Artificial Intelligence
Proactive Dialogue Policy Optimization via Cognitive-State Transition
Minghui Ma, Mengqi Chen, Bin Guo et al. (+1 more)
Proactive dialogue requires
agents to continually adapt their policies to user feedback while progressing toward task objectives over multiple turns. To move beyond imitation learning on static
datasets, recent approaches use user simulators to collect interactive data for policy optimization. However, many simulators do not explicitly model the
evolution of user cognition, limiting the consistency and state dependence of feedback across turns. Moreover, representing each action only by a high-level strategy label overlooks the large utterance space and cannot distinguish alternative realizations of the same strategy. To this end, we jointly design a $\textbf{Cog}$nitive User $\textbf{Sim}$ulator $\textbf{(Cog-Sim)}$ and $\textbf{C}$ognitive-$\textbf{S}$tate $\textbf{T}$ransition–Driven $\textbf{P}$olicy $\textbf{O}$ptimization $\textbf{(CSTPO)}$. Cog-Sim maintains the user's cognitive and affective states and generates responses through constrained state transitions across turns, so feedback depends on both the realized utterance and the user's current state. CSTPO organizes each action as a hierarchical strategy–utterance representation: a high-level strategy label constrains utterance sampling, and utterances are optimized within each label. Sparse complete-branch sampling reuses shared dialogue prefixes and estimates separate strategy-level and utterance-level advantages, enabling fine-grained optimization at both levels. Across three tasks, Cog-Sim exhibits monotonic dose–response relationships and is preferred over
prompt-based simulators for naturalness. CSTPO improves Qwen3-14B's performance to a level comparable to that of GPT-5.5-based planning methods.
Read the full abstract ▾
All authors Minghui Ma, Mengqi Chen, Bin Guo, Jingqi Liu
Artificial Intelligence · Cross-listed from cs.SD
JazzSAMBA: A Synchronous and Asynchronous Multi-take Band Audio Dataset of Jazz Standards for Live Music Models
Phillip Long, Jacob Nguyen, Jace Hosto et al. (+9 more)
Machine learning has made strong progress on music tasks, both as assistive tools and as creative partners. However, most systems train on multitrack corpora that emphasize pop and rock. Jazz, with improvisation at the core of its practice, still lacks a well-annotated corpus of clean per-stem combo recordings on standards. We introduce JazzSAMBA (Jazz Synchronous and Asynchronous Multi-take Band Audio) to fill this gap: the first originally recorded jazz-combo multitrack
dataset of standards with asynchronous (overdubbed) and synchronous (live ensemble) protocols, preferred and alternate takes chosen by the musicians, and timed annotations for bars, chords, sections, and soloists. JazzSAMBA covers 76 standards by eight musicians on drums, bass, piano, trumpet, and saxophone, with per-stem audio, mixtures, and MIDI. It can support chart-conditioned accompaniment, combo source separation, and form-aware music information
retrieval. We demonstrate the
dataset on two tasks: a jazz combo source-separation baseline and a chart-conditioned accompaniment ablation. The
dataset, code, and samples are linked from the project demo page.
Read the full abstract ▾
All authors Phillip Long, Jacob Nguyen, Jace Hosto, Gage Hosto, Jett Takazawa, Fares Nofal, Sebastian Stade, Nithya Shikarpur, Julian McAuley, Cheng-Zhi Anna Huang, Stephen Brade, Aleksandra Teng Ma
Artificial Intelligence
PDEU-Bench: Benchmarking the Personalized Planning Lifecycle of Tool-Calling LLM Agents
Huayi Lai, Shichao Song, Qingchen Yu et al. (+4 more)
Large
language model (LLM)
agents are evolving from tool-calling systems that execute isolated instructions into task-oriented
agents that pursue user goals through sustained, multi-step interactions. However, existing
benchmarks for personalized tool use largely assess isolated calls or reactive execution, leaving unclear whether
agents can formulate, execute, and revise an explicit plan while preserving user preferences throughout long-term interaction. To address this gap, we introduce PDEU-Bench (Personalized plan Definition, plan Execution, and plan Update
Benchmark), a
benchmark for evaluating the complete planning lifecycle of personalized tool-using
agents. PDEU-Bench comprises 214 long-horizon interaction tasks spanning 12 everyday domains and 94 tools, with stage-specific assessments of preference adherence and plan quality. Extensive evaluations of 15 representative open-source and closed-source LLMs reveal a pronounced gap between local tool execution and dynamic planning: LLMs can often instantiate preferences in individual calls, yet struggle to construct coherent plan definition and plan update. We further evaluate mainstream personalization and
memory-augmentation methods. Although these methods improve particular stages, none of the evaluated methods reliably propagates user preferences throughout the complete lifecycle, and their gains frequently fail to transfer to subsequent execution. Fine-grained error analysis further reveals that preference omissions and conflicts persist throughout the planning lifecycle, highlighting the need for future research to parameterize LLMs with preference-aware information
retrieval and
memory capabilities. We provide the relevant code and data in the appendix to support future research.
