Academic Intelligence · Curated Daily

Explore the Frontier of Global Academia

AcademicHub aggregates real-time literature from top journals and preprint platforms. Build your personal research radar and let large language models compile cross-disciplinary analysis briefings automatically.

01.
medRxiv (Medicine) 2026-06-18

Age as a moderator of a brief alcohol intervention among injury patients in Northern Tanzania

Background: Alcohol use is a leading modifiable risk factor for injury in sub-Saharan Africa. In Tanzania, young people ([≤]24 years) experience greater alcohol-related harm despite drinking less frequently than adults. Punguza Pombe kwa Afya Yako (PPKAY) is a culturally adapted, brief intervention for injury patients in Tanzania. This study examined whether age moderates its effectiveness. Methods: We conducted an exploratory secondary analysis of baseline and 3-month data from the PPKAY randomized trial among injury patients aged [≥]18 years at Kilimanjaro Christian Medical Centre, Tanzania. Eligible participants reporting alcohol use before injury, AUDIT [≥]8, or positive breathalyzer were randomized to usual care or PPKAY with SMS boosters. The primary outcome was binge drinking days. Count outcomes were analyzed using negative binomial regression with robust SEs and continuous outcomes using mixed-effects models. Effect modification was assessed using a three-way interaction (Time x intervention x Age). Results: Among 543 participants (mean age 36.8 years; 16.2% aged 18–24), age moderated the intervention effect for drinking days (IRR = 0.27, 95% CI 0.07 – 0.98; p = 0.046) and drinks consumed (IRR = 0.17, 95% CI 0.04 – 0.77; p = 0.021). The intervention reduced 4 drinking days (95% CI -7.1 to -0.8) and 27.5 drinks (95% CI -42.8 to -12.2) among young people, while adults showed reductions in both arms, without intervention-specific effect. Conclusion: The effects of ED-based brief alcohol interventions are not uniform, varying across both age groups and alcohol-related outcomes. We found a greater responsiveness in drinking frequency and quantity reported among young people.

02.
arXiv (CS.AI) 2026-06-16

Skill-to-LoRA: From Using Skills to Learning Behaviors for Token-Efficient LLM Agents

arXiv:2606.16769v1 Announce Type: new Abstract: Agent skills are commonly distributed as SKILL.md files: human-readable procedural documents that describe workflows, tools, resources, and domain conventions. While convenient for inspection and reuse, this design requires the same reusable procedure to be repeatedly injected into the runtime context. We propose Skill-to-LoRA(S2L), a behavior-centric skill representation that replaces runtime skill text with skill-specific LoRA adapters. Rather than compressing the skill document itself, S2L models the behavioral change induced by the skill text: offline, the complete SKILL.md is used to synthesize skill-guided demonstrations; online, the full document is omitted and the corresponding LoRA adapter is dynamically loaded to activate the learned skill behavior. We evaluate S2L with Qwen3.6-27B on a 21-skill subset of SWE-Skills-Bench. Compared with the no-skill and Full Skill Text baselines, S2L improves pass rate by 2.9 and 5.2 percentage points, respectively, while reducing per-step token cost by 6.6% relative to Full Skill Text prompting. S2L matches or improves Full Skill Text on 18/21 skills and the no-skill baseline on 15/21 skills. Control experiments further show that the gains depend on skill-specific adapter alignment: Wrong-LoRA and Shared-LoRA both reduce performance. These results suggest that many procedural agent skills can be converted from runtime instructions into trainable, dynamically loadable behavioral modules. Code will be released upon acceptance.

03.
arXiv (CS.CL) 2026-06-12

PersonaDrive: Human-Style Retrieval-Augmented VLA Agents for Closed-Loop Driving Simulation

