Artificial Intelligence
Efficient Reasoning via Constrained Optimization in Latent Space
Zhinan Hou, Xingchen Li and Keyou You
Large
Reasoning Models (LRMs) have shown remarkable
reasoning capabilities, yet they still suffer from overthinking, generating redundant
reasoning steps which incur substantial
token consumption. Existing methods, such as suppressing reflective keywords or forcing shorter
reasoning lengths, attempt to mitigate this issue but inevitably truncate necessary steps and induce underthinking, thereby compromising performance. To address this dilemma, we investigate the latent representations and observe that efficient
reasoning steps naturally cluster into a concentrated region in latent space, while those deviating from this region tend to produce verbose sequences. To leverage this, we keep
reasoning focused within this region via a quadratic program which projects deviating hidden states back into the region. Then we propose a novel training-free framework to achieve efficient
reasoning that reduces
token generation costs without sacrificing performance. Extensive experiments conducted on four models ranging from 1.5B to 14B, and across six
benchmarks in math
reasoning, coding, and scientific QA, validate the effectiveness of our method, up to a 12.1% improvement in accuracy while reducing generated
tokens by 11.8% to 52.8%. Codes are available at \href{https://github.com/hzn18/Opt4
Reasoning}{https://github.com/hzn18/Opt4
Reasoning}.
Read the full abstract ▾
Artificial Intelligence
Decision Readouts for Text-Mediated Video Anomaly Detection: An Exploratory Evaluation of Jev and Qwen
Xukui Qin, Youting Wang, Xinjie He et al. (+4 more)
How much does the decision readout matter when
video-derived textual evidence is held fixed? We evaluate Jev typed decisions and three Qwen readouts on a sparse development sample of 40
videos and 400 target anchors from UCF-Crime and XD-Violence, each presented as a summary and ordered captions. Each
dataset contributes 20 source groups and 200 anchors, including only 10 and 37 positives, respectively. The original five-backend pilot requested 4,000 predictions; Jev Choice returned 776 valid responses out of 800 under the study's strict numerical policy, blocking its full-coverage quality comparison. On XD captions, Jev Noul achieved 75.99% average precision versus 48.47% for Qwen generated probability and 57.81% for the stronger local ordinal-likelihood expectation. The latter paired difference was 18.18 percentage points (95% source-group bootstrap interval 5.53-31.50). UCF did not show a corresponding advantage: caption ROC-AUC was 52.26% for Noul and 65.95% for ordinal likelihood. Both probability readouts had higher, hence worse, UCF Brier scores than the evaluation-prevalence reference of 0.0475. We additionally audit historical LAVAD scores at exactly matched anchors and distinguish response structure from numerical consistency. A binary-likelihood control is missing. These exploratory offline results characterize ranking, probability quality and interface failures; they establish neither a causal typed-interface benefit nor general superiority, calibration or end-to-end acceleration.
Read the full abstract ▾
All authors Xukui Qin, Youting Wang, Xinjie He, Ziyang Luo, Runxiong Wu, Yan-Syuan Chen, Zhongyao Chu
Artificial Intelligence
RAGWarrant: Evidence-Preserving Governance for RAG Policy Promotion Under Quality, Cost, Latency, and Risk Constraints
Richard Krueger, Lucas Krause and Zach Pocquette
Retrieval-augmented generation systems are extensively instrumented with metrics,
benchmarks, traces, and automated judges, but these tools do not decide whether a proposed policy change is safe to release. We present RAGWarrant, an open-source promotion-control framework that treats deployment as a constrained evidence decision rather than a leaderboard choice. RAGWarrant normalizes evaluator outputs and operational telemetry, applies predeclared quality and hard-risk gates, assigns evidence-class claim ceilings, preserves negative outcomes, and emits auditable PROMOTE, BLOCK, REJECT, or INCONCLUSIVE decisions. We evaluate the framework across T2-RAGBench, MultiHop-RAG, CRAG, HotpotQA, synthetic reproduction, and bounded local generative experiments. On HotpotQA, operational savings were blocked because answer quality fell beyond the declared margin. A bounded CRAG study selected a lower-cost quality-tied policy, but related generative gains were unstable and a held-out guardrail failed closed. We claim an auditable promotion-control abstraction, not optimizer superiority, human validation, or production readiness. The tagged artifact reproduces from a fresh clone, runs as a hardened Docker job, accepts external evaluator exports, and verifies artifact integrity.
Read the full abstract ▾
Artificial Intelligence
ReplayLens: Auditing Agents' Use of Outcomes
Dong Xu, Zhangfan Yang, Jiantao Wu et al. (+5 more)
When an
agent reuses logged experience, a changed decision may reflect the recorded score, the action's name, or the record's position in storage. Standard
memory evaluations do not reveal which relationship drives that change. We introduce ReplayLens, a black-box audit that changes one relationship in the stored history at a time, holds the remaining interface fixed, and measures the resulting decision. Four interventions target four relationships. Outcome reassignment swaps which scores belong to which actions. Pair transport moves intact action-score pairs to new record slots. Consistent renaming relabels actions in both history and menu. Key-slot reassignment changes both score attachment and position. A constructive separation shows why the audit is needed: two
memory writers with identical endpoint accuracy respond differently to the same replay, so conventional evaluation cannot resolve the underlying dependence. On black-box LLM interfaces, swapping scores changes decisions while moving intact pairs does not, separating score attachment from record order. A bounded-
memory study exposes ingestion-order sensitivity that endpoint comparison misses. In sequential experiment planning, altered historical scores redirect exploration and reduce final utility despite fresh measurements. A code-debugging
agent with sealed hidden tests shows the same pattern outside model selection. ReplayLens provides a relationship-level audit for deciding whether logged experience can be merged, reordered, or reindexed safely.