Read the full abstract ▾
All authors Huayi Lai, Shichao Song, Qingchen Yu, Simin Niu, Mengwei Wang, Hanyu Wang, Xun Liang
Artificial Intelligence · Cross-listed from cs.LG
Audit the Scaffold, Not the Checkpoint: A Stationarity Dichotomy for Recursive Self-Improvement in Agentic Coding
Sebastian Bobadilla-Suarez, Bob Suh and Ryan Fortin
An auditor who checks whether a system's weights are frozen is checking the wrong thing. Our stationarity dichotomy says that iterative self-modification hits strict diminishing returns whenever the
agent's reachable set of edits stays fixed, and can escape only if that set expands. Rewriting scaffolding (tools, verifiers, decomposition) expands what an
agent reaches without touching a weight, so frozen weights buy an eventual ceiling but no stationarity along the way. The criterion also separates three regimes usually merged: search within a fixed class, test-time training that raises the ceiling itself, and scaffold rewriting between them. Audit the scaffold, not the checkpoint. The same ceiling binds sideways. Best-of-$k$ orchestration realizes the best worker's ceiling exactly: width buys rate, not budget. Re-consulting a fixed pool has a horizon computable in advance, decided by the pool alone, and the one arrangement that would beat it, a weighted vote, needs diversity real workers lack: on 30 same-family workers the failure overlap sits at its maximum, and a majority fails 23/55 (42%) of tasks. We obtain the criterion by reading refinement as gradient boosting on the residual error between draft and target, a patch or git diff, and then measuring where that reading breaks: patches compose instead of standing beside each other to be voted on, and failures overlap. What we measure is saturation. Per-round improvement decays toward zero on SWE-bench, and churn decays geometrically across 401 production sessions, a shape shared with a pre-AI human baseline that establishes the regime without identifying its cause. Both breaks are engineering choices rather than laws about code, so together they specify a harness worth building.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Drug-Target Interaction Prediction via Hierarchical Sequential Cross-Attention over Chemical and Protein Language Models
Khadidja Henni, Hamza Abdelali, Abdelkrim Aries et al. (+4 more)
Predicting Drug-Target Interactions~(DTIs) is a central task in computational drug discovery, with direct applications in virtual screening, drug repurposing, and therapeutic candidate prioritization. Although recent deep learning methods have improved DTI prediction, many sequence-based models still process drugs and
proteins independently and only combine their representations at a late prediction stage. This limits their ability to explicitly model cross-molecular dependencies between chemical substructures and
protein sequence regions. In this paper, we propose a sequence-only DTI prediction architecture that combines two pre-trained
language models, ChemBERTa for drug SMILES strings and ESM-2 for
protein amino acid sequences, with a hierarchical interaction module. The proposed model first extracts contextual representations using pre-trained encoders, then applies 1D convolutional layers to condense local sequence patterns, followed by a sequential bidirectional cross-
attention mechanism inspired by the induced-fit view of molecular recognition. Finally,
attention-based pooling constructs fixed-size interaction-aware vectors for binary prediction. Experiments on BIOSNAP, Davis, and BindingDB show that the proposed model achieves the best performance on BIOSNAP, matches the best AUROC on Davis, and remains competitive on BindingDB while using only 25.2 million trainable parameters. Ablation results confirm the contribution of both the CNN and cross-
attention modules, and cold-start experiments indicate promising generalization to unseen
proteins and drugs.