Closed-loop driving simulators typically populate their environments with non-ego traffic agents that behave largely the same way, produced either by rule-based traffic managers or by learned models trained toward a single behavioral mode. Recent work introduces style variation through post-hoc labels on observational data or LLM-inferred reward weights, but these signals act as proxies for what a style should reward rather than demonstrations of humans explicitly asked to drive in that style. We introduce PersonaDrive, a pipeline that conditions a vision-language-action (VLA) driving agent on retrieved demonstrations from a style-instructed human driving dataset, in which participants drive CARLA leaderboard routes under aggressive, neutral, and conservative instructions on a driver-in-the-loop rig. The pipeline has three stages: (i) offline triplet mining over per-style human driving data using a combined image-text similarity score; (ii) training a lightweight retrieval head that fuses frozen visual features with a small control encoder over per-style databases; and (iii) fine-tuning a single VLA backbone to treat retrieved context points as in-context behavioral demonstrations during waypoint prediction. At inference, the same backbone is conditioned on any style by swapping which per-style database the retrieval head queries, so selecting a style requires no per-style retraining while enabling human-style, style-diverse non-ego agents for closed-loop simulation. On Bench2Drive, PersonaDrive (no style) improves the driving score by 4.6% over SimLingo and 2.5% over HiP-AD, and under style conditioning attains the highest driving score in every style within a roughly 2% band (its weakest style surpassing the strongest baseline, DMW, by 5.4%), while average speed and acceleration rise by 18% and 25% from the conservative to the aggressive instruction.

04.
arXiv (CS.AI) 2026-06-16

CAP: Towards PPG Universal Representation Learning with Patient-level Supervision

arXiv:2606.15284v1 Announce Type: cross Abstract: Photoplethysmography (PPG) plays a central role in wearable health monitoring and clinical decision support. Yet existing approaches to universal PPG representation learning largely focus on signal-level objectives and often overlook patient-level health context, which limits generalization to complex clinical tasks and heterogeneous cohorts. To address this gap, we construct a large-scale paired PPG-EHR multimodal dataset by distilling fragmented medical histories and clinical records into cohesive, patient-level electronic health records (EHR). Building on this resource, we propose Clinical Anchored Pretraining for PPG (CAP). During pretraining, CAP performs cross-modal contrastive alignment that anchors PPG representations to patient-level clinical semantics, guiding the encoder beyond waveform fitting toward modeling consistency in a patient's overall physiological state. During downstream adaptation, the pretrained PPG encoder provides clinically grounded representations that strengthen inductive bias and improve robustness and transferability. Experiments demonstrate that CAP consistently outperforms strong baselines on four diverse downstream tasks. CAP achieves a particularly large gain on respiratory rate prediction (up to +87.6% relative improvement over the state-of-the-art baseline) and delivers an average relative +26.7% across all tasks. We further enhance the interpretability of our approach through comprehensive analyses, including ablations and multiple complementary visualizations of the learned representations. The code for our experiments is available at: https://github.com/gody123gody/CAP .

05.
arXiv (CS.CV) 2026-06-11

Natural-Language Temporal Grounding in Hour-Long Videos is a Search Problem: A Benchmark and Empirical Decomposition

Temporal grounding–returning the interval $[t_s, t_e]$ for a natural-language query over a video–is the language interface to long-form video, yet has been studied on short videos; the dynamics of hour-scale natural-language grounding remain underexplored. We take the position that at hour-scale, the binding constraint is search, not recognition: Video-LLMs are bottlenecked not by localizing a nearby event, but–given a natural-language query–by searching for the relevant region of a long video. To test this, we release ExtremeWhenBench, the first open hour-scale grounding benchmark (2,273 queries over 194 videos, mean 75.7 min, max 9 hr) with an open-form query distribution. Every open Video-LLM collapses while a frame-level retrieval baseline outperforms them; a failure taxonomy attributes 85% of failures to search; and a retrieve-then-ground hybrid recovers 6.7x over the monolithic Video-LLM–mirroring retrieve-then-read in open-domain QA.

06.
arXiv (CS.CL) 2026-06-16

Understanding LLM Reasoning for Abstractive Summarization

Reasoning has substantially improved Large Language Models (LLMs) on analytical tasks such as mathematics and code generation, but its value for abstractive summarization remains unclear. To address this gap, we adapt general reasoning strategies to the summarization setting and conduct a large-scale comparative study of 8 reasoning strategies and 3 Large Reasoning Models (LRMs) across 8 diverse datasets, evaluating both summary quality and factual faithfulness. Our results show that reasoning is not a universal solution and its effectiveness depends strongly on the strategy and the summarization setting. In particular, we find a trade-off between summary quality and factual faithfulness. Explicit reasoning strategies often improve reference-based quality, but may weaken factual grounding, whereas implicit reasoning in LRMs shows the opposite tendency. We further find that increasing an LRM's internal reasoning budget does not reliably improve summarization and can even reduce factual consistency. These findings suggest that, for summarization, more reasoning is not always better. Effective reasoning should preserve faithful compression rather than induce over-elaboration. Our source code is publicly available.