Read the full abstract ▾
All authors Dong Xu, Zhangfan Yang, Jiantao Wu, Shipeng Zhang, Zexuan Zhu, Jiangqiang Li, Jun Zhang, Junkai Ji
Artificial Intelligence · Cross-listed from cs.LG
GradLev: Token-Parallel Test-Time Training Via Costate Prediction
Bo Liu and Qiang Liu
Test-time training (TTT) allows a model to improve its predictions at inference time by updating weights after every observed
token. However, sequential gra- dient writes make parallel training difficult. We observe that, given layer inputs and activation gradients (costates), online gradient descent admits exact parallel scans for both forward evaluation and reverse backpropagation. GradLev lever- ages this duality: a causal auxiliary network predicts costates across all
tokens in parallel; associative scans compute the adapted weights and forward activations and propagate gradients backward; and the resulting gradient targets supervise the predictor via a consistency loss. Exact consistency guarantees exact recovery of the sequential online learner. At deployment, the auxiliary predictor is discarded, and the model updates natively via
token-by-
token forward and backward passes.
Read the full abstract ▾
Artificial Intelligence
RoutePrism: Tracing Construction Order Effects in Agent Memory
Dong Xu, Zhangfan Yang, Jiantao Wu et al. (+5 more)
Processing the same records in a different order can discard different evidence, yet endpoint accuracy alone cannot reveal what changed or whether it mattered. We introduce RoutePrism, a diagnostic protocol that builds
memory twice from the same source pool in two processing orders, then traces which sources, compiled contexts, and answers differ. Because record content, timestamps, policy, and the answer model all stay fixed, any observed difference is localized to the
memory construction step. A matched four-condition intervention tests whether a record displaced by reordering actually carried task-relevant evidence: restoring that single record recovers over 60 percentage points of lost accuracy, while substituting a non-supporting record of equal length does not. We evaluate the protocol on PersonaMem-32K (63 primary queries, 29 users) and 470 LongMemEval-S questions with histories spanning 38 to 62 sessions, replicating the core intervention across five answer models. Survivor selection, defined as the choice of which record a cluster retains, drives most source-level changes, while different
memory policies (compaction, bounded recency, MemoChat-style summarization, A-MEM) produce distinct failure signatures at the source, context, and metadata layers.
Read the full abstract ▾
All authors Dong Xu, Zhangfan Yang, Jiantao Wu, Shipeng Zhang, Zexuan Zhu, Jiangqiang Li, Jun Zhang, Junkai Ji
Artificial Intelligence · Cross-listed from cs.LG
WorldGraph: Graph-Native World Modeling
Zezhong Ding, Yipeng Li and Xike Xie
World models infer latent states of an environment to capture its underlying dynamics and predict future
evolution. Many real-world environments, however, are inherently relational and observed as evolving graphs, where entities, relations, and their properties change over time. Prior graph-related world models use graph structures to organize internal states or support task-specific
reasoning, rather than treating an evolving graph itself as the modeled world. We instead study graph world modeling (GWM), where graph
evolution itself constitutes the world dynamics. We formulate graph world modeling over observed graph
evolution, latent graph states, and heterogeneous graph-transition predictions. Based on this formulation, we construct GWM-Zero, a
benchmark covering node-, edge-, and graph-level transitions over eight temporal graph
datasets. We propose WorldGraph, which combines a state-aware graph
transformer for multi-granularity structural and transition-conditioned
evolution modeling with transition-aware GRPO using dynamic grouping and structure-aware verifiable rewards. Extensive experiments on GWM-Zero show that WorldGraph consistently outperforms representative graph representation, temporal graph learning, graph pretraining, and graph world-model baselines across all three transition granularities.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Toward a Graded Measure of Belief Stability in Large Language Models
Samantha Dies, Branden Fitelson and Tina Eliassi-Rad
Large
language models (LLMs) increasingly mediate how people access and reason with information, yet factual reliability is usually evaluated one judgment at a time. We introduce graded belief stability, a relational measure of how well a belief persists within an LLM's broader belief system. Unlike individual belief probability, it asks whether support for a claim persists when that claim is considered alongside the model's other epistemic commitments. We operationalize this idea with a Direct Conditional
estimator that uses internal model representations to estimate conditional belief probabilities. Across 12 LLMs and three domains, lower-stability beliefs exhibit greater mean behavioral movement under conversational challenge in 83.3% of model-domain settings after matching on individual belief probability. Graded belief stability therefore extends reliability assessment beyond how strongly an LLM supports a claim to how robustly that belief is supported within its broader system of beliefs.
Read the full abstract ▾
Artificial Intelligence
TableSeek: Structure-Preserving Agentic Evidence Seeking over Heterogeneous Table Corpora
Jiaming Tian, Liyao Li, Wentao Ye et al. (+5 more)
Open-domain table
retrieval seeks tables that contain sufficient evidence for answering a question or verifying a claim. Yet semantic relevance is often misleading: topically similar tables may lack the required facts, while answer-bearing evidence is often confined to a few
cells whose meaning depends on surrounding schema and table context. Heterogeneous schemas, value formats, and serializations further weaken one-shot matching. We present TableSeek, a structure-preserving agentic search framework for heterogeneous table corpora. Instead of ranking tables once, an LLM
agent iteratively follows sparse clues, inspects schema-preserving previews, identifies schema- and value-level mismatches, and refines its investigation. TableSeek uses
cells and schemas as evidence anchors while retaining complete tables as evidence units, enabling fine-grained localization without losing the context required for interpretation and answerability checking. Without relying on retriever training or a precomputed semantic index, TableSeek produces transparent evidence-seeking trajectories and achieves competitive end-to-end performance against strong
retrieval-and-reranking pipelines on heterogeneous table
benchmarks. These results suggest that active, structure-preserving evidence seeking is a promising paradigm for open-domain table
retrieval.
