Artificial Intelligence
Evidence-Aligned Entity Verification for Hallucination Detection in Retrieval-Augmented Generation
Runsong Jia, Zhen Fang, Mengjia Wu et al. (+2 more)
Hallucination detection is crucial for large
language models (LLMs), as hallucinated content creates significant barriers in applications requiring factual accuracy. Current detection methods mainly depend on internal signals like uncertainty and self-consistency checks, using the model's pre-trained knowledge to identify unreliable outputs. However, pre-trained knowledge may become outdated and has coverage limitations, especially for specialized or recent information. To address these limitations,
retrieval-augmented generation (RAG) has emerged as a promising solution by retrieving relevant evidence at inference time, grounding outputs beyond the model's parametric knowledge. In this paper, we target a critical and practical learning problem RAG-based
hallucination detection (RHD), where RAG is employed to enhance
hallucination detection by addressing information updating challenges. To address RHD, we propose a novel method Evidence-Aligned Entity Verification (EAEV), which detects entity-level
hallucinations by leveraging RAG to align generated entities with retrieved evidence contexts. Specifically, EAEV evaluates entity-evidence
alignment through three complementary dimensions and introduces counterfactual stability analysis to ensure robust
alignments under evidence perturbations. Experiments across multiple RAG
benchmarks demonstrate that EAEV achieves consistent improvements over existing methods with strong generalization capabilities.
Read the full abstract ▾
All authors Runsong Jia, Zhen Fang, Mengjia Wu, Jie Lu, Yi Zhang
Artificial Intelligence
Revoked but Still Authoritative: An Empirical Study of Revocation Enforcement in Agent-Memory Systems
Yi Ting Shen, Kentaroh Toyoda and Alex Leung
Long-running
language-model
agents depend on persistent
memory. Many
agent-
memory systems preserve history through soft revocation: a contradicted fact is marked invalid and retained rather than deleted. However, whether that mark is enforced at
retrieval time is unexamined. In this paper, we measure five such systems: we load each with a revoked policy and its replacement, track whether the revoked fact is returned at
retrieval and whether the
agent then acts on it across nine policy scenarios and nine models, and score every trial under six defense conditions. We find that no system enforces revocation by default: the revoked fact is returned wherever the revocation label is visible to the
retrieval layer, outranks its replacement, and leads
agents to the unsafe action. Based on these findings, we develop a guard that sits between the
agent and any
memory backend and withholds records that are revoked or conflict with their replacement.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
ACEA: An Adversarial Co-Evolution Arena for Head-to-Head Red-Team and Blue-Team LLM Testing
Yi Ting Shen, Kentaroh Toyoda and Alex Leung
Automated red-team attacks and blue-team defenses for large
language models (LLMs) are advancing quickly. However, attackers and defenders are built and tested in isolation, and the resulting scores are hard to trust. To tackle this, we present ACEA (
Adversarial Co-
Evolution Arena), a platform that connects a pluggable red-team adapter and a pluggable blue-team adapter to a shared target LLM and scores their attack and defense rates with an LLM judge. ACEA contributes four components. First, a pluggable, model-agnostic arena. Any red or blue project connects over a minimal HTTP protocol, which we call the ACEA Standard Adapter Protocol (ASAP). It can be written in any
language, and a project that exposes nothing but the protocol is a full participant. Second, an evaluation methodology built for
adversarial rounds. Seeding the target with canonical secrets gives verifiable ground truth that separates real leakage from
hallucination. We also send each attack to the target even when the defense blocks it, which measures the attack's raw potency independently of whether it was stopped. Together these yield a per-round decomposition of attack strength and defense effectiveness. Third, a real-time, game-style visualization with a detailed end-of-battle report that localizes each failure. The evaluation thus becomes an actionable signal for improving a red or blue project. Fourth, an optional in-context improvement loop that turns each round's outcome into advisory hints for the next. An adapter can then adapt across rounds without keeping state, provided it reads the hints. We describe the design of ACEA and the metrics through which red and blue teams are scored head to head.
Read the full abstract ▾
Artificial Intelligence
CircuTutor: Transforming Static Circuit Problems into Intelligent and Dynamic Tutoring
Ziyu Luo, Xiaorui Ma, Lin Chen et al. (+1 more)
Learning direct current
circuit concepts requires learners to connect invisible physical quantities, such as current, voltage, resistance, and power, with observable outcomes such as bulb brightness. Conventional textbook materials and general-purpose
circuit simulators provide opportunities for problem solving and exploration but offer limited support for explaining why
circuit behavior changes or diagnosing the
reasoning behind incorrect answers. We present CircuTutor, a
circuit-state-driven intelligent tutoring system that transforms static textbook
circuit problems into an interactive tutoring workflow. CircuTutor first uses
multimodal problem parsing to extract the textbook question,
circuit topology, component parameters, switch states, and answer options, which are converted into a structured task and validated through
circuit simulation. Learners can then interactively explore the
circuit (by changing parameters) and submit an answer while a SPICE-compatible solver computes physically consistent
circuit states. After the learner submits an answer, CircuTutor presents a before-and-after
circuit state animation corresponding to the selected operation, organizes the simulated state changes into a causal
reasoning chain that explains the underlying
circuit behavior, maps answer discrepancies to likely misconceptions, and generates adaptive follow-up exercises targeted at the diagnosed misconception. Our experimental results demonstrate that CircuTutor effectively improves conceptual learning and the overall learning experience. The proposed framework demonstrates how simulated
circuit states can be transformed into intelligent and interactive tutoring for
circuit education, with the potential to generalize to other STEM domains.