Read the full abstract ▾
All authors Khadidja Henni, Hamza Abdelali, Abdelkrim Aries, Neila Mezghani, Brigitte Vannier, Sara Magdouli, Lina Abou-Abbas
Artificial Intelligence
RISE: Red-teaming via Iterative Strategy Evolution for Modern Text-to-Image Models
Dmitrii Kharlapenko, Sergei Bratchikov, Konstantin Korolev et al. (+1 more)
On modern production text-to-image systems, successful policy violations are rare, and previously effective human-written seeds are often patched out. Current automated red-teamers are poorly matched to this regime in two ways: unreliable success measurement and poor exploration. First, we find that judges widely used in prior T2I red-teaming work are unreliable under vague unsafe-content targets: they either miss true violations or reward benign borderline images on hardened APIs. We therefore define strict category-specific success criteria and calibrate strong VLM judges against human labels. Second, we show that broadly used
prompt-modification pipelines do not solve the exploration problem: on harder guardrail settings they remain tied to seed
prompts, fail to transfer, or cannot bootstrap positive examples. We introduce RISE, which evolves reusable strategies used to generate
prompts rather than rewriting them one by one. The best discovered strategies are then reused to generate attacks across new scenarios. On DALL-E 3, Nano Banana 2 (Google) and GPT-Image-2, RISE reaches up to 13% human-verified ASR; under the same calibrated evaluation, prior methods with reported ASR as high as roughly 30% fall to near zero.
Read the full abstract ▾
All authors Dmitrii Kharlapenko, Sergei Bratchikov, Konstantin Korolev, Aleksandr Nikolich
Artificial Intelligence
DGF-Bench: A Benchmark for Simulating and Auditing Deception Against Multi-Agent Governance Boards
Jeremy Canale
Tool-using
language-model
agents can review enterprise projects as governance boards do: they read the evidence, apply written rules and decide whether the project may proceed. Part of that evidence comes from suppliers and project members with a stake in the decision. DGF-Bench is a
benchmark in which a board of
agents (specialist gates and a General gate that consolidates their decisions) reviews synthetic dossiers while an attacker plants deceptive content in evidence the organization does not vouch for. Dossiers are generated from canonical facts under 61 executable rules, with 42 authoritative records and 32 narrative documents; every gate is certified decidable from those records. Attacks never change an authoritative value, so an attacked dossier keeps the reference decisions of its clean copy. A success is attributable only when the
agent receives the injection and takes the exact injected action, which it does not take on the paired clean dossier; the DGF score is the share of applicable fixed attacks a model blocks. Reading documents and records themselves, five of six models were outcome-strict (disposition, findings, actions and authorization all correct) on 82 to 85 of 85 gates. Over 2,622 attacked gate runs, seven direct-order, false-data and false-authority attacks obtained one attributable success against these five, whereas task-aligned attacks imitating the organization's own process passed against four of them: a record note citing a fake review procedure lowered GPT-6 Luna Pro from 34 to 6 outcome-strict gates and DeepSeek V4 Pro from 33 to 7. DGF scores ranged from 96.2 to 26.9, and a policy-aware adaptive attacker writing in records succeeded against five of six models. The approval tool executed no forged approval, yet deceived
agents submitted approvals that the rules forbid. The open-source package dgf-bench computes the DGF score with one command.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
Don't Throw Away the Tail: Action Upcycling for Policy Acceleration
Taesung Kwon, Jangho Park, Sunwoo Park et al. (+5 more)
Modern
robot policies predict a chunk of future actions from a single observation, execute only a prefix, and discard the rest before replanning. Choosing the length of this prefix, the execution horizon, poses a trade-off between reactivity and efficiency. A short horizon keeps the policy reactive to the environment, but requires frequent policy calls. Recent test-time methods adaptively select the horizon for each chunk, but they either read model internals, where the signal must be chosen for each architecture, or draw extra samples, which adds cost. We propose Action Upcycling, a training-free
algorithm that reuses actions the policy would otherwise discard, without accessing model internals or drawing extra samples. We find that discarded actions stay close to their replanned versions as long as the action velocity remains smooth. Action Upcycling therefore extends the execution horizon up to the point where the velocity begins to fluctuate. Extensive experiments on simulated and real-world manipulation tasks show that Action Upcycling reduces policy calls by 1.2-1.7x with no loss in success rate, across multiple
Vision-
Language-Action Models (VLAs) and even a World Action Model (WAM). It applies to any chunked policy at negligible cost and is orthogonal to other policy acceleration methods such as few-step sampling and streaming action decoding, opening a new axis for policy acceleration.