Read the full abstract ▾
All authors Jiaming Tian, Liyao Li, Wentao Ye, Haobo Wang, Lihua Yu, Zujie Ren, Gang Chen, Junbo Zhao
Artificial Intelligence
Self-Evolving Agents via Likelihood-Guided Tool-Space Optimization
Xuanqi Zhang, Ruinan Jin, Running Yang et al. (+4 more)
Self-evolving
agents can continually improve their behavior, while tools define the executable action space through which they interact with the environment. However, exposing the full tool library to model introduces substantial irrelevant context and can impair tool-use decisions. We study tool-space self-
evolution, where each recurring task type maintains a persistent tool space which is constructed from accumulated output experience. We identify three limitations of existing methods: (1) output-unaware selection: they rely primarily on tool descriptions or model priors rather than observed tool outputs; (2) statelessness across request: they select tools independently for each request without consolidating prior output experience into persistent task-specific state; (3) inference cost: they repeatedly search, rank, or reason over candidate tools for subsequent requests of the same task. We address these limitations through output-aware tool scoring, persistent task-specific tool spaces, amortized tool selection, and reusable configurations across models. We introduce LOTS (Likelihood-Only Tool Scoring), which evolves an
agent's tool space from accumulated output experience while keeping model parameters fixed. After each request, LOTS holds the model's generated answer and estimates each tool's contribution by measuring how much the answer likelihood changes when its observed output is removed. These contributions are aggregated within each recurring task to rank tools and update its persistent space. Across three
benchmarks, LOTS improves task performance while substantially reducing tool context. More importantly, sequential experiments demonstrate that task-specific spaces persist and continue to improve over time, while cross-model experiments show that learned configurations transfer across different models.
Read the full abstract ▾
All authors Xuanqi Zhang, Ruinan Jin, Running Yang, Yuxuan Zhang, Minghui Chen, Wenlong Deng, Xiaoxiao Li
Artificial Intelligence
Same Tasks, Different Apps: Why Mobile GUI Agents Fail to Generalize?
Tien Tran, Namho Koh, Daiki E. Matsunaga et al. (+2 more)
Mobile GUI
agents deployed in real settings must work across different applications that support the same functionality. Most existing
benchmarks test each task in only one app, so a high score can mean the
agent understands the task, or only that it knows that particular app. We introduce AnyAppBench, a category-controlled live Android
benchmark that evaluates cross-application generalization while keeping the user goal fixed. It spans 10 functional categories, 100 task templates, and 520 task–application pairs over 52 applications.
Agents run from raw instructions and with app-independent sub-goals, and a VLM judge labels every failed run under a fixed failure taxonomy whose reliability is measured by human annotation. We find that, across 13
agents, success on the original application does not transfer reliably to new applications with the same goal. Furthermore, providing high-level sub-goal decomposition produces only small, category-dependent changes that do not close the gap, and the mix of failure types changes with the target interface. Based on those insights, we believe the AnyAppBench
benchmark provides an important stepping stone toward robust real-world deployment of mobile GUI
agents. Our code, data and the leaderboard can be found at the project website https://anyappbench.github.io/.
Read the full abstract ▾
All authors Tien Tran, Namho Koh, Daiki E. Matsunaga, Ayush Jain, Kee Eung Kim
Artificial Intelligence
You Can't Have It Both Ways: Concept Entanglement Limits Diffusion Model Unlearning
Yian Wang, Ali Ebrahimpour-Boroojeny, Hari Sundaram et al. (+1 more)
Concept unlearning in text-to-image
diffusion models aims to suppress a target concept (e.g., horse) while preserving related but distinct content (e.g., donkey), yet existing methods either leak under indirect
prompts or visibly degrade other concepts. We show that these failure modes stem from the geometry of concept representations rather than from any particular
algorithm. Formalizing concepts as activation-space regions, we prove that the overlap between a target and other concepts lower-bounds the damage any robust erasure must inflict on them, with the trade-off scaling linearly in the degree of overlap. Across thirteen unlearning methods, including methods designed to preserve non-target concepts, no method achieves both strong erasure and strong neighbor preservation: STEREO nearly eliminates indirect leakage but cuts neighbor generation by more than 75%, while sparse inference-time methods preserve neighbors but leak. Damage increases with our overlap measure, monotonically so for STEREO; the $\kappa$-scaling reproduces on SDXL, and neighbor-selective damage recurs on FLUX. Perfect unlearning is the wrong target for entangled concepts; methods should be evaluated on the Pareto frontier our
theorem establishes.