Read the full abstract ▾
All authors Ziyu Luo, Xiaorui Ma, Lin Chen, Xiaoming Chen
Artificial Intelligence · Cross-listed from cs.RO
CALIPER: Clean Scenes Cannot Rank Physical Inference in Pretrained Visual Representations
Aman Mehta and Riya Baviskar
How far a pushed object slides depends on its mass and friction, which no single image reveals. Pretrained visual encoders are increasingly used as the perception front end of world models for manipulation, and their physical competence is assessed with perturbation
benchmarks and linear probes, almost always in a clean, fixed-camera scene. We show that these assessments cannot distinguish an encoder that infers physics from one that does not. CALIPER (calibrate, then predict) is a direct test: an object of unknown mass and friction is struck twice at known speeds, a third strike is shown only up to the moment of contact, and a linear readout on frozen features must predict how far the object slides. Swapping in another object's calibration clips checks that the evidence is actually used. Across 2,000 simulated episodes and eight representations, from V-JEPA 2 to a randomly initialised ViT and raw pixels, calibration adds +0.50 R^2 and the swap removes it. Yet in the clean scene every representation lands within 0.02 R^2 of the ceiling set by true simulator state, because a fixed camera exposes the object's displacement directly in pixel coordinates. Resampling camera, lighting, and clutter for every clip spreads the same representations across 0.50 R^2; when the readout chooses a push speed for a goal distance, V-JEPA 2 misses by 4 mm and the random ViT by 20 mm, no better than ignoring the object. Linear probes track none of this: a change in frame aggregation moves a probe more than pretraining does, and erasing the probed mass direction from the same representation costs nothing in one scene and 0.35 R^2 in the other. Whether a
benchmark can rank models is an empirical property, and we give three checks that establish it.
Read the full abstract ▾
Artificial Intelligence
Agentic ML Exploration (A-MLE) for Ads Ranking
Erwin Gao, Vinodh Kumar Sunkara, Jingyi Guan et al. (+36 more)
Modern industrial ads ranking stacks are increasingly bottlenecked not by model capacity or training compute, but by the throughput of human ML iteration - the cycles of research, implementation, training, debugging, evaluation, and launch required to surface a single statistically significant improvement. A typical ranking stack contains numerous differentiated models with heterogeneous data, architectures, and infrastructure constraints, and each cycle takes days to weeks of senior engineer
attention per model. As a result, techniques that have proven effective on one model diffuse into others slowly and unevenly, leaving substantial recoverable signal unexplored. We present Agentic ML Exploration (A-MLE), an autonomous LLM-
agent system that systematically explores ML techniques across a portfolio of ads ranking models. A-MLE decomposes ML iteration into five stages involving hypothesis generation, exploration strategy, experiment execution, result analysis and shared knowledge substrate which are orchestrated by a single
agent that invokes domain-specific skills and agentic workflows against a sandboxed execution layer, with human-in-the-loop checkpoints at each stage boundary. We deploy A-MLE across a representative set of large-scale ads ranking models and evaluate it along a tiered capability framework (tool availability, autonomous workflow execution, and open-ended exploration). We further report a controlled cross-LLM study using a fixed
agent loop, which surfaces qualitative differences in execution reliability and exploration aggressiveness across the Claude Sonnet, Gemini, and GPT families. We discuss failure modes and the design choices that govern reliability. Our findings suggest that agentic exploration is a practical force multiplier for ML engineers in industrial recommenders, especially for the long tail of models that rarely receive expert
attention.
Read the full abstract ▾
All authors Erwin Gao, Vinodh Kumar Sunkara, Jingyi Guan, Qinjin Jia, Hangjun Xu, Xiang Ji, Sherman Wong, Surya Teja Chavali, Pratik Vaishnavi, Aryan Pandhi, Xiaoyu Deng, Zhaodong Wang, Samarth Inani, Fan Yang, Jakob Moberg, Zoe Zu, Nicolas Bievre, Sami Khenissi, Amit Jaspal, Ehsan Fakharizadi, Srinidhi Viswanathan, Dorothy Sun, Abishek Vanam, Sneha Iyer, Sheela Yadawad, Wenjie Chen, Gaby Nahum, Junhua Gu, Peter Chu, Yucheng Liu, Xin Zhao, Vitor Cid, Chaorong Chen, Vijay Pappu, Ashwin Kumar, Wenlin Chen, Ben Schulte, Deepak Chandra, Ritwik Tewari
Artificial Intelligence
zScore-N: A Neural Network for On-Chain Wallet Reputation Scoring
Girish G N, Ashutosh Sahoo, Akshay SP et al. (+2 more)
Wallet reputation scores decide who receives an airdrop, who can borrow, and who enters an allowlist across decentralised finance. They almost always begin as hand-written formulas: compositions of clamped logarithmic, linear and square-root transforms over behavioural features, with every threshold and point award set by hand. Such a formula is readable and deterministic, but it is piecewise and non-differentiable, it cannot improve as data accumulates, and it cannot distinguish a feature that is genuinely zero from one its pipeline failed to capture. We present zScore-N, the neural network that replaced ours in production. The formula served as its teacher: calibrated against 5,208,952 wallets sampled across 2019-2024 and verified to reproduce production output to within 2.3e-13, it supplies unlimited labelled training data at zero label noise. The trained network reproduces it to 0.58 points RMSE on the 1000-point scale (R^2 = 0.99997), against 2.25 for gradient-boosted trees and 28.04 for linear regression on identical features and splits. Trained with missing-value masks against uncorrupted targets, it halves the error that incomplete data introduces: at 10% feature-level missingness the formula drifts 51.4 points from its own complete-data output with a systematic -12.5 point bias, while the network drifts 17.9. The network carries the score at production scale, across a population of millions of wallets spanning six orders of magnitude in size and activity.
