice Similarity Coefficient (DSC) of 0.71 and $R^2$ accuracy of 0.84 for the respective workloads, improving the worst single-site model accuracy by 22.4% and 9.1%, respectively, while preserving
privacy.
Read the full abstract ▾
All authors Shuangyu Lei, Muhammad Salman Abid, Jacob Belding, Sam Mosher, Manushi B. Trivedi, Shivranjani Baruah, Liam Wickes-Do, Andrew Anderson, Braulio Dumba, Alyssa Whitcraft, Ritvik Sahajpal, Sijin Li, Kelly Robbins, Michael Gore, Margaret Frank, Steven Wolf, Liz Jones, Abraham Stroock, Kaitlin Gold, Hakim Weatherspoon
Information Theory
Solomonoff Induction and Singular Integrals
Will Troiani and Daniel Murfet
The Solomonoff distribution $M$ assigns an a priori probability to a finite binary string $z$ by summing over all programs whose output begins with $z$, weighting a program of length $\ell$ by $2^{-\ell}$. Thus, likely strings are those with many short explanations. This appears to be a purely discrete notion of complexity. However, Riemann sums are also countable. We show that the sum defining $M$, suitably reorganised, contains Riemann sums approximating the
Bayesian evidence of any computable statistical model. These evidence integrals are singular integrals whose asymptotics are governed by Singular Learning Theory and, through it, by invariants of algebraic geometry. Concretely, for every computable
Bayesian model, we construct a single monotone Turing machine whose induced semimeasure agrees with the evidence $Z_n$ up to a uniform multiplicative constant. If the model also satisfies the hypotheses of Watanabe's free-energy asymptotics, then a sample $X^n=X_1\cdots X_n$ drawn i.i.d. from the true distribution satisfies $-\log M(X^n) \le nL_n(w_0)+\lambda\log n-(m-1)\log\log n+O_{\mathbb{P}}(1)$, where $L_n$ is the empirical loss, $w_0$ is an optimal parameter, $\lambda$ is the learning coefficient, and $m$ is its multiplicity. Thus the learning coefficient, a
geometric measure of model simplicity, appears within the Solomonoff distribution as the coefficient of $\log n$ in an upper bound on code length.
Read the full abstract ▾
Machine Learning · Cross-listed from astro-ph.IM
Amortized Opacity Marginalization Improves C/O Interval Calibration for Brown-Dwarf Retrievals
Kellen Heraty
Molecular line lists disagree at a level that measurably shifts retrieved C/O, so
retrievals conditioned on a single list omit a dominant systematic from their error bars. Classical marginalization re-runs a full
retrieval under K opacity realizations per object. We move that cost into simulation: while generating the training set we randomize opacities (smooth multiplicative
Fourier fields in log(nu) plus a discrete line-list mixture, under a deliberately broad prior informed by measured inter-list differences), so a neural posterior
estimator learns an already-marginalized posterior. On perturbed held-out spectra (n=2048) a standard NPE covers nominal 90% C/O intervals 43.3% of the time against 82.4% for a compute-matched marginalized network; three-seed control ensembles reach 93.2% on clean data but 61.4% under perturbation, against 89.4% marginalized, isolating the deficit as opacity-induced (TARP joint expected-coverage deviation 0.005 against 0.035 for a single control network). An axis ablation traces the gain to the continuous field (45.4% for the discrete swaps alone, 79.3% for the field alone). In simulation, real JWST bad-pixel masks with median filling cut the marginalized ensemble's C/O coverage from 0.894 to 0.683; an ensemble retrained with mask augmentation holds 0.918 under the full deployment preprocessing (n=1024). We apply the networks to one pipeline-combined JWST/NIRSpec G395H spectrum each of 14 late-T and Y
dwarfs. The recommended mask-augmented ensemble returns C/O medians between 0.24 and 0.62 and contains the Hood et al. (2024) value of 0.53 for the T8
benchmark 2MASS J0415-0935, which every fixed-opacity control network excludes. With 90% intervals spanning about 0.43 of the prior width, this is a consistency check, not a validation.