Read the full abstract ▾
All authors Yian Wang, Ali Ebrahimpour-Boroojeny, Hari Sundaram, Varun Chandrasekaran
Artificial Intelligence
Waggle: Learning One Anonymous Local Law for Self-Organizing LLM Swarms
Mingxi Zou, Wei Zhu, Zhuo Wang et al. (+4 more)
As LLM
agents increasingly collaborate on complex tasks, how to organize their interactions becomes a central design question. Existing multi-
agent systems typically learn or adapt explicit roles, hierarchies, routing policies, or communication
topologies. We shift the learning target to a reusable local law that can be shared across interchangeable
agents and adapt coordination as populations or interaction conditions change, without redefining a global organization. We introduce Waggle, a shared anonymous policy over bounded local views that jointly selects task actions, semantic communication, and local commitment updates. Repeated execution of the same law allows coordination to form, persist, and reorganize online without explicit roles or global
topology. To learn this law across interchangeable
agents and evolving coordination, we develop Swarm-Consistent
Distillation (SCD), combining anonymous-orbit consistency with rollout-grounded prediction of the next local coordination field, with no added inference-time components. Across diverse coordination settings, the same learned law remains effective as populations and interaction budgets change, retains over 96% of substrate-specific oracle quality, and transfers without retraining; SCD further improves reorganization after counterevidence. Together, these results show that LLM-
agent organization can emerge and adapt through repeated execution of a learned local law.
Read the full abstract ▾
All authors Mingxi Zou, Wei Zhu, Zhuo Wang, Langzhang Liang, Zhiwen Tang, Yinghui Xu, Zenglin Xu
Artificial Intelligence
Evo2Team: When Do Evolved Skills Transfer? From Selection to Deployment
Renxiang Wang and Jiaming Cui
A skill bank that helps one multi-
agent system may leave another's behavior unchanged. A transferred rule helps only when target
agents act on it successfully. We study this path for routing and communication skills in Count-Frequency and AgentsNet, using teams of 4–32
agents and GPT and Qwen model ladders. Source
evolution meets a joint quality, cost, model-tier, and confirmation goal in 14 of 16 settings. We then evaluate Evo2Team, which selects, adapts, and confirms source skills for the target team, alongside six frozen selectors across 28 transfer directions. Evo2Team's target-side exploration cost is below that of evolving a new target bank in every direction, even when reused reference evaluations are charged once. Twenty of 28 held-out outcomes meet the positive-transfer criterion, including three saved diagnostic tests. Selection alone does not explain these outcomes: KNN and CORAL choose different banks in two AgentsNet directions but produce identical recorded executions. When Evo2Team changes execution, gains can reach many tasks, as in a Count-Frequency direction that improves 28 of 32 tasks over KNN. Seven positive AgentsNet outcomes save 6.1–14.6% in deployment cost while using transferred skills on only three to six of fifteen tasks. In five earlier accepted directions, all 22 task records using transferred skills pass three fixed-graph confirmations, but four fail in recorded executions on new graphs. Graphs and model responses change together in this comparison. These results show that skill transfer must be assessed through the actions
agents take, the tasks those actions reach, and the quality and cost of the final deployment.
Read the full abstract ▾
Artificial Intelligence
StateGuard: Analytical-State Management with Validity-Aware Intervention for Long-Horizon Data Agents
Wenle Liao, Zhao Wang, Jingchao Zhang et al. (+3 more)
LLM-based
agents have shown strong capabilities in automated data analysis and are increasingly moving toward long-horizon, multi-stage analytical workflows. However, as the analytical process evolves, constraints, variables, and conclusions remain implicitly embedded in interaction histories, making it difficult for
agents to track which analytical artifacts remain valid over increasingly long horizons and changing dependencies. Consequently, stale artifacts may be silently inherited, propagating errors to downstream stages. To address this challenge, we propose StateGuard, an analytical-state validity management framework for long-horizon data
agents. StateGuard externalizes evolving analytical progress into a state graph containing constraints, versioned variables, intermediate conclusions, and cross-state relations, treating each state as an executable, verifiable, and traceable object rather than textual
memory alone. StateGuard maintains state validity through evidence-grounded verification and hierarchical intervention. To equip StateGuard with these capabilities, we first introduce Manager-Oriented Counterfactual Supervision, which constructs 3K state-centric trajectories through counterfactual runtime synthesis to fine-tune StateGuard for state maintenance, verification, and repair. We then apply Validity-Guided Policy Optimization, using runtime validity evidence to provide fine-grained learning signals for protocol correctness, state grounding, and intervention quality. Experiments on three diverse long-horizon data-analysis
benchmarks show that StateGuard consistently improves data-
agent performance while reducing dependency-induced downstream error propagation, demonstrating the advantages of explicit analytical-state management for reliable long-horizon data analysis.
Read the full abstract ▾
All authors Wenle Liao, Zhao Wang, Jingchao Zhang, Jiajie Jin, Yimeng Xu, Zhicheng Dou
Artificial Intelligence · Cross-listed from cs.CV
PrefLUT: Reusable and Refinable Personalized Color Editing from Pairwise Preferences
Chuanzhi Xu, Langyi Chen, Chengkun Yue et al. (+5 more)
Photographic color editing is inherently personal: the same image can appear too warm, too muted, or already satisfactory to different users. Most lookup table (LUT) and reference-guided methods target a specified appearance rather than model persistent preferences from repeated user choices. To address this gap, we introduce PrefLUT, a reusable and refinable user-preference modeling framework for deployable 3D LUTs, encoding ordered preferred/non-preferred image pairs into a lightweight Reusable User Profile that is reused across queries and refined using additional user preference pairs, without per-user optimization. A Query-Conditioned LUT Predictor combines this profile with each image to predict a LUT latent vector and edit strength. An Identity-Residual LUT Decoder and Edit-Strength Controller then produce an exportable 3D LUT. Experiments on three
datasets demonstrate effective personalized editing and general-purpose enhancement. Each quantized profile requires only 260 bytes, and editing takes 1.365 ms/image on an RTX 5090 GPU. We also introduce the Preference-Conditioning Verification Protocol (PCVP), an evaluation protocol to verify whether personalized image edits depend on user preferences and the query image through controlled changes to user profiles, preference orders, pair correspondences, and query images.