Read the full abstract ▾
All authors Girish G N, Ashutosh Sahoo, Akshay SP, Gurukiran S, Dhanashekar Kandaswamy
Artificial Intelligence · Cross-listed from cs.LG
CUNO: Curriculum and Preference Optimization for Stable Graph Unlearning under Mass Deletion
Chenhan Zhang, Ali Braytee, Madhushi Bandara et al. (+4 more)
Graph unlearning removes the influence of designated training data from a trained graph model without retraining from scratch. However, existing methods suffer a sharp drop in model utility under large deletion ratios (mass deletion), a phenomenon we refer to as catastrophic unlearning. We find that a key cause is the uniform treatment of all deleted samples, which is particularly damaging in graph learning: structural dependencies cause different nodes to play vastly different roles in the learned model, yet existing methods apply the same forgetting operation to the entire forget set. Based on this insight, we propose CUNO, a curriculum-based graph unlearning framework that removes the forget set progressively, ordering samples by their estimated unlearning difficulty across multiple stages. CUNO further employs a distribution-level negative preference optimization (NPO) objective at each curriculum stage that steers the model away from its original behavior on the current forget subset while preserving retained performance. Our theoretical analysis shows that the curriculum design is most beneficial when the forget set spans a wide range of unlearning difficulty, a condition naturally satisfied under mass deletion. Comprehensive experiments confirm that CUNO consistently mitigates catastrophic unlearning: at 20% deletion, it retains 74% of the original utility compared to 26-53% for existing methods, and maintains more than half the original utility even at 50% deletion. Our code is publicly available at https://anonymous.4open.science/r/cuno-D4FF.
Read the full abstract ▾
All authors Chenhan Zhang, Ali Braytee, Madhushi Bandara, Xin Hao, Paul J. Kennedy, Massimo Piccardi, Raymond Owen
Artificial Intelligence · Cross-listed from cs.CV
CS-CLIP: Compositional Scene Graph-guided CLIP for Robust Compositional Reasoning
SeongJun Jeong, Minjoon Jung, Woo Suk Choi et al. (+2 more)
Vision-
language models (VLMs) demonstrate strong performance across compositional
reasoning benchmarks, which require
reasoning over semantic perturbations of objects, attributes, relations, and their interactions. However, our controlled analysis reveals that existing compositionality-aware VLMs exhibit element-specific biases, often underperforming vanilla CLIP on certain compositional elements. To address this, we propose Compositional Scene Graph-guided CLIP (CS-CLIP), which uses scene graphs to identify compositional elements and construct structured negatives via selective masking. We further retain negatives that are most contradictory to the original caption, forcing the model to rely on compositional structure rather than surface cues. CS-CLIP achieves state-of-the-art compositional
reasoning with robust performance across compositional elements. It also preserves general
vision-
language capabilities such as cross-modal
retrieval and downstream visual
reasoning, while requiring fewer training samples than prior methods.
Read the full abstract ▾
All authors SeongJun Jeong, Minjoon Jung, Woo Suk Choi, Youwon Jang, Byoung-Tak Zhang
Artificial Intelligence
Style Over Substance: Content-Invariant Wrappers Flip LLM Safety-Judge Verdicts
Yongxi Zhou, Wenbo Ye, Yuanzhe Liu et al. (+3 more)
Automatic safety judges – for example Llama Guard, or GPT-4o given a grading
prompt – produce the numbers behind reported jailbreak success rates, defense evaluations, and safety leaderboards. We ask whether these judges grade what a reply contains or how it sounds. We place a fixed piece of text before or after a model reply (a style wrapper) and leave the reply itself unchanged byte-for-byte, so any change in verdict is an error of the judge. Over 600 JailbreakBench replies (300 harmful, 300 refusals), 9 wrappers, and 8 judges, using paired tests and a measured per-judge repeat-disagreement rate (the noise floor), we find that most judges barely move but specific judges have specific, cheap blind spots. A
token refusal ("I can't help with that") placed before the unchanged harmful text flips 19.9% of GPT-4o-mini's correct "unsafe" verdicts to "safe" (noise floor 0.5%; 18.2% under majority-of-three re-scoring), yet moves Claude only 0.4%. The deployed Llama Guard 4 guard model is evaded by an "educational course" preface on 12.3% of harmful replies, and the flips persist across repeats, while a second deployed guard (gpt-oss-safeguard-20b) is immune. Changing only the grading
prompt to ignore tone cuts the GPT-4o-mini attack roughly tenfold on the same model, so the weakness lives in the judge, not in the content. Pure tone-only decoration that adds no new claim still flips up to 2.1% of verdicts on the vulnerable judges, several times their noise floors. On this artifact set the judges also disagree about which target model is safest, and a bootstrap shows the ranking is unstable before any wrapper is added. We release the data, wrappers, code, and per-verdict labels.
Read the full abstract ▾
All authors Yongxi Zhou, Wenbo Ye, Yuanzhe Liu, Zihan Dong, Junwei Yao, Jiahui Ge
Artificial Intelligence
SE-GoS: Self-Evolving Graph-of-Skills for Skill Library at Scale
Dawei Fu, Cheng Jiang, Sitian Qian et al. (+2 more)
LLM
agents use large libraries of reusable skills. At thousands of skill entries,
retrieval becomes the bottleneck. Graph-of-Skills (GoS) retrieves dependency-aware bundles from a typed skill graph, and SkillDAG shows that such a graph can accumulate execution-backed structure online. Neither asks whether execution traces can be distilled into a better
retrieval graph that generalizes to unseen tasks. We present Self-Evolving Graph-of-Skills (SE-GoS), which treats the
retrieval graph as an index rather than a learned representation: the graph is maintained from execution traces while the
retrieval pipeline, the skill library, and the model stay fixed. SE-GoS applies three updates: (1)
topology, which induces relations from execution evidence and retracts an avoid edge only after repeated successful co-use; (2) edge-weight, which softly attenuates unsupported semantic edges and reinforces incoming edges to used skills; and (3) node-description, which updates
retrieval-facing descriptions stored on graph nodes ranked too low. On SkillsBench, one
evolution round lifts average reward from 52.4% to 59.4%, above full-library loading, vector
retrieval, static GoS, and SkillDAG, and this ordering repeats on all three backbones.