07.
arXiv (quant-ph) 2026-06-15

Path superposition activating perfect quantum teleportation ability for separable states

arXiv:2505.11398v2 Announce Type: replace Abstract: Quantum teleportation is a quintessential quantum communication protocol that enables the transmission of an arbitrary quantum state between two distant parties without physically transmitting the state with the help of shared entanglement and limited classical communication. We show that it is possible to relax the entanglement requirement in quantum teleportation if we have access to a certain strain of superposition of quantum processes. Two types of superposition of quantum processes are generally considered in the literature: superposition of paths identified with quantum maps and superposition of indefinite causal orders of the maps. We find that when superposition of paths is incorporated in the protocol, quantum teleportation with unit fidelity becomes possible with nonzero probability of 1/4 even when the two parties share certain classes of separable states, including pure product states. In contrast, the assistance of superposition of indefinite causal order of quantum maps in teleportation protocol does not enable any quantum advantage for shared pure product states. Furthermore, we show that separable Werner states can also yield quantum advantage in quantum teleportation assisted by the superposition of paths. Finally, we establish that the presence of quantum coherence in the control qubit is both necessary and sufficient to achieve quantum advantage in quantum teleportation assisted with superposition of paths. The results potentially uncover yet another role of quantum superposition, in general, in teleportation versus entanglement.

08.
arXiv (CS.CL) 2026-06-19

A Layered Security Framework Against Prompt Injection in RAG-Based Chatbots

Prompt injection is ranked as the most critical vulnerability in large language model (LLM) deployments by the OWASP Top 10 for LLM Applications, yet existing defenses operate at isolated pipeline stages and remain incomplete. Input filters cannot inspect retrieved documents, while output monitors cannot prevent malicious payloads from reaching the model. Consequently, retrieval-augmented generation (RAG) chatbots remain vulnerable to indirect injection, where a poisoned knowledge-base document compromises every user whose query retrieves it. We present a three-layer framework that intercepts both direct and indirect prompt injection throughout the inference pipeline. Layer 1 screens user input using a rule-based pattern library and a fine-tuned semantic anomaly classifier. Layer 2 enforces a provenance-based instruction hierarchy during context assembly, preventing retrieved content from overriding operator policy. Layer 3 audits model output using a policy rule engine and semantic drift detector before delivery. A continuous audit loop aggregates structured logs and supports retraining to adapt the classifier to emerging attack patterns. The framework is model-agnostic and deploys as middleware without modifying the underlying LLM. Evaluation on 5,080 samples across GPT-4o, Llama 3, and Mistral 7B shows that the framework reduces Attack Success Rate (ASR) from 71.4\% to 11.3\%, outperforming the best single-layer baseline by 27.3 percentage points and a published guardrail system by 23.8 percentage points, while maintaining a 4.8\% false positive rate and a median latency overhead of 61.2 ms. Ablation studies confirm that all three layers provide complementary protection and that their combined effect exceeds the sum of individual contributions.

09.
PLOS Computational Biology 2026-06-05

Heuristic multi-site optimization for protein sequence design using Masked Protein Language Models

Authors:

by Lijuan Wang, Yuze Wang, Chen Qiu, Liwei Xiao, Xianliang Liu, Junjie Chen Protein sequence design for tailored functional properties is a fundamental task in protein engineering, with critical applications in drug discovery and therapeutic development. Efficient navigation of the combinatorial vastness of protein sequence space to identify functional variants remains a formidable challenge. Conventional approaches, which predominantly rely on template-based local search or single-residue mutagenesis, are constrained by their susceptibility to local optima and their potential risk of destabilizing native structural stability. In this study, we introduce ProtHMSO, a heuristic multi-site optimization framework leveraging masked protein language models (ProtLMs) for context-aware sequence exploration. ProtHMSO mimics natural evolutionary mechanisms by employing ProtLM-derived substitution probabilities to guide heuristic searches for synergistic mutations, thereby constraining combinatorial search spaces through evolutionary and biophysical priors. ProtHMSO is further applied to replace the exploration strategies in genetic algorithms (GAs) and Monte Carlo tree search (MCTS) for improving their convergence efficiency. Benchmark experiments demonstrate that protein sequences generated by ProtHMSO exhibit superior functional performance and closer alignment with natural sequence distribution, compared with state-of-the-art methods. These advancements highlight that ProtHMSO has strong potential and compatibility to accelerate functional protein discovery, offering a robust framework for efficient and context-aware exploration of protein sequence space.