Read the full abstract ▾
All authors Chuanzhi Xu, Langyi Chen, Chengkun Yue, Xuanhua Yin, Boyu Wei, Qingwen Zeng, Zihan Deng, Weidong Cai
Artificial Intelligence
From Attack Success to Attack Severity: Counterfactual Memory Attacks on LLM Agents
Mingxi Zou, Langzhang Liang, Zhuo Wang et al. (+3 more)
As LLM
agents increasingly rely on persistent
memory for long-horizon and personalized behavior, they can retain and reuse information across interactions, but this also creates a lasting channel through which malicious
memory writes can influence future behavior. Persistent-
memory attacks are typically evaluated by whether they succeed, yet successful attacks can leave persistent states with substantially different downstream consequences. We study this severity as a distinct attack-design objective and formalize it with counterfactual
memory regret (CMR), the paired increase in expected downstream loss relative to clean
memory. We introduce MemHarm, which predeclares a finite class of sparse, grounded semantic edits, evaluates candidates through the normal
agent memory interface using offline paired-loss feedback, and certifies resolved selections within that class. Compared with attack-success optimization, CMR-guided selection produces substantially larger downstream loss while retaining most of the success-rate gain. Across two
agent benchmarks and diverse
memory designs, MemHarm attains the highest CMR point estimates among the evaluated general attacks on identical support. Factor-removal interventions link this harm to the selected semantic factor, and native-
agent deployments verify the write-to-fresh-process attack path.
Read the full abstract ▾
All authors Mingxi Zou, Langzhang Liang, Zhuo Wang, Yiyang Zhao, Lizhen Qu, Zenglin Xu
Artificial Intelligence · Cross-listed from cs.IR
STITCH-RAG: Spatio-Temporal Influence Tracing over Topic Hypergraphs for Multi-Hop Retrieval-Augmented Generation
Haodong Yang, Mengzhu Chen and Jia Cai
Multi-hop
retrieval-augmented generation requires a retriever to connect evidence distributed across documents while preserving a concise, faithful generation context. Existing indexes leave two complementary gaps: chunk-based RAG can break cross-passage evidence chains, whereas an unlabeled pairwise projection without generating-topic provenance cannot jointly preserve topic-level co-participation and per-occurrence entity descriptions. We propose STITCH-RAG, a hypergraph-based framework with three coupled components. First, a semi-merged topic hypergraph encodes multi-entity co-participation as topic-summary hyperedges while retaining per-chunk entity states linked by canonical-name equivalence. Second, spatio-temporal influence bridging propagation (STIBP) combines topic-space propagation with deterministic chunk-index linkage across name-equivalent states under frequency-adaptive decay. Third, continuous STIBP scores replace binary entity-match seeds in localized Personalized PageRank (PPR). We characterize the condition under which this prior assigns more PPR mass to ground-truth evidence than a binary prior. Under the reported protocol, STITCH-RAG attains the highest reported Contain-Acc and LLM-Acc point estimates among the compared methods on HotpotQA and 2WikiMultiHopQA, and higher Recall@8 than the methods included in the standardized
retrieval comparison. Results on the mixed-domain
benchmark remain auxiliary preference-based evidence because only LLM-judged accuracy is available.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SE
JET: Judge-Guided Evolution at Test Time for Agent Programs
Yao Long Teng, Jiayi Cai and Bo An
An
agent's executable program governs how it uses tools, processes observations, and responds to failures. Evolving this program at test time can help adaptation, but deciding which changes to retain is difficult when true rewards are unavailable. Execution traces provide evidence of
agent behavior, yet interpreting that evidence requires a judge that remains useful as tasks and candidate programs change. We introduce Judge-Guided
Evolution at Test Time (JET), which evolves an executable judge on labeled source trajectories, then freezes and transfers it to guide target-side program
evolution. The judge supplies scores and diagnostic feedback without target evaluator access or model-weight updates. On unseen WebShop tasks, JET achieves approximately 13% higher mean reward than fixed-rubric guidance when
evolution begins from an unevolved program (cold start) and 4% higher when it begins from one already optimized on source tasks (warm start), with a 36% relative improvement in cold-start exact success. An exact-judge control on PushT, where the judge reconstructs the scoring rule from observations, shows that without judge error, program search becomes the bottleneck. Analyses identify useful reward-prediction logic in the evolved code and show that better final selection alone cannot explain the gains. These results support executable judge transfer for program adaptation under evaluator-preserving task shifts.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Probabilistic electrical power demand forecasting with uncertainty quantification
Mahesh Neupane, Pragya Dhungana, Pradip Khatri et al. (+2 more)
The majority of research on electricity consumption
forecasting has focused on deterministic approaches, which generate a single point estimate for each time step in the
forecasting horizon. However, the increasing penetration of renewable energy sources and the growing complexity of modern smart grids have introduced greater variability and uncertainty into power-system demand and operation. Consequently, probabilistic
forecasting, which quantifies the uncertainty and variability associated with future electricity demand, is becoming increasingly important for reliable power-system planning and operation. This study presents an empirical comparison of four contemporary probabilistic
forecasting models for electricity consumption, highlighting their respective strengths and limitations. We have performed comparision on real-world power systems related
datasets. Across all power-consumption zones, NGBoost demonstrates superior probabilistic
forecasting performance, achieving the lowest MAE and RMSE while providing well-calibrated uncertainty estimates with high prediction-interval coverage and reasonably narrow intervals. These results indicate that NGBoost offers a more accurate and reliable
forecasting framework than
Bayesian, Monte Carlo (MC) Dropout, and Gaussian Process Regression (GPR) models for the considered electricity consumption data.