Retrieval over the evolved graph spends about two-thirds of the input
tokens that loading the full library costs. Repeating the round does not help. The same graph improves a held-out split it never saw from 52.9% to 58.3%, so what it accumulates transfers rather than memorizes traces. Skill graphs can therefore be improved from execution experience without model training,
retrieval-
algorithm changes, skill-content modifications, or a model judging which skills are related.
Read the full abstract ▾
All authors Dawei Fu, Cheng Jiang, Sitian Qian, Huainan Wang, Zhongkai Hao
Artificial Intelligence
TTGBench: Benchmarking Topological Evolution and Semantic Drift in Text-attributed Temporal Graphs
Longfei Ma, Zemin Liu and Fei Wu
Temporal graph learning models the
evolution of dynamic systems, where both structural interactions and semantic states change over time. However, existing
benchmarks primarily emphasize structural
evolution via temporal link prediction (TLP), while support for semantic
evolution remains limited. Although temporal node classification (TNC) is sometimes included, it is typically restricted to simplistic binary settings that fail to capture realistic semantic drift. Moreover, commonly used
datasets exhibit high link repetition, leading to inflated performance estimates and obscuring true model capability. To address these limitations, we introduce TTGBench, a new
benchmark that jointly evaluates structural and semantic
evolution. TTGBench comprises six real-world, text-rich
datasets characterized by Dual
Volatility, enabling rigorous and fair evaluation of existing models. Notably, it is the first
benchmark to support both multi-class and multi-label TNC, filling a critical gap in evaluating temporal semantic drift. We conduct a comprehensive evaluation of 17 state-of-the-art methods across Temporal Graph Neural Networks (TGNNs) and Large
Language Model (LLM)-based paradigms. The results reveal a clear capability divide between the two paradigms: TGNN-based methods excel at structural prediction but fail at semantic tracking, whereas LLM-based predictors show the opposite trend. Through in-depth analysis, we uncover their fundamental limitations and provide insights for developing more comprehensive temporal graph models.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
3DWay: Generalizing Robot Manipulation via 3D Consistent Waypoints
Ziqin Huang, Yingyue Li, Chenyangguang Zhang et al. (+6 more)
Intermediate representations are key to bridging the modality gap between generalizable manipulation policies and large-scale pretrained
vision-
language models (VLMs). Among these, trajectory-based representations compactly represent motion-relevant cues, yet most existing approaches predict trajectories in 2D image space, resulting in intrinsic 3D ambiguity. Moreover, using 2D trajectories with depth still leaves the free-space waypoints ambiguous, limiting reliable 3D
reasoning. To address this, we propose predicting 3D consistent waypoints (3DWay) from multi-view images. By reformulating 3D waypoints prediction as generating multi-view consistent 2D waypoints followed by
geometric triangulation, we enable explicit 3D motion specification while preserving the strong priors of pretrained VLMs. The predicted waypoints can guide existing VLA models for better generalization or be directly executed on simple tasks. Extensive experiments show that 3DWay substantially improves 3D spatial grounding and
vision-
language reasoning, demonstrating strong potential for generalizable
robot manipulation. Codes will be released at https://github.com/ziqin-h/3DWay.
Read the full abstract ▾
All authors Ziqin Huang, Yingyue Li, Chenyangguang Zhang, Ruida Zhang, Yuxin Chen, Gu Wang, Xingyu Liu, Masayoshi Tomizuka, Xiangyang Ji
Artificial Intelligence
Vision: Data-Centric Anchoring for Robust and Interpretable Agentic AI
Arun Vignesh Malarkkan, Xinyuan Wang and Yanjie Fu
Agentic AI systems built on large
language models fail in two persistent ways that scaling does not fix: they break under distribution shift, and they cannot explain the decisions they make. We argue these are co-symptoms of one structural deficiency in the data lifecycle that governs how
agents are trained, evaluated, and deployed. Observational interaction logs record what an
agent did, not what it would have done otherwise. They encode spurious correlations without controlled variation, so they lack the counterfactual structure needed to separate causal signal from coincidence or to validate an explanation. No model-centric method can recover invariances the data never contained. We present Data-Centric Anchoring: robustness and interpretability should be engineered into the data environment, not extracted from models after training. Our central contribution is the Data-Centric Agentic Loop, a four-stage framework of Curate, Augment, Constrain, and Attribute. The ordering is structural, not stylistic. Curation precedes augmentation because generative models amplify whatever bias they are trained on. Augmentation precedes constraint because invariance objectives are vacuous without variation across environments to be invariant to. Attribution closes the loop, converting observed failures into targeted data interventions for the next iteration. Each stage manufactures the preconditions of the next, which makes the loop self-correcting rather than merely sequential. We ground the framework in a failure-driven taxonomy that links four core failure modes to the data lifecycle: spurious feature reliance, distribution-shift fragility, uncertainty miscalibration, and explanation unfaithfulness. We close with the limits of this approach and the open problems that stand between it and practical deployment at scale.