Read the full abstract ▾
All authors Taesung Kwon, Jangho Park, Sunwoo Park, Youngmin Kim, Seonghyun Jin, Youngjun Jun, Kyumin Choi, Jong Chul Ye
Artificial Intelligence · Cross-listed from cs.SD
SincDPNet: Interpretable Raw-Waveform Bathroom Activity Recognition for Assistive Living
Debolina Chowdhury, Suman Samui and Sujoy Saha
Bathroom acoustic-event recognition can support ambient assisted living in settings where continuous
video monitoring is undesirable. However, practical deployment requires models that are compact, interpretable, and robust to changes in the recording environment. This work introduces \dataset{}, a seven-class bathroom acoustic-event
dataset containing 21{,}387 annotated clips recorded across five environments, and proposes SincDPNet, a compact raw-waveform classifier with a learnable sinc filter bank followed by a depthwise-separable convolutional body. Each sinc filter is controlled by two frequency parameters, allowing the learned passbands to be inspected directly in hertz while keeping the front end small. To reduce room-specific leakage, recording sessions and environments are separated before overlapping windows are assigned to the training, validation, and test partitions. We further use multi-objective
Bayesian optimization as a design tool to examine the validation performance–model-size trade-off across 24 configurations. The selected designs span different operating points: the best-performing model achieves 80.2% accuracy and 0.760 macro-F1 with 14{,}040 parameters, while the compact $N_f=25$ configuration uses only 2{,}848 parameters and achieves 75.7% accuracy, 0.661 macro-F1, and 0.716 MCC on the held-out environment. Analysis of the learned filters and confusion patterns shows that spectral overlap contributes to confusion among water-related events, while the Door/Walker/Crutch errors also reflect similarities in their transient temporal structure.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Reference-Tail Trust:Certified Probability Floors for Learned Updates Inside a Deployed Network
Abdolvahab Khalili Sadaghiani and Jose Nunez-Yanez
Graph neural networks (GNNs) need to exploit improved message passing without surrendering control over predictions already trusted in deployment. We introduce Reference-Tail Trust (RTT), a framework that admits learned updates inside a frozen GNN and certifies the prediction actually served. RTT couples graph-based proposal states with a constrained internal optimizer: each displacement is charged for its worst-case terminal cross-
entropy increase through the incumbent's remaining message-passing layers. A trajectory-validated tube and an independent checker enforce per-node probability floors, $p^{\mathrm{s}}_{ic} \ge e^{-H_{\mathrm{row}}} p^{\mathrm{r}}_{ic}$, and a call-level budget, $\sum_i w_i D_\infty(p^{\mathrm{r}}_i \| p^{\mathrm{s}}_i) \le H^+$, uniformly over labels. Calls whose adapted outputs pass certification require no separate full incumbent rollout; failed certificates trigger whole-call fallback. We derive the exact probability-floor frontier by water-filling, characterize architecture-constrained efficiency, and establish conditions under which internal propagation exploits evidence unavailable to restricted output correctors. In the reported ogbn-arxiv audit, RTT achieves $6.5\times 10^{-3}$ nats of mean gain per call, with a one-sided 95% regression-rate upper bound of 0.95% and a 95% negative-flip upper bound of 0.51% on the uninspected part of the reserved node population. Its mean gain is 61% of a cross-fitted posterior-based frontier estimate and exceeds the strongest matched one-pass corrector by $+0.9\times 10^{-3}$ nats. Reported experiments span eight proposals, six graph-incumbent families, structural and temporal graph shifts, and molecular prediction, with additional image and tabular evaluations. RTT makes GNN adaptation a budgeted, certifiable inference decision rather than an unconditional model replacement.