Read the full abstract ▾
Computer Vision
Uncovering Understanding-Generation Synergy in Native Unified Multimodal Models: From Representation, Task to System
Penghao Wu, Haiwen Diao, Weichen Fan et al. (+3 more)
While unified
multimodal models (UMMs) jointly perform visual understanding and generation within a single model, functional unification does not guarantee learning synergy: the two objectives may reinforce each other, compete for capacity, or merely coexist. We investigate their relationship at the representation, task, and system levels in a controlled, structurally native setting without pretrained
vision priors. At the representation level, we find that each objective provides useful signal to the other: generation enriches the visual features learned for understanding, while understanding strengthens
vision–
language alignment for generation. However, when both objectives are forced through the same computation path, one tends to dominate. A task-decoupled architecture that specializes conflicting visual computation while preserving semantic interaction avoids this asymmetric degradation. At the task level, through three case studies, we find positive bidirectional transfer when understanding and generation tasks rely on shared knowledge. At the system level, we show that an end-to-end UMM outperforms a matched planner–executor pipeline on complex tasks that explicitly require both image understanding and generation. Together, these results show that the value of UMMs extends beyond a unified interface: appropriate specialization, shared task knowledge, and end-to-end optimization can turn coexistence into synergy.
Read the full abstract ▾
All authors Penghao Wu, Haiwen Diao, Weichen Fan, Lewei Lu, Dahua Lin, Ziwei Liu
Computational Complexity · Cross-listed from quant-ph
Depth-1 expanders on the unitary group and applications
Anurag Anshu, Shankar Balasubramanian, Jonas Haferkamp et al. (+2 more)
We construct a constant-degree and constant-gap
quantum expander on $n$
qubits where each
unitary can be implemented by a depth-$1$ and 1D
circuit of Pauli or CNOT gates. We provide two applications of this expander. First, we use it to construct a family of frustration-free 1D
Hamiltonians whose ground states obey the
entanglement-gap relation $S = \Theta(\Delta^{-1/2})$; this is believed to be optimal, but achieving it had been open. Second, we use it to provide a streaming protocol that tests for closeness to a class of 1D volume-law entangled states. Moreover, we extend our
quantum expander to a constant-degree and constant-gap expander on the
unitary group where each
unitary is a single $T$ gate, a single $T^{\dagger}$ gate, or a depth-$1$ Clifford
circuit. This implies that a random sequence of
unitaries from the expander yields a gapped walk on a dense subgroup of the
unitary group. This improves upon previous work by Bourgain and Gamburd which did not control the dependence of the gap on the dimension.
Read the full abstract ▾
All authors Anurag Anshu, Shankar Balasubramanian, Jonas Haferkamp, Aram W. Harrow, Xinyu Tan
Computation and Language
Beyond Scores: Understanding LLM-as-a-Judge Mechanisms in Summarization Evaluation
Himil Vasava and Ming Jiang
LLM-based evaluators of natural
language generation (NLG) quality are widely deployed as scoring tools and as automated training signals, yet the internal procedure by which they assign a rating remains poorly understood. We investigate this procedure mechanistically through an eight-attack perturbation taxonomy across the Readability and Adequacy dimensions of NLG quality, a generation pipeline that produces paired clean and corrupt summaries with controlled error intensity and explicit
token-level modification maps, and a four-experiment battery of causal tracing, logit-lens vocabulary projection, and
attention-head knockout applied to Themis (Llama-3-8B) and Prometheus (Mistral-7B). Both evaluators implement a structured, coherent evaluation pipeline operating in two stages: below layer 15,