10.
arXiv (CS.AI) 2026-06-16

Phase-Aware Guidance Injection for Recurrent MAPPO in Assembly-Line Disruption Recovery

arXiv:2606.16330v1 Announce Type: new Abstract: Disruption recovery in industrial assembly lines requires timely decisions under machine faults, worker absence, and emergency orders. Existing methods either rely on rigid handcrafted recovery logic or learn adaptive policies that do not readily exploit heterogeneous external recovery knowledge at decision time to reduce abnormal recovery time (ART) and preserve on-time delivery (OTD). To address this gap, we propose a phase-aware guidance injection framework that augments a trained recurrent MAPPO (RMAPPO) scheduling policy through logit-level action bias during evaluation. The framework provides a unified decision-time interface for rule-based, replay-based, and online LLM-based guidance, while activating intervention only during abnormal and recovery phases. Experiments on a custom AssemblyLineEnv show that high-quality rule guidance yields the strongest gains, replay-based guidance degrades smoothly under imperfect availability, and online LLM guidance still provides useful intermediate improvements. These results show that decision-time guidance injection can exploit heterogeneous recovery hints without redesigning the actor.

11.
arXiv (CS.LG) 2026-06-19

Minimal Filling Architectures of Polynomial Neural Networks: Counterexamples, Frontier Search, and Defects

arXiv:2605.09609v2 Announce Type: replace Abstract: We provide counterexamples to the unimodal minimal filling architecture conjecture for polynomial neural networks (PNNs) with power activation functions. Fixing the input and output widths, the conjecture states that any minimal filling architecture has unimodal widths for the hidden layers. We found counterexamples via a frontier search, recursive dimension bounds on neurovarieties, and symbolic computation. Notably, several subarchitectures of our main example exhibit large defect, in contrast with the predominantly small-defect behavior observed in prior literature.

12.
arXiv (quant-ph) 2026-06-16

No Universal Purification in Quantum Mechanics

arXiv:2509.21111v2 Announce Type: replace Abstract: Many central tasks in fundamental physics and quantum information processing are possible only insofar as mixed quantum states can be made purer. In this work, we prove that the linearity and positivity of quantum mechanics impose general restrictions on quantum purification, unveiling a new fundamental principle of quantum information processing. We first establish that no quantum operation can transform a finite number of copies of an unknown quantum state or channel into an exactly pure output that depends non-trivially on the input, thereby ruling out an important form of universal purification in both static and dynamical settings. Building on this, we show that, upon relaxing the requirement of exact purity, one can establish quantitative sample-complexity lower bounds for approximate purification that hold for arbitrary physically allowed strategies, whose scaling matches the performance of purification-related tasks across several different areas of quantum information processing. Moreover, this lower bound leads to a generalized standard quantum limit for learning arbitrary functions of a quantum state, greatly extending earlier results based on quantum Fisher information and revealing a deep connection between purification and quantum learning. Extending this principle to other important settings, we establish, for the first time, an exponential sample-complexity lower bound for approximate pure dilation state preparation and a no-go theorem for approximate bosonic Gaussian state purification with passive Gaussian operations, establishing much more stringent limitations under practical operational constraints.

13.
arXiv (quant-ph) 2026-06-19

Accelerated Rydberg electromagnetically induced transparency quantum memory via shortcuts to adiabaticity