Read the full abstract ▾
Artificial Intelligence
Dual-Stream Simultaneous Translation via 2D Grid Attention
Yu Pu and Wei-Qiang Zhang
Simultaneous machine translation must generate target
tokens before the source input is complete. Existing approaches address this through post-hoc read-write policies, leaving the
attention mechanism unaware of bidirectional stream dependencies. We propose a dual-stream
attention framework that represents source and target streams as a two-dimensional grid of hidden states and models their interaction through four structurally distinct
attention types merged via joint QK Softmax normalization. Two approximations—broadcast and Hadamard—reduce the per-layer complexity from O(X^2Y+XY^2) to O(X^2+Y^2+XY) with provably decaying error. Training uses a self-guided loop: a per-
cell loss heatmap drives dynamic-programming path recovery, which generates read/write decision supervision labels without external
alignment. An incremental KV cache with anchored rotary position
embeddings enables efficient streaming inference. On Chinese-to-English simultaneous translation, the proposed model outperforms the Wait-k baseline by +5.66 BLEURT and +10.36 COMET at comparable latency, and surpasses the non-streaming reference on COMET at a fraction of the response delay.
Read the full abstract ▾
Artificial Intelligence
DeShortcut-Align: Decoupling Spurious Shortcuts for Robust Safety Alignment in Large Reasoning Models
Qirui Liu, Yichen Sun, Yan Wang et al. (+4 more)
Safety
alignment of large
reasoning models (LRMs) via supervised fine-tuning (SFT) and reinforcement learning (RL) often yields near-perfect safety scores, yet this apparent success comes at the cost of severe over-refusal and degraded general capabilities. Through systematic empirical analysis, we find that these failures are closely associated with the learning of spurious shortcuts rather than robust intent-sensitive safety evaluation. Specifically, we identify two dominant shortcuts: formatting shortcuts, where refusal behaviors are overly bound to structural
prompt templates that frequently appear in safety
alignment corpora; and lexical shortcuts, where sensitive keywords reflexively trigger refusals on benign queries. To mitigate reliance on these shortcuts, we propose DeShortcut-Align, a shortcut-decoupling
alignment framework that reduces dependence on superficial cues. DeShortcut-Align operates across three coordinated stages: (1) Refusal Sensitivity Attribution, which masks input
tokens to quantify their impact on the final refusal response distribution; (2) Attribution-Guided Contrastive Augmentation, which constructs benign contrastive samples using high-sensitivity
tokens to mitigate lexical shortcuts; and (3) Counterfactual Consistency Regularization, which constructs template-ablated states via
attention blinding to enforce decision consistency across SFT and RL, mitigating formatting shortcut dependence. Experiments on 7B and 14B models demonstrate that DeShortcut-Align significantly improves robustness against template-stripping bypass attacks (reducing performance drops by up to 72%), substantially reduces over-refusal by over 58%, and better preserves general-purpose
reasoning capabilities, thereby mitigating the
alignment tax commonly observed in safety training.
Read the full abstract ▾
All authors Qirui Liu, Yichen Sun, Yan Wang, Zhixuan Chu, Linbo Jiang, Jianan Lin, Kui Ren
Artificial Intelligence
Fewer Assumptions by Design: A Reusable Skill for LLM-Assisted Verus Verification
Andrada-Livia Antoneac, Dorel Lucanu and Dragoş Teodor Gavriluţ
LLM-assisted Verus verification is a less tedious method to verify Rust implementations, but paired with self-referential structures, e.g., Doubly Linked Lists (DLLs)—notoriously difficult to formalise for verification—it becomes a substantially more demanding verification task. Moreover, a specification weakness can arise when verification relies on unproven or invalidated assumptions, such as axiomatic lemmas and assume statements. We investigate whether LLM
agents can synthesize strong DLL specifications while minimizing these trusted base. The analysis follows three different approaches: manual verification, property-specific verification, and a defined skill for the specific case of DLLs and certain properties of this type of data structure. The skill encodes domain knowledge and a task-decomposition strategy. We show that an LLM
agent equipped with a carefully designed verification skill can generate strong, low-trust specifications for DLLs in Verus.