attention performs local error comparison and routes the result to the final input position; above it, the MLP cascade integrates the signal and writes the rating, with the decision crystallizing in the residual stream at a sharp late layer (L = 26 on Themis, L = 25 on Prometheus). Furthermore, a base-model control at the same scale (Llama-3-8B) reproduces the routing architecture and crystallization but not the stage separation, isolating the two mechanisms that fine-tuning specifically installs, suppression of below-L15 MLP contribution at the last position and a two-layer advance of the crystallization depth, indicating that fine-tuning sculpts an existing substrate rather than building the pipeline from scratch. We release the source code and data at https://github.com/himil-v/judge-mech
Read the full abstract ▾
Software Engineering
Efficient SWE Agent Benchmarking via Trajectory-Aware Evaluation
Kefeng Duan, Dewu Zheng, Yanlin Wang et al. (+7 more)
Evaluating software engineering
agents on realistic
benchmarks is costly, since each task may require multi-step code exploration, modification, and test execution. Existing efficient evaluation methods select representative subsets to estimate full-
benchmark performance, but are largely result-only: they fit historical pass/fail response
matrices or static task semantics, discarding how
agents solve problems. We propose PTA-IRT, a Privileged Trajectory-Aware Item Response Theory framework that fuses process and outcome signals. Historical execution trajectories supply process-level evidence beyond pass/fail, such as explored context, attempted edits, and solving paths, which PTA-IRT uses as privileged information for calibration subset selection and ability estimation. Under low calibration budgets, PTA-IRT consistently outperforms prior IRT baselines on score and ranking recovery across four SWE
benchmarks. Code and data are publicly available at https://github.com/DeepSoftwareAnalytics/PTA-IRT.
Read the full abstract ▾
All authors Kefeng Duan, Dewu Zheng, Yanlin Wang, Xiwen Wang, Ensheng Shi, Xilin Liu, Yuchi Ma, Jiachi Chen, Mingwei Liu, Zibin Zheng
Software Engineering
Adaptive Critical Token-Aware Retrieval for Repository-Level Code Generation
Kefeng Duan, Dewu Zheng, Yanlin Wang et al. (+8 more)
The repository-level code generation task requires synthesizing code that satisfies task requirements while remaining consistent with the target repository context. Since real-world repositories often exceed the input length limits of LLMs, existing approaches commonly adopt
retrieval-augmented generation (RAG) to provide repository-specific context. Despite improving repository-context
retrieval, existing methods typically provide context as task-level support, without explicitly identifying the critical
tokens that require fine-grained repository context during generation. During the autoregressive generation process of LLMs, errors often concentrate at a small number of decisive positions: once such
tokens are generated incorrectly, subsequent code may follow an incorrect semantic path and eventually lead to functional failure. We refer to these positions as "critical
tokens". In this paper, we propose ACToR, an adaptive critical
token-aware
retrieval framework for repository-level code generation. ACToR identifies critical
tokens during generation and triggers targeted
retrieval on demand to provide repository context at these decisive positions. In addition, we design a position-aware weighting method for dense retrievers to prioritize context that is more informative for generation. We evaluate ACToR on two representative repository-level
benchmarks, RepoExec and CoderEval. Experimental results show that ACToR consistently outperforms state-of-the-art methods, achieving relative improvements of 8.4% on RepoExec and 15.4% on CoderEval. Beyond performance gains, we systematically quantify the impact of critical
tokens, revealing their central role in major generation failures and highlighting the necessity of targeted
retrieval strategies. We provide the code and data at https://github.com/DeepSoftwareAnalytics/ACToR.
Read the full abstract ▾
All authors Kefeng Duan, Dewu Zheng, Yanlin Wang, Terry Yue Zhuo, Mingwei Liu, Jianxing Yu, Jiachi Chen, Ensheng Shi, Xilin Liu, Yuchi Ma, Zibin Zheng
Computation and Language
CordisBench: Can Language Models Reason About Component Lifecycles in Dynamic Agent Harnesses?