arXiv:2603.18399v2 Announce Type: replace Abstract: Electromagnetically induced transparency (EIT) enables coherent light-matter storage, forming the basis of photonic quantum memories that are essential for scalable quantum networks and distributed quantum computing. However, accelerating the storage process violates the adiabatic condition, resulting in the excitation of the lossy intermediate state and a reduction in writing efficiency. We propose and numerically investigate a high-speed, high-fidelity quantum storage scheme by incorporating a shortcut-to-adiabaticity (STA) technique based on counter-diabatic (CD) driving. By introducing a precisely engineered auxiliary field into a conventional EIT system, our protocol significantly shortens the writing time beyond the conventional adiabatic limit while effectively suppressing the transient population of the lossy intermediate state. Furthermore, our scheme demonstrates strong flexibility in pulse design, remaining effective across different temporal profiles of both the control and signal fields. It also exhibits robustness against imperfections in the CD drive. Even with imperfect single-photon writing and non-ideal Rydberg blockade, the scheme retains clear advantages, maintaining high storage performance and overcoming the intrinsic speed-fidelity trade-off of traditional EIT protocols. These features pave the way for fast and robust quantum devices suitable for high-throughput quantum repeaters and advanced quantum information processing.

14.
arXiv (CS.LG) 2026-06-16

{\alpha}-Fair Insurance Pricing: A Fairness Continuum

arXiv:2606.14898v1 Announce Type: new Abstract: Fairness in insurance pricing remains a long-standing and deeply debated puzzle. On one hand, insurers, driven by profitability considerations, set premiums that differentiate across individual risks to achieve actuarial fairness. On the other hand, insurance serves a critical societal function by pooling risks across a population, motivating cross-subsidization among groups to promote solidarity fairness. The tension between these two competing notions of fairness makes insurance pricing inherently complex, particularly in modern settings where granular data allow for increasingly fine risk differentiation and regulators face growing pressure to protect vulnerable groups. To address this challenge, we propose an $\alpha$-Fair Individual Solvent Premium ($\alpha$-FISP) framework for insurance pricing that explicitly captures the trade-off between actuarial and solidarity fairness while guaranteeing solvency, a fundamental requirement in insurance operations. We formulate the pricing problem as a constrained optimization task, where actuarially fair premiums are adjusted subject to budget constraints on cross-subsidization within each risk class. This formulation naturally yields a family of solutions parameterized by $\alpha$, tracing a continuum between purely actuarial and purely solidarity-based pricing and enabling decision-makers to select an operating point along this fairness spectrum. We derive theoretical guarantees for the proposed framework. Numerical experiments show that $\alpha$-FISP is computationally tractable and aligns well with the U.S. regulatory regimes featuring heterogeneous state-level fairness requirements.

15.
arXiv (CS.CV) 2026-06-12

Revisiting Vehicle Color Recognition in Long-Tailed Surveillance Scenarios

Vehicle color recognition is an important cue for vehicle identification in surveillance systems, especially when license plates are illegible due to low resolution, occlusion, motion blur, or poor illumination. However, real-world vehicle color distributions are highly imbalanced, making overall accuracy insufficient to assess performance on rare but operationally relevant colors. This paper presents a comprehensive study of vehicle color recognition under severe class imbalance using UFPR-VeSV, a challenging real-world surveillance dataset. We investigate synthetic minority-class augmentation through two off-the-shelf generative strategies: text-conditioned image generation with RunDiffusion/JuggernautXL and image-conditioned color editing with Gemini 2.0 Flash. The curated synthetic data are combined with modern visual representations, loss reweighting, learning-rate scheduling, color-safe augmentation, foreground-aware preprocessing, and ensemble fusion. The bestperforming approach achieves 94.6% micro accuracy and 79.7% macro accuracy, improving macro accuracy by 8.2 percentage points over recent literature. A manual error analysis further shows that many remaining failures are visually ambiguous even for human annotators, highlighting the practical limits of color-based vehicle identification in unconstrained surveillance imagery. The generated images and source code are publicly available at https://github.com/viniciusorru/vcr-synthetic

16.
arXiv (CS.CL) 2026-06-18

BCL: Bayesian In-Context Learning Framework for Information Extraction

Existing information extraction (IE) tasks increasingly adopt in-context learning (ICL) with large language models. However, current approaches either show inconsistent performance across model scales or lack systematic optimization and generalizability. Building on this, we propose BCL (Bayesian In-Context Learning Framework for Information Extraction), the first optimization framework that uses particle filtering with Bayesian updates to systematically refine label representations across IE tasks. Through four steps initialization, observation, weight update, and resampling, BCL generalizes to both sequence labeling and relation classification paradigms. Extensive experiments demonstrate substantial and consistent improvements over existing approaches.