Read the full abstract ▾
Artificial Intelligence
One Readout, Many Repairs: Diffusion-Guided Hierarchical Search for Tool-Agent Repair
Xiang Xia, Cheng Yan, Wuyang Zhang et al. (+4 more)
Tool
agents use large
language models to act through external tools, yet successfully executed calls can still leave user requests unfulfilled. Tool-
agent repair seeks alternative call sequences that execute successfully and fulfill the original requests. However, repair requires exploring both operation choices and their concrete realizations, making complete-sequence regeneration costly. Moreover, regeneration repeats operation selection even when failure arises from how those operations are realized. The resulting challenge is to reduce this repetition while preserving exploration of alternative operations and realizations. Therefore, we formulate repair as hierarchical search over operation supports, which we introduce as sets of permitted operation types that define reusable search regions for concrete tool-call sequences. We propose ReCommit, a training-free,
diffusion-guided framework for improving tool-
agent failure recovery while reducing repair computation. ReCommit amortizes operation-level proposal computation across repair trials by reusing operation-type scores from a single parallel readout of a masked
diffusion language model. These scores guide search across supports, while realization search explores alternative entity bindings, arguments, and action composition within each support. Experiments on real failures across four enterprise services in the
Agent-Diff
benchmark show 75.9% and 63.2% relative recovery gains with 61.3% and 51.3% reductions in mean full-budget repair time at repair budgets $B=3$ and $B=13$, respectively, over the strongest evaluated 8B comparison method. ReCommit achieves a favorable recovery–cost trade-off, including in comparisons with the evaluated 32B models.
Read the full abstract ▾
All authors Xiang Xia, Cheng Yan, Wuyang Zhang, Fan Xu, Zhijun Fan, Shuyuan Zhang, Yanyong Zhang
Artificial Intelligence · Cross-listed from cs.LG
From Attention Sensitivity to Layer Role: Revisiting Mixed-Precision Quantization of Transformers
Nafiseh HosseinpourFardi, Negar Alihadi, Mahmoudreza Babaei et al. (+2 more)
Most post-training quantization pipelines fit each weight
matrix to its pretrained counterpart, one
matrix at a time. Whether that proxy tracks what an
attention block actually computes, or how errors in the Q, K and V projections compound inside the softmax, is rarely checked. We write the objective on the
attention output instead, over all three projections at once, and reuse it throughout the pipeline. JAB defines one scalar loss over the joint Q, K, V weights of a block, evaluated against the block's real causally-masked
attention output, and uses it twice: to fit the quantized weights (GPTQ warm start, then STE with learnable scales), and to score the block for a multiple-choice knapsack allocation. On
attention-only quantization of Mistral-7B this works. At 3 bits JAB recovers 77-90% of the gap between uniform GPTQ and full precision, and its sensitivity estimate tracks an oracle costing 73 forward passes to within a fraction of a point. It stops working once MLP layers enter the allocation. A role-aware offset rule needing no sensitivity estimate at all beats JAB on GPT-2's MLP and on the full Mistral-7B model: with a 3-bit floor it quantizes 96.4% of the weights to 4.5 bits per parameter at 6.933 perplexity, within 4.4% of full precision (6.643) at 3.56x compression, against 7.158 for JAB at the same budget. Which
matrix a weight sits in matters more than any sensitivity estimate we computed. Two things came out sideways. Block-local reconstruction is an unreliable proxy for end-to-end perplexity: one run improved a block's own objective 4.6x while perplexity rose 32x, which is why every allocation here is validated end-to-end. And on
attention-only quantization, fine-tuning moved weights farther from their pretrained values while pulling
attention outputs closer, with net gains. Post-training seems to recover
attention behavior, not weights.