Damien Sileo and Dimitri Kachler
Dynamic
agent harnesses let
language models change the software that shapes their own execution. This flexibility brings a new
reasoning burden: a local plugin change can propagate through dependencies and cleanup. We introduce CordisBench, a 1,200-question
benchmark of this lifecycle
reasoning. It combines a controlled formal setting with programs executed against Cordis, a runtime that manages component dependencies and cleanup, and asks models to identify affected components, predict state after a specified teardown order, determine which conditions hold under all or some orders, and choose reconfigurations that succeed when executed. Across these tasks, we evaluate three efficiency-oriented models at low
reasoning effort with 2, 4, 8, 16, 24, or 32 relevant interactions, using deterministic task-specific scoring. Models usually handle small systems well but grow less reliable as more interactions become relevant, especially when predicting final state and when
reasoning across teardown orders. Additional inference effort recovers marked gains for some models. The cost is nontrivial: on our 16-interaction subset, GPT-5.6 Luna uses nearly 3,000
reasoning tokens per question at medium effort. For these controlled instances, that cost is avoidable: an independent finite reference semantics agrees with Cordis execution on every observation and action outcome used for scoring across all 528 executable questions.
Read the full abstract ▾
Computer Vision
UI-VISA: U-Net Initialized Vascular Image Segmentation Architecture
Asees Kaur, Suzanne S. Sindi and Erica M. Rutter
Accurate
segmentation of vascular structures in digital subtraction angiography (DSA) images remains challenging due to the thin, elongated, and branching nature of blood vessels. Pixel-wise deep learning approaches such as U-Net achieve strong general-purpose
segmentation performance but often produce fragmented or discontinuous predictions in fine vascular regions, since they do not explicitly enforce structural connectivity. Region growing
algorithms preserve spatial context and topological continuity, but are highly sensitive to seed point initialization and can be computationally expensive. We propose UI-VISA (U-Net Initialized Vascular Image
Segmentation Architecture), a hybrid pipeline that combines the complementary strengths of both approaches. UI-VISA uses U-Net's foreground predictions as informed seed points for a CNN-guided region growing
algorithm, which then iteratively refines the
segmentation by enforcing local connectivity and recovering fine vessel details that U-Net alone tends to miss or over-predict. We evaluate UI-VISA against standalone U-Net and a prior region-growing-based method (VISA) using 5-fold cross-validation on 26 DSA images. UI-VISA achieves the highest mean Dice and clDice scores across folds, and a paired Wilcoxon signed-rank test shows the improvement in clDice is statistically significant ($p=0.023$), consistent with the method's design goal of preserving vascular connectivity, while the improvement in Dice does not reach significance ($p=0.104$).
Read the full abstract ▾
Computation and Language
The Rise of Verbal Reinforcement Learning
Kshitij Tayal, Arun Sharma, Genta Indra Winata et al. (+2 more)
Natural
language is emerging as a primary feedback channel for improving
language agents, capable of conveying intent, preferences, and causal structure in forms interpretable by both humans and modern
language models. We call this paradigm Verbal Reinforcement Learning (VRL) and offer the first unified account of it. We organize the field around a single axis, when verbal feedback takes effect in an
agent's lifecycle and what it modifies, yielding three pillars: (1)
Language as Grounding Signal, where
language defines the task itself by specifying goals, states, and reward structures; (2)
Language as Deliberative Feedback, where natural
language guides
reasoning at test time without the need to update model parameters; (3)
Language as Learning Signal, where
language-based feedback shapes model parameters through training. Within each pillar, we synthesize representative work, distinguish key subcategories of approaches, and outline the distinct role
language plays in shaping
agent behavior. Together, this taxonomy shows how verbal reinforcement is reshaping
agent development, while also defining the challenges and opportunities for building more capable and aligned
agents.