17.
arXiv (CS.CL) 2026-06-16

LM-SPT: LM-Aligned Semantic Distillation for Speech Tokenization

With the rapid progress of speech language models (SLMs), discrete speech tokens have emerged as a core interface between speech and text, enabling unified modeling across modalities. Recent speech tokenization approaches aim to isolate semantic information from low-level acoustics to better align with language models (LMs). In particular, previous methods use self-supervised learning (SSL) teachers such as HuBERT to extract semantic representations, which are then distilled into a semantic quantizer to suppress acoustic redundancy as well as capture content-related latent structures. However, these tokenizers often operate at relatively high frame rates, producing token sequences significantly longer than their textual counterparts and hindering seamless integration with pretrained LMs. Although recent methods attempt to reduce the token rate by applying uniform average pooling to SSL features, this can over-smooth content-bearing regions and dilute the structural information, thereby potentially limiting the LM alignment. To address this, we propose LM-SPT, an LM-aligned speech tokenization method based on semantic speech-resynthesis distillation. Instead of directly matching teacher and student features via pooling, LM-SPT resynthesizes speech from semantic tokens only and minimizes the discrepancy between representations extracted from the original and resynthesized waveforms using a frozen, LM-aligned speech encoder. This indirect supervision avoids rigid temporal alignment and encourages dedicated semantic units that are more semantically aligned with LMs under reduced frame rates. Experimental results show that the proposed LM-SPT consistently outperforms previous semantic-enhanced speech tokenizers when applied to SLMs for the tasks of automatic speech recognition and text-to-speech, even without compromising the speech reconstruction fidelity at the codec level.

18.
arXiv (quant-ph) 2026-06-16

Bath memory as a precision resource in quantum transport

arXiv:2606.17026v1 Announce Type: new Abstract: Structured baths can reshape transport fluctuations in mesoscopic quantum devices, yet a predictive criterion for when this enhances precision has been lacking. We propose a route towards such precision advantages by utilizing bath memory in coherent fermionic transport through a noninteracting quantum-dot chain. Using the Landauer-Büttiker formalism, we derive a dual impedance-matching condition that synchronizes the conductor mode splitting, boundary dissipation, and bath bandwidth, and sustains constructive multimode interference across the transmission window. The analytical predictions for the optimal bath bandwidths show excellent agreement with exact nonequilibrium Green's function calculations of the transport for Lorentzian, Gaussian, and Newns spectral densities. The prescription yields an optimal bath bandwidth at which the current Fano factor is minimized and the thermodynamic and kinetic precision coefficients are simultaneously enhanced beyond their Markovian limits. The alignment of the optimal precision regime with the experimentally accessible current Fano factor minimum thus provides a practical strategy for designing precision-enhanced transport in mesoscopic platforms such as semiconductor quantum-dot arrays and ultracold fermionic channels.

19.
arXiv (CS.CL) 2026-06-19

Self-Preference Is Weak or Absent in Verifiable Instruction-Following Revision: A Four-Model Test Under Genuine Authorship

Large language models (LLMs) increasingly review and revise text, including their own. A documented self-preference bias (models favoring their own generations when acting as judges) raises the question of whether models also resist valid corrections to their own writing. We test this in a setting where "valid" is decided not by another model but by a deterministic verifier: instruction-following revision on IFEval. A model writes a draft; the official IFEval checker confirms the draft violates a constraint and that a candidate edit fixes it; the model then accepts or rejects that edit either as the genuine in-context author or as a fresh model that sees the draft neutrally. Across four mid-tier model families and 85 author-versus-fresh comparisons, we find no detectable self-preference: authors reject verified-good fixes to their own drafts at essentially the same rate as fresh models judging the same drafts (gap -5.1 pp, 95% CI [-12.9, +2.7]). A self-skepticism hint from a smaller pilot did not replicate at scale. The one robust observation is qualitative: when authors do reject a verified-good fix, 97% of their stated reasons are flaw-catching rather than preference, that is, about the character of rejections, not an elevated rate. Effects smaller than ~13 pp cannot be excluded at this sample size.