Read the full abstract ▾
Artificial Intelligence
A Better Spur Should Start From Each Objective
Shanwen Mao, Hao Zhang, Guangtao nie et al. (+4 more)
Real-world Multi-Objective Reinforcement Learning (MORL) often suffers from sparse rewards, reward conflicts, and late-stage reward tug-of-war, causing traditional linear scalarization to experience severe metric oscillations. To address optimization conflicts among multiple objectives in real-world deployment scenarios, we propose Multi-Marginal Preference Optimization (MMPO), a fine-grained framework that intervenes at the data, gradient, and constraint levels rather than relying on coarse-grained global scalarization. Specifically, MMPO performs exposure debiasing to mitigate sparse and biased rewards, applies priority-aware orthogonal projection to decouple conflicting gradients, and introduces self-prompted gradient constraints to prevent dominant objectives from overwhelming weaker ones. Experiments on real-world e-commerce
datasets show that MMPO improves training stability and consistently achieves better performance across conflicting metrics. Moreover, it generalizes robustly to broader tasks such as ToolRL and code generation, demonstrating its effectiveness as a practical paradigm for multi-objective
alignment.
Read the full abstract ▾
All authors Shanwen Mao, Hao Zhang, Guangtao nie, Zhiheng Li, Huimu Wang, Sulong Xu, Gu Simiu
Artificial Intelligence
Qiushi Engine on AstaBench E2E-Bench-Hard
Wenhao Li, Shuxing Yang, Fujia Chen et al. (+13 more)
This report analyzes Qiushi Engine v0.8 across all 40 test tasks in AstaBench E2E-Bench-Hard, a
benchmark that requires autonomous
agents to carry a research question through experimental design, code implementation, actual execution, result analysis, and report delivery. Qiushi Engine is model-configurable; this evaluation selected DeepSeek deepseek-v4pro-preview as the model backend. The official AstaBench leaderboard records a score of 0.816 and an average
benchmark cost of USD 15.209 per task, while the full-precision local recomputation is $81.59 \pm 1.87$. Four tasks satisfied every rubric item, yielding a full-task completion rate of 4/40 = 10% – 7 percentage points above, and about 3.3 times, the approximately 3% best rate reported for AstaBench's official
agents. Across 507 required rubric items, 416 were satisfied (82.1%). Official scoring archives and 40 Meta-Trace records show sustained production and verification of reports, code, and experimental artifacts; the principal gaps lie in repeated runs, external dependencies, specified metrics, and ablation studies. The report explains the
benchmark, system workflow, aggregate results, representative cases, and limits of interpretation.
Read the full abstract ▾
All authors Wenhao Li, Shuxing Yang, Fujia Chen, Jincheng Mi, Yuang Pan, Rui Zhao, Zichen Li, Junyao Wu, Shenzhan Hong, Yaqi Li, Yize Wang, Kaihao Zhu, Taowen Deng, Junjie Yang, Hongsheng Chen, Yihao Yang
Artificial Intelligence
Do Dynamic Routers Need Memory? HeRo: History-Aware Routing for Efficient LLM Inference
Hongjin Lin, Wentao Wan and Keze Wang
Dynamic layer routing reduces the inference cost of Large
Language Models (LLMs) by learning to skip layers for individual
tokens. Existing methods, however, treat each routing decision as a local operation conditioned solely on the current hidden state which is a formulation that overlooks the sequential, path-dependent nature of routing across depth: earlier decisions shape the representations seen by downstream routers, and the layer-usage objective couples all decisions jointly. We propose History-Aware Routing (HeRo), a dynamic routing framework that resolves this mismatch by introducing a router
memory mechanism to maintain an explicit routing state across model depth. The
memory is constructed via linear
attention, incrementally aggregating preceding routing scores and their induced residual updates into a compact history representation. At each routed layer, the router conditions jointly on this accumulated state and the current hidden representation to select the executed branch. Instantiated for
token-wise FFN routing, HeRo trains only lightweight routers and adapters on a frozen backbone, requiring no modification to pretrained parameters. Across Llama 3.1-8B, Llama 2-7B, and Llama 2-13B, HeRo consistently achieves the highest aggregate performance retention among ten baselines. On Llama 3.1-8B, it bypasses 26.87% of model parameters while achieving 100.24% of dense model performance across seven
benchmarks, and retains 97.01% while bypassing 38.82% of model parameters under a tighter computation budget. Ablation studies confirm that removing routing history consistently degrades performance, most notably on multistep
reasoning and code generation, validating that explicit routing
memory enables more accurate and adaptive dynamic routing than solely conditioning on hidden state.
Read the full abstract ▾
Artificial Intelligence
Bridging the Semantic-Utility Gap in Multimodal RAG via Generator-in-the-Loop Alignment
Zhan-Lun Chang, Dong-Jun Han, Seyyedali Hosseinalipour et al. (+2 more)
Vision-
language models (VLMs) augmented with
retrieval-augmented generation (RAG) benefit from access to external evidence. However, standard retrievers and rerankers optimize for semantic similarity rather than answer utility, creating a preference gap: documents that appear relevant may not help the generator produce a correct answer. Motivated by this, we propose a two-stage generator-in-the-loop
alignment framework that closes this gap without human document-level relevance annotations. Our framework consists of two stages: in Stage 1, a VLM generates a hypothetical text passage from the image-query pair, which is used as the
retrieval query for dense text search, bridging the image-to-text modality gap. In Stage 2, a cross-encoder reranker adapted with low-rank adaptation (LoRA) is fine-tuned using answer-supervised preference pairs mined from the frozen VLM: given the
dataset answer label, a candidate document is labeled positive if the VLM produces the correct answer when given that document as context, and negative otherwise. This generator-guided signal is compatible with multiple
alignment loss functions, including contrastive (triplet) loss, pairwise direct preference optimization (DPO), and supervised fine-tuning (SFT), and supports periodic re-mining to refresh preference pairs as the reranker improves. Experiments on VQA-X and A-OKVQA with Qwen3.5-2B and Qwen3-VL-4B-Instruct show that our proposed framework consistently outperforms rank-order, random, and REPLUG-style likelihood baselines under various
alignment losses and pool size settings, suggesting that answer-level generator feedback is an effective supervision signal for preference
alignment.