Read the full abstract ▾
All authors Kshitij Tayal, Arun Sharma, Genta Indra Winata, Anirban Das, Sambit Sahu
Robotics
Facet-0: A Robotic Foundation Model for Contact-Rich Precise Manipulation
Haoyuan Deng, Haichao Liu, Wenkai Guo et al. (+6 more)
Real-world robotic assembly at sub-millimeter tolerances demands spatial precision, compliant interaction, and robustness to contact failures. We present Facet-0, a robotic foundation model that predicts and values the contact consequences of its actions. Facet-0 unifies
multimodal representation learning and reinforcement learning (RL) post-training around a joint action-wrench proposal: a causal wrench history is aligned with
vision-
language semantics and kinematic state, and flow matching generates each action chunk together with the future wrist-wrench profile it is expected to induce. Deployment rollouts train a distributional Action-Wrench Critic to distinguish motions with similar task progress but different contact outcomes, while phase-aware rewards and contact-selective credit concentrate policy improvement on decisive interactions. To accommodate part-specific dynamics, a lightweight bounded actor reuses the frozen representation for on-
robot adaptation; RL remains defined over executable Cartesian actions, while an auxiliary wrench head preserves predictive, non-commanded action-contact coupling. Trained on ManuFacet-1K, a 1,000-hour force-synchronized corpus spanning three embodiments and multiple manufacturing
cells, the bounded task-adapted system reaches 82% mean success on five sub-millimeter computer-assembly tasks, compared with 15% for the strongest baseline, with 0.5 mm placement accuracy and 50 ms command latency.
Read the full abstract ▾
All authors Haoyuan Deng, Haichao Liu, Wenkai Guo, Yuan Ling, Zaijia Yang, Yuanjiang Xue, Haosheng Sun, Liangzi Wang, Ziwei Wang
Artificial Intelligence · Cross-listed from econ.TH
Mechanism Design for Alignment and Control
Dirk Bergemann, Andrew Koh and Stephen Morris
We develop a framework for mechanism design with AI
agents whose
alignment (preferences) and capabilities (feasible actions and information) are unknown. We want such
agents to act on our behalf so mechanisms must incentivize both honesty and obedience. A one-sided imitation structure—capabilities can be concealed but not counterfeited—yields a revelation principle, a characterization of implementable policies via nested cyclical monotonicity, and conditions under which eliciting higher-order beliefs can discipline multiple
agents. We apply our framework to stylized examples of (i) sandbagging in which a more capable
agent pretends to be less capable; (ii) an
alignment–interpretability trade-off, where the two are substitutes in the instrument but complements in value; (iii) discipline via peer scoring; (iv) coupling rewards to induce competition among multiple
agents; and (v) scalable oversight and reward shaping.
Read the full abstract ▾
Computation and Language
StudentSim: Training LLM-based Student Simulators
Ke Yang, Chenglong Wang, Michel Galley et al. (+4 more)
AI tutors are most useful when they adapt to each student's strengths, weaknesses, and preferred guidance, but evidence about which guidance works for which student is sparse, slow, and costly to collect from real learners. Student simulators can provide this signal as a proxy, yet existing approaches are limited: state-tracking models fit student behavior but struggle to process explanations or corrections, while LLM role-play follows guidance fluently but does not reliably match the competence of the student being imitated. We present StudentSim, a training framework that turns sparse per-student data into individualized simulators through pooled training followed by per-student specialization. The resulting simulators both mirror a student's own responses and update them under tutor guidance. We also introduce StudentSimEval, a standardized protocol covering 60 students across chess, second-
language English writing, and mathematics, using public learner
datasets with de-identified records shared for research. StudentSimEval measures behavioral fidelity (F), or how well a simulator matches a student's responses, and guidance responsiveness (R), or how readily it updates under tutor guidance, with all methods fit and evaluated on the same records. Across all three domains, StudentSim outperforms GPT-5.4 on both metrics. In chess, StudentSim reaches F=0.51 and R=0.91, compared with 0.23 and 0.72 for GPT-5.4 and 0.45 and 0.27 for Maia2. As a proof of concept, using StudentSim as a reward model for tutor reinforcement learning produces a chess tutor that expert humans rate as more accurate, better-guided, and more personalized than a no-RL baseline and a tutor trained against a GPT-5.4 simulator reward. Code is available at https://github.com/microsoft/StudentSim.