Read the full abstract ▾
All authors Mahesh Neupane, Pragya Dhungana, Pradip Khatri, Swechhya Baskota, Hariom Dhungana
Artificial Intelligence · Cross-listed from cs.LG
SlimWise: Decoupling Expert Pruning Across Prefill and Decode for Efficient MoE Serving
Gunho Park, Kyoungho Jeun, Juntaek Oh et al. (+3 more)
Mixture-of-experts (MoE) models activate few experts per
token, yet batched decoding can access nearly the entire expert pool, making expert-weight traffic a major bottleneck. Expert
pruning reduces this traffic, but conventional approaches also prune compute-bound prefill, sacrificing model quality for little throughput benefit. We present SlimWise, a serving framework that tailors the expert pool to each inference phase. SlimWise performs prefill with the full model and decode with a pruned model that directly reuses the prefill-generated KV cache without conversion. Across two MoE backbones and three
pruning criteria, this training-free KV cache handoff substantially narrows accuracy gaps relative to the full model in many settings. We also show that
benchmark accuracy can conceal substantial
pruning-induced changes in generation length. To address these distortions and residual accuracy loss, SlimWise introduces a low-cost
distillation stage that trains the decoder to continue from full-model KV caches while updating only a small subset of parameters. Implemented in vLLM, SlimWise supports both prefill-decode (PD) disaggregation and PD-colocated serving. On Qwen3.6-35B-A3B, SlimWise improves decode throughput by up to 1.81x at 50% expert
pruning with minimal accuracy loss.
Read the full abstract ▾
All authors Gunho Park, Kyoungho Jeun, Juntaek Oh, Byeongjun Shin, Baeseong Park, Minsoo Rhu
Artificial Intelligence
GUITAR: Structured Failure Diagnosis of GUI Agents via State Transitions
Shaoqing Zhang, Kehai Chen, Xuefeng Bai et al. (+4 more)
Understanding where and why Graphical User Interface (GUI)
agents fail is essential for building more reliable systems, yet current evaluation relies on step accuracy, a metric that treats each screen independently and overlooks the underlying structure of GUI environments. This leads to two critical blind spots: (1) functionally equivalent screens are evaluated in isolation, obscuring systematic failure patterns across shared screens; and (2) the long-tailed GUI distribution renders failures on rare but critical screens invisible under standard metrics. To address these issues, we propose GUITAR, a state-centric diagnostic framework that performs structured failure analysis over both states and transitions, using a State Transition Graph (STG) by mapping visually diverse screens to shared functional states. Across 8
agents and 6 tasks from AndroidControl and Mind2Web, GUITAR reveals that 60.4% of failures occur in 20% of states, localizing errors to a small set of bottlenecks. Bottleneck-targeted guidance improves SR by 2.8% and retains a 1.88% average gain across 7
agents under three-fold trajectory-held-out evaluation with fully automatic STGs. These findings demonstrate the diagnostic and actionable value of structure-aware evaluation within the evaluated mobile and web tasks. Code is available at https://github.com/sqzhang-lazy/GUITAR
Read the full abstract ▾
All authors Shaoqing Zhang, Kehai Chen, Xuefeng Bai, Zhuosheng Zhang, Pengfei Zhang, Yang Xiang, Min Zhang
Artificial Intelligence · Cross-listed from cs.CL
Unknown is not normal: separating language-model extraction from rule-based decision logic for clinical risk scores
Nicolás Vera Zúñiga
Large
language models (LLMs) are increasingly used to compute clinical risk scores from free-text notes. Notes are often incomplete, and treating undocumented findings as normal can silently misclassify patients. We test whether separating three-state extraction (present, absent or unknown, by an LLM) from decision logic (deterministic code computing score bounds over unknown inputs) lets a system ask only questions that can change the decision. On 1,200 synthetic emergency cases across six calculators (HEART, CURB-65, qSOFA, PERC, Wells, Cockcroft-Gault), with a simulated clinician answering questions, we compared this bounds policy with asking for every missing input, a missing-equals-normal schema, and an end-to-end LLM
agent (Claude Opus 5.5). With Claude Haiku 4.5 as extractor, the bounds policy matched ask-all accuracy (99.4% vs 99.4%) with half the questions (0.92 vs 1.78 per case) and no irrelevant ones. Treating missing as normal dropped accuracy to 91.2% and under-triaged 8.5% of patients (95% CI 7.1-10.2), and under-triage persisted under messy notes and a noisy clinician. The
agent was equally accurate under ideal conditions (99.6%) but 9.5% of its questions were irrelevant; with a noisy clinician it was less accurate than the bounds policy (83.5% vs 87.0%, p<0.001) and committed prematurely in 2.7% of cases (bounds: 0%). A 9B local model as extractor reached oracle-level accuracy (99.8%). In 584 real case reports from MedCalc-Bench, only 52% contained enough information to determine the category (HEART 13%). Routing decisions through code that reasons explicitly about unknowns avoids premature commitment and irrelevant questions, halves the questions asked, and works with small local models.