20.
arXiv (CS.AI) 2026-06-19

Reward as An Agent for Embodied World Models

arXiv:2606.19990v1 Announce Type: new Abstract: While RL has become a promising tool for refining world models, existing methods largely rely on conservative rollouts near the training distribution, limiting exploration, behavioral diversity, and richer dynamic discovery. In this work, we challenge this conservative paradigm. We argue that the core limitation is not exploration itself, but the lack of reliable verification strategies to support broader exploration. Without reliable verification, expanded exploration becomes highly susceptible to reward hacking, where policies exploit imperfect rewards without achieving genuine improvement. To evaluate this motivation, we instantiate our method in embodied world models, where physical plausibility, and task completion provide a rigorous testbed for scalable RL under complex dynamics. On the verification side, we introduce Reward as an Agent, an agentic reward framework that actively evaluates generated behaviors to provide robust reward signals and mitigate reward hacking under distribution shifts. On the exploration side, we introduce Dynamic-Aware Rollout Diversification through DynDiff-GRPO, which explicitly expands action-space exploration to diversify trajectories, broaden state-action coverage, and encourage richer embodied behaviors beyond conservative rollout regimes. By unifying Reward as an Agent with DynDiff-GRPO, we enable RL on a more reliable reward foundation with substantially diversified sampling, effectively mitigating reward hacking while yielding significant accuracy gains across multiple open-source world models, thereby demonstrating that broader exploration can scale successfully when grounded in robust verification.

21.
arXiv (CS.AI) 2026-06-16

DynaDebate: Breaking Homogeneity in Multi-Agent Debate with Dynamic Path Generation

arXiv:2601.05746v2 Announce Type: replace Abstract: Recent years have witnessed the rapid development of Large Language Model-based Multi-Agent Systems (MAS), which excel at collaborative decision-making and complex problem-solving. Researchers have further investigated Multi-Agent Debate (MAD) frameworks, which enhance the reasoning and collaboration capabilities of MAS through information exchange and debate among multiple agents. However, existing approaches often rely on unguided initialization, causing agents to adopt identical reasoning paths that lead to the same errors. As a result, effective debate among agents is hindered, and the final outcome frequently degenerates into simple majority voting. To solve the above problem, we introduce Dynamic Multi-Agent Debate (DynaDebate), which enhances the effectiveness of multi-agent debate through three key mechanisms: (1) Dynamic Path Generation and Allocation, which employs a dedicated Path Generation Agent to generate diverse and logical solution paths with adaptive redundancy; (2) Process-Centric Debate, which shifts the focus from surface-level outcome voting to rigorous step-by-step logic critique to ensure process correctness; (3) A Trigger-Based Verification Agent, which is activated upon disagreement and uses external tools to objectively resolve deadlocks. Experiments show that DynaDebate achieves superior or highly competitive performance across the majority of benchmarks\footnote{The code is at https://github.com/nwpuLee2021/brianstorm.}.

22.
arXiv (CS.CL) 2026-06-17

Rift: A Conflict Signature for Deception in Language Models

Authors:

A model that lies while knowing the truth is the central case ELK cannot handle with behavioral evaluation alone. We ask whether such deception leaves an internal signature distinguishing it from honest error. Our key move is a control for wrongness: we contrast a sleeper agent (knows the truth, lies on trigger) against a naive liar (fine-tuned to emit the same wrong answers with no honest training). Both produce identical wrong outputs; any difference is about knowledge conflict, not incorrectness. We find deceptive forward passes carry a conflict signature - 2.1-2.3x higher residual rank than naive-liar passes on the same wrong answer - strong enough to identify which of two responses is the lie with 100% accuracy and no labels, across GPT-2 small/medium (three seeds) and three instruct models. Across Qwen2.5-1.5B/7B and Phi-3-mini, instructed deception raises residual rank on every tested fact (18/18, 40/40, 34/34); on Phi-3, lies separate perfectly from both honest answers and hallucinations (AUC 1.0, Wilcoxon p~6e-11). The signature survives strategic self-constructed deception (model invents its own lie, AUC 1.0), active concealment attempts (AUC 1.0), and length-controlled replication (20/20, AUC 1.0, p~1e-6). Using basis-free relative representations, a probe trained on one model family detects deception in two other families zero-shot (mean AUC 0.933), surviving simultaneous architecture and format change (AUC 0.821), and transfers across five languages (AUC 1.000, length-controlled). The signature is read-only: detectable but not injectable (0/8 both directions). Honest limitations and six negative experiments are documented in full.