Read the full abstract ▾
All authors Ke Yang, Chenglong Wang, Michel Galley, Chandan Singh, Jeevana Priya Inala, ChengXiang Zhai, Jianfeng Gao
Human-Computer Interaction
Designing Proactive Thought Partners for Writing
Chao Zhang, Abe Davis, Chih-Wei Chen et al. (+1 more)
Writing involves diverse cognitive activities, from ideation to revision, and writers' needs vary across individuals and moments. Proactive AI promises to provide the right support at the right time, yet existing proactive tools largely focus on generic textual assistance, such as autocomplete. This paper studies the design space of proactive thought partners: AI
agents that proactively offer customizable, higher-level cognitive support during writing. We instantiated this concept in a technology probe and deployed it with 16 participants for one week. The probe allows users to create partners by configuring their roles and proactivity. As users write, relevant partners take the initiative at appropriate moments to offer suggestions. Our findings show that participants configured proactive support through prospective planning, used suggestions for both idea generation and self-monitoring, and valued lightweight visual representations alongside non-directive rhetorical framing for non-intrusive interventions. We derive implications for designing proactive writing assistants around customization, timing, engagement, and representation.
Read the full abstract ▾
All authors Chao Zhang, Abe Davis, Chih-Wei Chen, Chin-Chia Hsu
Machine Learning
The Structure of Quantization Damage in LLMs: Why the Next Bit Should Be Spent Globally
Jundong Hu and Shekar Ramachandran
Post-training quantization (PTQ) is widely used to reduce the cost of serving large
language models (LLMs), but its accuracy cost is uneven and is often tuned per model. We study where quantization damage occurs and how to allocate a small additional precision budget. Using causal mixed-precision intervention as ground truth (raise each layer to 8-bit in turn and measure the accuracy it recovers) across 9 open-weight models in 4 architecture families, we test 3 intuitive hypotheses: that quantization damage lives in task
circuits, where the model computes, or in weight statistics. None of them predicts which layers benefit from restored precision. Recovery is instead diffuse: for 8 of 9 models, recovering 75% of the gap takes roughly half the layers; the lone exception, Qwen3-8B, is sharply concentrated. At a matched precision budget, spending it globally on finer quantization granularity beats locally repairing the most recoverable layers for all 8 group-128-compatible models (all but OpenLLaMA, whose width rules out group-128), by 21-52 points, including the concentrated Qwen3-8B. We report 2 secondary findings: the residual is budget-limited (8-bit is near-lossless in our evaluation across RTN, GPTQ, and AWQ), and the location of peak recovery correlates with architecture within a family, though not across families. Within this budget setting, global granularity is a better default than selectively protecting critical layers. More broadly, cheap signals that correlate with quantization damage do not necessarily identify where restoring precision improves accuracy; this must be tested with causal intervention.
Read the full abstract ▾
Numerical Analysis · Cross-listed from math.DS
Families of relative periodic orbits in the planar three-body problem via consecutive alignments
Joan Gimeno, Marc Jorba-Cuscó and Begoña Nicolás
Relative periodic orbits (RPOs) are solutions of the three-body problem that are periodic in a uniformly rotating reference frame and, in general, quasi-periodic in inertial coordinates. We present a numerical procedure for computing and continuing one-parameter families of RPOs of the planar Newtonian three-body problem. The method exploits consecutive syzygies, understood here as configurations in which the three bodies are aligned and their velocities satisfy the corresponding
symmetry conditions. Matching the positions and momenta at two consecutive
alignments reduces the computation of RPOs to a low-dimensional nonlinear problem. Its solutions are then numerically continued, and linear stability is determined from the nontrivial
eigenvalues of the rotated monodromy
matrix after removing the neutral directions associated with conserved quantities and continuous
symmetries. The procedure is applied to several mass distributions and initial configurations, producing families of Poincaré, Hill, and binary-type solutions. These families exhibit transitions from nearly circular to highly eccentric motion, changes of stability near resonances and turning points, and absolute periodic solutions when the rotation angle is a rational multiple of 2{\pi}. In the Hill families, the continuation connects satellite configurations with circumstellar motion as the smallest body loses its gravitational binding to the intermediate body. Circumbinary and circumstellar configurations are also obtained in the binary regime. The results illustrate the dynamical diversity of RPOs and provide coherent three-body motions that can be used as prescribed trajectories in restricted four-body models.