Read the full abstract ▾
Artificial Intelligence
SpecRegMatch: Robust Semi-Supervised Regression for Vehicle Interior Noise Prediction
Sejin Sim, Jinsoo Bae and Seoung Bum Kim
The rapid advancement of artificial intelligence has observed increased application in predicting vehicle interior noise levels within the automotive industry. However, the collection of labeled data for training models in this context involves significant costs. Previous studies in semi-supervised regression (SSR) have effectively mitigated the reliance on labeled data by incorporating unlabeled data. Nonetheless, these approaches often introduce a high computational cost due to the training of multiple models and data sampling. This study introduces SpecRegMatch, a novel SSR method aimed at addressing the computational cost associated with training by leveraging a single model, thus eliminating the need for multiple data samplings. SpecRegMatch integrates consistency regularization and information maximization to robustly train the model, achieved through various augmentations applied to both the
embedding vectors and predicted values. Experimental results demonstrate that SpecRegMatch achieves state-of-the-art performance across various scenarios, even when using a single model. It attains a remarkable performance, as indicated by an R^2 score of 0.434. This is especially noteworthy in scenarios where labeled data is scarce. You can access the code for our proposed method at https://github.com/sejin-sim/SpecRegMatch.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
The Devil is in the Spectrum Bias: Spectrum-Balanced Feature Matching for Robust Representation Distillation
Kuniaki Saito and Yoshitaka Ushiku
Large visual foundation models have demonstrated remarkable transferability across a wide range of downstream tasks. To deploy such models efficiently, feature matching has become a popular knowledge
distillation approach that transfers teacher representations to smaller student models without requiring labeled data. However, we show that the conventional feature matching objective with L2-distance is inherently biased toward reconstructing dominant spectral directions of the teacher representation, while under-optimizing low-variance directions that often contain task-relevant information. To address this, we propose Spectrum-Balanced Feature Matching, SpecMatch, a simple objective that adaptively emphasizes under-optimized spectral directions while preserving the relative importance of dominant directions. SpecMatch is easy to implement and introduces negligible computational overhead. Extensive experiments on image recognition demonstrate that SpecMatch consistently improves downstream adaptation across diverse tasks, including image classification, anomaly detection, medical image analysis, and domain generalization. In particular, SpecMatch outperforms conventional feature matching in 40 of 42 teacher–student and training-setting combinations, while consistently improving over the original student model in all settings. We further demonstrate that the proposed objective generalizes beyond
vision, improving downstream performance across six
protein understanding tasks.
Read the full abstract ▾
Artificial Intelligence
A Differentiable Optimization Framework for Registering Sequential Bounding Boxes with Point Cloud Stream
Xuesong Li, Jinguang Tong and Jie Hong
Refining a sequence of coarse 3D bounding boxes against a
LiDAR point-cloud stream demands tracks that are geometrically accurate (high IoU) and temporally coherent (low roughness), preferably without training data. The usual recipe keeps the two concerns apart: register each frame independently, then smooth the trajectory afterwards with a Kalman~RTS or Savitzky–Golay filter. Smoothing displaces boxes from a
geometric optimum and never re-optimises, so it trades accuracy for smoothness. We instead fold the temporal smoothness constraint into a training-free registration objective and solve for all poses jointly with L-BFGS. The payoff depends on how well the object is seen. On well-observed tracks it is large: within the low-roughness budget, the joint objective beats both post-hoc smoothers on paired multi-seed statistics and cuts roughness several-fold relative to frame-wise registration at matched accuracy. Treating visibility as an experimental variable exposes the limit. The advantage decays monotonically as views become one-sided, until it is indistinguishable from zero for near-edge-on objects and slightly negative under a ray-cast simulator with range-dependent density and ego motion, where the decoupled pipeline is in fact ahead at tight roughness budgets. We locate that boundary and trace it to one term: orientation
alignment ties yaw to the estimated velocity and fails once that estimate is noisy. A ground-truth-free rule can choose the temporal scale and keep every track inside the roughness budget.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
TRACE: Expert-Aligned ECG Representation Learning with Rigorous Benchmarking and Real-World Validation in Acute Cardiac Care
Lovely Yeswanth Panchumarthi, Andrew Lu, Saurabh Kataria et al. (+11 more)
TRACE (Text-Reinforced Analysis of Cardio ECGs) is a
multimodal electrocardiogram (ECG) representation model that learns clinically grounded signal
embeddings for downstream cardiac classification. It is designed to address the limitations of existing CLIP-style training, which often struggles with noisy clinical text and fails to leverage the complementary strengths of unimodal (from ECG) and cross-modal (between ECG and matched cardiologist reports) learning. To bridge this gap, we propose a hybrid architecture that jointly learns unimodal and cross-modal representations via uncertainty-weighted multi-task learning while utilizing an LLM-based pipeline to extract high-fidelity findings from cardiologist reports. We evaluate TRACE across a spectrum of clinical urgency, establishing robust performance on public
benchmarks for arrhythmia classification and structural abnormalities relative to existing unimodal and
multimodal ECG models. To demonstrate real-world utility, we further validate the model on acute coronary occlusion (ACO), where the prevailing ST-elevation criteria miss 25-34% of true occlusions. Utilizing a large private ACO
dataset with expert-annotated ground truth, TRACE significantly outperforms real-world clinical practice, yielding a 19.0% increase in sensitivity or a 62.6% reduction in false positive rates at the clinical baseline. This extensive evaluation confirms that TRACE delivers both strong performance on
benchmark tasks and tangible clinical impact in the most acute, high-risk cardiac scenarios.