Read the full abstract ▾
All authors Zhan-Lun Chang, Dong-Jun Han, Seyyedali Hosseinalipour, Mung Chiang, Christopher G. Brinton
Artificial Intelligence
Does Deeper Reasoning Compromise Alignment? Revealing and Mitigating of Alignment Collapse in Large Reasoning Models
Yu-Hang Wu, Yu-Jie Xiong, Henghua Zhang et al. (+3 more)
The emergence of Chain-of-Thought (CoT) has established a robust foundation for Large
Reasoning Models (LRMs). While deep
reasoning is widely believed to enhance safety
alignment, the stability of
alignment mechanisms under extended
reasoning remains underexplored. This paper challenges the prevailing view by revealing a critical vulnerability: Deep
Reasoning May Induce
Alignment Collapse. To rigorously quantify this phenomenon, we propose the
Alignment Loss Rate (ALR) metric. Our experiments demonstrate that as
reasoning depth increases, ALR rises significantly, indicating a severe degradation in model robustness against external perturbations. Capitalizing on this instability, a novel jailbreaking paradigm,
Reasoning Trap (RT), is proposed. RT induces the model into extended
reasoning to amplify the impact of
adversarial attacks, leading to a sharp decline in safety capabilities. To elucidate the mechanism behind this collapse, we identify
Attention Dilution as the root cause, arising from the competition for
attention between the extended
reasoning process and the original input. To mitigate this,
Reasoning Residual
Alignment (RRA), a lightweight defense strategy that dynamically re-emphasizes the input via residual connections integrated with the
reasoning process.
Read the full abstract ▾
All authors Yu-Hang Wu, Yu-Jie Xiong, Henghua Zhang, Bairui Zhang, Jia-Chen Zhang, Shaohua Li
Artificial Intelligence · Cross-listed from cs.CV
WSPolypNet: Weakly Supervised Polyp Localization in Colonoscopy Videos
Giseong Hwang, Minjae Jo, Yeonghyeon Park et al. (+9 more)
Because dense frame-level annotation of colonoscopy
videos is costly, we propose WSPolypNet, a weakly supervised framework for polyp localization using only
video-level labels. WSPolypNet employs a 3D convolutional neural network trained with
video-level supervision to generate class activation maps (CAMs), which identify candidate polyp regions without requiring frame-level spatial annotations. The CAM-derived localization cues are further enhanced using a multi-view strategy and provided to MedSAM2 as point
prompts. MedSAM2 then propagates
segmentation masks across the
video, refining the coarse localization cues according to polyp boundaries. WSPolypNet achieved CorLoc scores of 47.80%, 43.68%, and 35.01% at IoU thresholds of 0.3, 0.5, and 0.7, respectively, compared with 36.87%, 33.72%, and 27.94% in the single-view setting. For small polyps, the multi-view strategy improved CorLoc@0.5 from 16.01% to 30.97%. The framework also achieved a recall of 94.51%. These results demonstrate the potential of weakly supervised spatiotemporal learning to substantially reduce spatial annotation requirements for polyp localization in colonoscopy
videos.
Read the full abstract ▾
All authors Giseong Hwang, Minjae Jo, Yeonghyeon Park, Kyeonghun Kim, Seoyeon Han, Donghoon Han, Haneul Kim, Yului Jeong, Insung Hwang, Pa Hong, Ken Ying-Kai Liao, Nam-Joon Kim
Artificial Intelligence
Less Is Personal: Learning Minimal Sufficient User Profiles for Personalized Language Models
Minghang Liu, Qiang Qiu, Yuanzhuo Wang et al. (+2 more)
Retrieval-augmented personalization enables large
language models to produce more accurate and preference-aligned outputs using relevant records retrieved from user histories. Personalized
language models typically prepend a fixed number of retrieved user records, even when additional history is redundant, harmful, or unrelated to a user's distinctive behavior. We study minimal sufficient personalization: constructing the least costly ordered profile for each input while preserving the utility achievable from a retrieved candidate pool. We introduce ENOUGH, a method that iteratively appends behavioral records or emits STOP to construct profiles with adaptive lengths. Offline, bounded counterfactual search evaluates profile prefixes by jointly considering downstream gains, user specificity, and
token costs. The resulting long-horizon targets are distilled into a multi-head value controller with explicit ranking and stopping supervision. At inference, the controller selects and orders records through lightweight decisions, and the frozen generator is invoked once after stopping. Extensive experiments on six personalized tasks demonstrate that ENOUGH consistently outperforms strong heuristic and
retrieval-augmented baselines in both effectiveness and efficiency, achieving minimal sufficient profiles that preserve personalization utility while reducing unnecessary context costs.
Read the full abstract ▾
All authors Minghang Liu, Qiang Qiu, Yuanzhuo Wang, Huawei Shen, Xueqi Cheng
Artificial Intelligence
A Theory of Reliable Self-Evolution for Agent Harnesses
Qianshu Cai, Yonggang Zhang, Jun Nie et al. (+6 more)
In harness self-
evolution,
agents modify their own
prompts, code, tools, and orchestration while keeping the underlying
language model fixed. Recent work has shown that
agents can improve themselves in response to task failures and achieve substantial performance gains. However, gains on failed tasks do not automatically ensure that performance on previously successful tasks is preserved, raising concerns about reliable adoption. In this work, we provide a theoretically grounded condition under which a self-evolved harness can be reliably adopted. We then propose a validation rule to make the evolved system satisfy the reliable adoption condition with theoretical guarantees. Consequently, the system can achieve progressive improvement through
evolution. This leads to a natural question: Does reliable self-
evolution have a performance ceiling, and which factors govern this ceiling? Our theoretical results show that the performance ceiling is determined by the costs of verification and evaluation. On the other hand, self-
evolution may stall in practice. In this regard, we show that experimental evidence on
agent performance shifts can be used to identify the sources of stagnation. Our work thus establishes a theoretical framework for understanding and advancing reliable harness self-
evolution.