Read the full abstract ▾
Computer Vision
A Benchmark for Vehicle Attribute Classification in Cross-Domain Surveillance Scenarios
Sergio M. Silva Jr., Otavio T. Remer, Gabriel E. Lima et al. (+3 more)
Vehicle attribute analysis is a key component of Intelligent Transportation Systems (ITS), supporting applications such as vehicle identification, traffic monitoring, and forensic investigation. However, models trained under controlled conditions often degrade in real surveillance scenarios due to changes in viewpoint, occlusion, illumination, and sensor characteristics. This paper introduces Unconstrained Vehicle Identification
Benchmark (UVIB), a
benchmark for evaluating three operational vehicle-analysis tasks: front/rear orientation, occlusion-related suitability for Vehicle Make and Model Recognition (VMMR), and color clarity. The
benchmark contains 84,835 vehicle images from seven public Brazilian
datasets, grouped into surveillance and general acquisition domains, with unified binary annotations that were not jointly available in the original sources. Four representative architectures, EfficientNetV2-S, ResNet-50, ViT/B-16, and YOLO11s-cls, are evaluated under mixed-domain, cross-domain, and cross-
dataset protocols. The results show that domain shift has a stronger impact than architecture choice, with substantial degradation in cross-domain settings, especially for VMMR suitability and color clarity. While orientation generalizes more reliably, VMMR suitability remains affected by class imbalance and ambiguous occlusions, and color clarity is highly sensitive to illumination and sensor modality. These findings highlight the need for
benchmarks and evaluation protocols that explicitly measure operational robustness beyond standard in-domain accuracy. The proposed
benchmark is publicly available at https://github.com/UFPR-IPASP-PR/uvib-vehicle-attributes/.
Read the full abstract ▾
All authors Sergio M. Silva Jr., Otavio T. Remer, Gabriel E. Lima, Lucas Wojcik, Rayson Laroca, David Menotti
Computer Vision
SpatialGuard: Harness-Guided Verifiable Spatial Reasoning for Text-to-Image Generation
Ziyun Qian, Zizhi Chen, Yizhou Liu et al. (+3 more)
Complex 3D spatial text to image generation requires models to convert natural
language into stable visual geometry, not merely semantic appearance. Existing
prompt-driven or layout-conditioned methods improve controllability, but often lack an optimizable and verifiable spatial intermediary before visual sampling. As a result, object relations, occlusion, visibility, and camera constraints can decay during multi-round generation. This paper presents SpatialGuard, a structured layout-guided framework for complex 3D spatial text-to-image generation. SpatialGuard parses
prompts into image synthesis-oriented 3D layouts through a Spatial Layout Architect, realizes them as visual conditions and candidate images through a Visual Realizer, and uses a Visual
Alignment Critic to validate consistency among
prompt, layout, and image. To keep constraints stable across iterations, SpatialGuard introduces a Layout Harness that organizes rule constraints, tool invocation, shared knowledge, and feedback loops around the editable layout state. This design turns complex spatial generation from implicit
prompt following into a verifiable process of planning, realization, validation, and repair. Comprehensive experiments show that SpatialGuard achieves state-of-the-art performance in complex 3D spatial layout generation and improves spatial faithfulness over existing text-to-image and layout control baselines.
Read the full abstract ▾
All authors Ziyun Qian, Zizhi Chen, Yizhou Liu, Mingyang Sun, Dingkang Yang, Lihua Zhang