Read the full abstract ▾
All authors Lovely Yeswanth Panchumarthi, Andrew Lu, Saurabh Kataria, Delgersuren Bold, Minxiao Wang, Runze Yan, Patricia Dykes, Brian J. Gow, Tom J. Pollard, Jessica K. Zègre-Hemsey, Dillon J. Dzikowicz, Lekshmi Kumar, Xiao Hu, Ran Xiao
Artificial Intelligence · Cross-listed from cs.RO
AD-E2E-JEPA: A Joint-Embedding Predictive Architecture For End-to-End Autonomous Driving
Haoran Zhu, Wancong Zhang, Yann LeCun et al. (+1 more)
Autonomous driving requires world models that can understand the physical world, reason and plan, and operate safely. In this paper, we first systematically evaluate existing action-conditioned joint-
embedding predictive architecture (JEPA) world models, including LeWM, DINO-WM, and JEPA-WM for end-to-end autonomous driving (E2EAD). To isolate world-model quality from policy learning, we employ a goal-conditioned zero-shot planning setting that evaluates these models using ground-truth future observations as goals, without training any driving policy. We find that existing JEPA-based world models are either accurate for driving but computationally expensive, or computationally efficient but insufficient for planning. To address this trade-off, we propose AD-E2E-JEPA, which introduces a SIGReg-regularized learnable projector applied to projected patch
embeddings. The projector reduces the number of planning patches by $16\times$ and the
embedding dimension by $4\times$, achieving a $100\times$ inference speedup while retaining planning performance, with a 0.8-second runtime for an 8-frame rollout over 256 candidate trajectories. Without training any driving policy, the world model itself reaches the goals located 20 meters away on average within the displacement of respectively 4.0/2.8 meters, using world-model rollouts over trajectory vocabularies of respectively 256/8,192 candidates. On the NAVSIMv2
benchmark, it achieves 67.3/72.9 EPDMS with multiplicative safety metrics and 84.1/86.5 EPDMS$^{\dagger}$ without them in goal-conditioned zero-shot planning. Experiments further show that the self-supervised pretrained projector improves downstream imitation learning performance from 80.2 to 85.4 EPDMS. The source code is available at https://github.com/HaoranZhuExplorer/AD-E2E-JEPA
Read the full abstract ▾
All authors Haoran Zhu, Wancong Zhang, Yann LeCun, Anna Choromanska
Artificial Intelligence
K-OPSD: Verifiable On-Policy Self-Distillation for Post-Training Vision-Language Models on AEC Drawings
Yunfei Bai, Enrico Chionna, Akash Amol et al. (+2 more)
Interpreting architecture, engineering, and construction (AEC) drawings is hard for general
Multimodal Large
Language Models (MLLMs) and
vision-
language models (VLMs). We introduce K-OPSD, a VLM post-training methodology for improving AEC drawing understanding. Building on On-Policy Self-
Distillation (OPSD) with verifiable supervision, we construct a teacher from the model's own best-of-N generations, certified by a process-level verifier, and rescue failed
prompts by resampling under a hint that exposes the verified answer. We then perform an on-policy model update by training on verified completions with a cross-
entropy inner-loss, outperforming the bounded
token-wise generalized Jensen-Shannon divergence (JSD) used by on-policy
distillation. Using K-OPSD, we fine-tune Qwen3-VL models on the AECV-Bench
dataset. The resulting models attain the top average judge score (0.819) and combined accuracy (0.738), achieving competitive results against open-source baseline models. The recipe transfers to the out-of-domain ArchCAD
dataset, where the 8B model gains most. We present the verifier suite and the continual learning and self-improving pipeline, our results provide preliminary evidence that verifier-guided self-
distillation is a promising route toward more reliable machine reading of architecture drawings.
Read the full abstract ▾
All authors Yunfei Bai, Enrico Chionna, Akash Amol, Kawaljit Singh KC, Joern Tinnemeyer
Artificial Intelligence
GenoMorph: Pathway-Grounded Genomic Disease Reasoning via Adaptive Latent Computation
Tanmoy Kanti Halder, Akash Ghosh, Arijit Roy et al. (+1 more)
Large
language models (LLMs) have demonstrated strong capabilities in biological
reasoning; however, genomic disease inference remains largely dependent on memorized gene-disease associations rather than understanding biological pathways. This shortcut learning undermines robustness and generalization, and breaks down when molecular identifiers are unavailable. We present GenoMorph, a
multimodal genomic
reasoning framework that shifts disease prediction from associative gene-disease mapping toward pathway-grounded
reasoning. GenoMorph couples a frozen DNA foundation model with question-conditioned cross-
attention fusion, self-adaptive latent
reasoning (LatentSp), a residual
reasoning gate for iterative genomic evidence reinjection, and rejection sampling fine-tuning regularized by hierarchical optimal transport (OT). Rather than learning direct gene-disease mappings, GenoMorph aligns genomic sequence representations with latent pathway dynamics, enabling
reasoning trajectories that follow molecular interactions before producing disease predictions. LatentSp dynamically allocates computation according to
reasoning confidence, reducing unnecessary
reasoning steps and improving inference efficiency. We further construct an anonymized
benchmark from the Kyoto Encyclopedia of Genes and Genomes (KEGG), replacing every gene and molecular identifier with anonymous symbols while preserving sequences and pathway
topology, thereby removing memorization shortcuts. GenoMorph raises the weighted F1 from 0.7863 (BioReason) to 0.9412, and rejection sampling fine-tuning with self-adaptive latent
reasoning pushes it to 0.9725 while cutting latency nearly 60%. On the anonymized
benchmark it reaches 0.9465 F1, substantially outperforming prior systems and confirming that accurate disease prediction can arise from pathway
reasoning rather than memorized gene-disease associations.
Read the full abstract ▾
All authors Tanmoy Kanti Halder, Akash Ghosh, Arijit Roy, Sriparna Saha