Read the full abstract ▾
All authors Qianshu Cai, Yonggang Zhang, Jun Nie, Maohao Ran, Huajiang Zheng, Jun Song, Xinmei Tian, Yike Guo, Wei Xue
Artificial Intelligence
OntologyBench: Can Dense Retrieval Satisfy Structured Biomedical Constraints?
Xiao Yu Cindy Zhang, Wyeth Wasserman and Jian Zhu
We introduce OntologyBench, a tiered biomedical
retrieval benchmark comprising 471,854 training and 125,744 evaluation query-document relevance pairs across concept grounding, relational
retrieval, and compositional phenotype-based
retrieval. Although these tasks can be tractable using ontology-aware reference methods, across task tiers,
embedding performance is generally lower on relational and compositional tasks than on concept-grounding tasks. Fine-tuning on ontology-derived supervision improves performance on several relational and compositional tasks, whereas the evaluated reranking and LLM-based candidate-scoring methods provide little or no end-to-end improvement. Errors frequently reflect diseases matching only subsets of the phenotype evidence. These findings indicate that the evaluated
embedding and reranking configurations do not reliably recover the compatibility encoded by the selected ontology relations and phenotype combinations and motivate
retrieval systems that better integrate learned representations with structured biomedical knowledge.
Read the full abstract ▾
Artificial Intelligence
Key Path Identification for Resolving Knowledge Conflicts via SAE-based Steering
Wenbo Zhang, Zhongxiang Sun, Zhiguang Han et al. (+1 more)
Sparse autoencoder (SAE)-based steering has been widely used to address knowledge conflicts by guiding LLMs to be more faithful to the contextual knowledge. Existing methods usually perform mass steering, which modifies a large batch of SAE features identified via correlation-based methods. However, due to the inaccurate correlation and the neglected feature interactions, mass steering methods fail to precisely identify the features that play the key roles in steering and introduce a large number of redundant ones, which add noise and weaken the steering effects. Our empirical studies reveal that steering only a small subset of the identified features can achieve comparable or even better performance. Motivated by this finding, we propose Key Path Identification (KPI), a novel method that identifies key steering features characterized by strong causal dependencies with both upstream and downstream features. From these features, KPI constructs key paths and steers through less feature modifications. In this way, KPI advances SAE-based steering from quantity-driven to quality-focused, offering a perspective for more precise and interpretable model editing. Experiments in RAG tasks with knowledge conflicts show that our method improves the accuracy by 18% on average compared to the best baseline of mass steering, effectively filtering redundant features, alleviating side effects and demonstrating the core role of key paths in steering.
Read the full abstract ▾
All authors Wenbo Zhang, Zhongxiang Sun, Zhiguang Han, Jun Xu
Artificial Intelligence · Cross-listed from q-fin.GN
AI for AI: Optimizing Additional Infrastructure Build-out to Power Artificial Intelligence Data Centers
Alexander Crosier, Kyle Onghai and Ronnie Sircar
The twenty-first century's transformative technology, artificial intelligence, is increasingly constrained by the twentieth century's transformative technology, the electricity grid. Rapid growth in electricity demand from data centers is leading to higher electricity prices, without a compensating supply-side response. We develop a framework linking data-center load growth, available generation capacity, and
market-clearing prices to understand this phenomenon. We first analyze a deterministic model to show how differing estimates of demand and supply growth rates affect prices. We then model the expansion of new data centers and their associated electricity demand, together with build-outs of new electricity supply, as
stochastic processes,resulting in probabilistic distributions of supply, demand, and prices rather than a single forecast. Finally, we formulate generation expansion as a
stochastic control problem in which a revenue-maximizing investor dynamically chooses the intensity of supply-side investments. The analysis highlights a central challenge of the data-center build-out: even when rapid demand growth increases the need for new generation, the uncertainties related to load forecasts, development execution risks, and value cannibalization from overbuilding capacity may weaken incentives to invest at the pace required to keep electricity prices stable.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
Dual-Layer Semantic-Spatial Belief Mapping for Aerial Object Goal Navigation
Jianqiang Xiao, Xiang Deng, Yuexuan Sun et al. (+3 more)
Aerial Object Goal
Navigation (ObjectNav) requires an unmanned aerial vehicle (
UAV) to locate a described target in an unknown outdoor environment using onboard visual observations.
Vision-
language models (VLMs) can interpret open-ended target descriptions and visual observations, but their frame-level outputs are often noisy, sparse, and spatially transient. We propose AeroBelief, a dual-layer semantic-spatial belief mapping framework that transforms transient VLM observations into persistent spatial guidance. It separates broad contextual plausibility from target-specific evidence: an intuition layer accumulates scene-level semantic cues for exploration, while an evidence layer preserves qualified target-specific observations for approach and confirmation. Evidence-gated fusion combines the two layers into spatial belief hotspots. We further introduce object-conditioned visual
reasoning with conservative evidence qualification to improve observation reliability before spatial accumulation. In parallel,
egocentric regional guidance converts quadtree coverage into
UAV-centered, yaw-aligned directional proposals and stabilizes them through temporal commitment. Its regional scoring is independent of semantic belief values, maintaining exploration pressure and reducing repeated low-gain search. Experiments on the
UAV-ON
benchmark show that AeroBelief achieves the best reported overall SR, OSR, and SPL among the compared methods, reaching 21.61%, 35.57%, and 10.62, respectively. These results support the effectiveness of persistent semantic-spatial belief, conservative evidence qualification, and temporally stable regional guidance for aerial ObjectNav.