23.
arXiv (CS.CV) 2026-06-18

Sensor Configuration Matters: A Systematic Evaluation of Multimodal SLAM on Quadruped Robots

Autonomous navigation of quadrupedal robots in diverse environments fundamentally relies on resilient Simultaneous Localization and Mapping (SLAM). While visual-inertial SLAM has matured across wheeled, handheld, and aerial platforms, a critical evaluation gap remains regarding how hardware-level sensor configurations affect performance under the aggressive dynamics of legged locomotion. Quadrupeds introduce distinct embodiment-induced sensory challenges, including foot-impact shocks, high-frequency mechanical vibrations, and rapid angular rotations, which degrade standard perception pipelines. To address this gap, we present a systematic evaluation of state-of-the-art visual, visual-inertial, and LiDAR-visual-inertial SLAM methods using the GrandTour dataset recorded on an ANYmal D quadruped. We isolate and quantify the impacts of camera modalities, shutter techniques, and inertial sensor tiers, analyzing their trade-offs across localization accuracy, algorithmic robustness, and computational resource utilization. Our empirical findings demonstrate that hardware selection has substantial influence on system resilience: stereo configurations consistently outperform monocular and RGB-D modalities, global shutter cameras significantly mitigate motion-induced tracking failures compared to rolling shutter cameras, and, crucially, standard inertial integration can degrade the performance of primarily vision-based frameworks under harsh legged locomotion. These insights additionally offer concrete design guidelines for tailoring custom sensor payloads to achieve dependable perception on agile legged systems.

24.
arXiv (CS.CV) 2026-06-12

Analyzing and Improving Fine-grained Preference Optimization in Medical LVLMs

Large Vision-Language Models (LVLMs) have achieved strong performance across medical imaging tasks, yet they remain prone to factual inconsistencies, poor visual grounding, and misalignment with clinically meaningful feedback. Existing post-training alignment approaches, including Direct Preference Optimization (DPO) and its variants, face three critical limitations in the medical domain: (1) sequence-level reward signals treat clinically critical tokens identically to generic filler text; (2) reliance on static supervised fine-tuning references as preferred responses introduces an off-policy distribution shift, steering optimization toward stylistic artifacts over clinical correctness; and (3) alignment objectives lack explicit visual grounding constraints, leaving models insensitive to subtle yet diagnostically decisive pathological features. Our method leverages a bidirectional token-wise KL regularizer alongside a visual-contrastive grounding objective that pairs clean and lesion-corrupted images to penalize responses generated without adequate visual evidence. Together, these components form a fine-grained, on-policy alignment framework that constructs preference pairs by minimally editing model-generated outputs, correcting only clinically erroneous spans while preserving the original linguistic style. Extensive experiments across medical imaging tasks and clinical text generation benchmarks validate the effectiveness of our approach.

25.
arXiv (CS.CV) 2026-06-12

Skill-3D: Evolving Scene-Aware Skills for Agentic 3D Spatial Reasoning

This paper explores agentic 3D spatial understanding, i.e., MLLM agents performing 3D reasoning through tool use. Existing methods often misuse tools and exhibit biased tool preferences under 3D scenarios, leaving the agentic paradigm with only marginal gains over non-agentic strategies. We reveal that 3D spatial reasoning tasks are heterogeneous across scenes, while these agents apply a uniform tool-use strategy to all scenes rather than selecting tools according to the specific scene and task. To address this, we propose Skill-3D, a framework that learns self-evolving scene-aware skills. Specifically, Skill-3D identifies the task scene and records the agent's tool-use trajectory into a Scene Memory, where successful trajectories from similar scenes are aggregated and distilled into a reusable scene-aware skill, with failed ones attached to the skill as lessons. During training, once a similar scene recurs, the corresponding skill is injected to guide the agent, producing new trajectories whose successes and failures further refine the skill, forming a loop in which the memory and the skill library co-evolve. Experiments show that Skill-3D substantially improves tool utilization in 3D spatial reasoning (from 39% to 78% on VSI-Bench), driving the agent toward correct and sufficient tool use. For instance, it improves Gemini-3-Flash by 67% on MMSI-Bench. Furthermore, we conduct agentic post-training over skill-guided trajectories, which boosts Qwen3-VL-8B by 60% on VSI-Bench.