Read the full abstract ▾
All authors Jianqiang Xiao, Xiang Deng, Yuexuan Sun, Yanjin Wu, Wenbiao Yan, Liqiang Nie
Artificial Intelligence
WorldAgen: Unified State-Action Prediction with Test-Time World Model Training
Chi Wan, Kangrui Wang, Yuan Si et al. (+2 more)
How can
vision-
language-action (VLA) models adapt to new environments where world dynamics shift? While recent research has combined world modeling and action prediction to improve VLA performance, existing methods largely rely on pretraining on static
datasets, without mechanisms for active adaptation at deployment time. As a result, these models often fail to generalize when deployed in unseen scenarios with novel object configurations or dynamics. We present WorldAgen, a unified framework that jointly learns world modeling and action prediction while enabling Test-Time Training (TTT) to adapt to new environments. WorldAgen employs a shared
Transformer backbone with two heads: (1) a world model head that predicts future states from past state-action trajectories, and (2) an
agent model head that predicts actions conditioned on task instructions. We design a Mixed Unidirectional
Attention Mask to separate these two models. During test time, WorldAgen samples exploratory actions, collects ground-truth state transitions, and performs lightweight TTT updates to refine its world model. This adaptation improves the model's understanding of the environment and leads to more accurate action predictions. Experiments on the CALVIN and LIBERO
benchmarks demonstrate that our baseline model achieves comparable, and in some cases superior, performance to current state-of-the-art approaches. Moreover, with TTT on a small number of samples, our method surpasses existing state-of-the-art models, highlighting the effectiveness of adapting world models at inference time.
Read the full abstract ▾
All authors Chi Wan, Kangrui Wang, Yuan Si, Pingyue Zhang, Manling Li
Artificial Intelligence
SWE-Bench Pro Verified: A Reliable Benchmark for Software Engineering Agents
Pujun Zheng, Zixin Shang, Shufan Jiang et al. (+5 more)
SWE-Bench Pro has emerged as a standard
benchmark for evaluating software engineering
agents on challenging repository-level tasks. However, our analysis work show that its evaluation is undermined by two sources of unreliability: reward hacking, enabled by leakage of gold solutions or hidden evaluation information, and task quality issues, including misleading problem statements and improperly scoped tests. These issues can inflate
benchmark performance and obscure
agents' true coding ability. We present SWE-Bench Pro Verified, a verified version of SWE-Bench Pro that addresses both problems. Our approach combines anti-hacking safeguards that eliminate major leakage channels without disrupting normal
agent functionality, with task refinement that minimally corrects inconsistencies within flawed instances. Evaluations on SWE-Bench Pro Verified reveal that some models perform substantially worse than previously evaluated, suggesting that existing results on SWE-Bench Pro may overestimate real software engineering capability. SWE-Bench Pro Verified offers a more trustworthy
benchmark for assessing software engineering
agents.
Read the full abstract ▾
All authors Pujun Zheng, Zixin Shang, Shufan Jiang, Wenhui Tian, Dongsheng Zhu, Zerun Ma, Dingbo Yuan, Qi Zhang
Artificial Intelligence · Cross-listed from cs.CL
IGT @ FinMMEval 2026 Task 2: Question-Type Prompting with Targeted Extraction for Multilingual Financial QA
Yuwen Chiu
We present the IGT system for PolyFiQA Task 2 of the FinMMEval Lab at CLEF 2026, a
multilingual financial question answering task over English SEC filings and
multilingual news articles (English, Chinese, Japanese, Spanish, Greek) for four companies. Our central observation is that the 344 development questions divide into two families requiring fundamentally different approaches: structured numeric types (R&D ratio, cash flow, capital expenditure) are best answered by direct keyword extraction on filing text, while synthesis types (investment strategy, capital allocation, top-three revenue focuses) require rule-based
multilingual news passage selection. A
dataset analysis reveals that 17-18 of 19 ground-truth reference answers per synthesis type share an exact evidence label prefix, whose unigram
tokens contribute directly to ROUGE-1 overlap. The final system achieves development ROUGE-1 approximately 0.395, a 60% relative improvement over a generic RAG baseline (approximately 0.247), and ranks 3rd of 12 teams on the official test set with ROUGE-1 = 0.3071, Precision = 0.2821, and Recall = 0.4044.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
KBBQ: A Predictive Noise Law and the Limits of Spectrum Flattening in FP4 Quantization
Lexington Whalen, Yuki Ito and Ryo Sakamoto
We develop a second-order theory of quantization noise in
matrix multiplication in which the quantization format is characterized by the variance it assigns to each element. The constant variance profile of integer quantization recovers existing integer-noise theory, while the multiplicative profile of floating-point rounding reduces the data dependence to a scalar, the participation factor $\kappa$, yielding a closed-form signal-to-noise-ratio law. The resulting functional also admits a closed-form upper bound $\kappa^{*}$ that no function-preserving linear transform can exceed and that is attained by a recent state-of-the-art method. Building on this analysis, we introduce KBBQ (Kappa-Braked Blockwise Quantization), which parameterizes the extent to which a transform approaches this ceiling. At W4A4, across four base models and two FP4 formats, KBBQ outperforms the prior state of the art without additional deployment-time computation.
Read the full abstract ▾