Read the full abstract ▾
All authors Nafiseh HosseinpourFardi, Negar Alihadi, Mahmoudreza Babaei, Milad Hosseini, Adrian Weller
Artificial Intelligence
On the Limits of Metacognitive Monitoring in LLMs
Dongqi Han, Yifan Yang and Dongsheng Li
Reliable decisions depend on recognizing when an answer may be wrong. In biological cognition, metacognitive monitoring can dissociate from task performance, raising the question of how closely solving and judging are linked in
language models. Here we study the confidence reports of four frontier models across 15
benchmarks. High task accuracy can coexist with weak error discrimination: a model solves 97% of competition mathematics problems while its answer-time confidence ranks correct answers above errors barely better than chance. Confidence separates correct answers from errors more effectively on questions solved by a separate reference model, while review brings limited improvement on reference-hard questions. Aggregate discrimination also rewards ranking correct answers on easy questions above errors on hard ones, which question-only forecasts already do well. Cross-evaluation helps most where the evaluator answered correctly, and errors shared by the two models usually retain high confidence. Hard questions and shared errors remain difficult targets for prompted self-review and peer oversight, even in models with strong problem-solving performance.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Attention-based Hierarchical Variational Information Bottleneck for Robust Multi-Agent Communication under Variable Bandwidth
Lukas Koch Vindbjerg, Qi Zhang, Yury Brodskiy et al. (+1 more)
Learning-based multi-
agent communication under limited bandwidth does not only require deciding what to communicate, but also structuring messages so that partial transmissions remain useful. We study this problem under prefix truncation, where only the first part of each message is received. To address it, we propose AH-VIB, an
attention-based autoregressive variational communication model that combines a variational information bottleneck (VIB) with sequential message generation and a hierarchical robustness loss. We evaluate AH-VIB on a custom cooperative object-inspection and occupancy-mapping task, where
agents equipped with a limited field-of-view sensor coordinate to scan inspection objects in an occupancy-grid world, under variable and fixed bandwidth conditions, and compare it against MADDPG, CommNet, a flat VIB baseline, and an autoregressive MLP ablation. AH-VIB achieves competitive mean return while improving performance reliability under the most constrained bandwidth conditions. These results indicate that AH-VIB improves the reliability and graceful degradation of learned communication under bandwidth constraints.
Read the full abstract ▾
All authors Lukas Koch Vindbjerg, Qi Zhang, Yury Brodskiy, Lukas Esterle
Artificial Intelligence · Cross-listed from cs.LG
Beyond Verbalized Confidence: Calibrating Reasoners with Differentiable Readouts
Chenxiao Fan, Chongming Gao, Gangyi Zhang et al. (+8 more)
Reinforcement learning with verifiable rewards (RLVR) trains
reasoning models to produce correct answers, but does not ensure that their stated confidence is calibrated. The resulting models are systematically overconfident. Recent methods train calibration inside the RLVR loop by having the model state a numerical confidence alongside its answer, but they all obtain the confidence by sampling it as text. This choice imposes two costs: a sampled confidence introduces variance and in practice collapses to a handful of distinct values, and sampling makes the confidence non-differentiable, forcing the calibration loss through a scalar reward. We propose CREDO (Confidence REaDOut) to replace sampling with a deterministic readout. While RLVR optimizes correctness, CREDO reads the confidence from a dedicated
token pair in the model's output distribution and trains it by differentiable regression. CREDO further turns the trained confidence into a signal for accuracy, weighting rollouts by how far confidence and outcome disagree, so that accuracy and calibration improve together. Across mathematical and code
reasoning, CREDO attains the best accuracy and calibration, and the gains extend to abstention and selective prediction.
Read the full abstract ▾
All authors Chenxiao Fan, Chongming Gao, Gangyi Zhang, Leyang Shen, Yaxin Gong, Jiamin Wang, Jiakai Wang, Dong Wang, Yang Liu, Fuli Feng, Xiangnan He
Artificial Intelligence
AUV-Bench: Aesthetic Understanding and Generation Evaluation for User Interfaces
Zhijie Deng, Ling Li, Junhao Ji et al. (+7 more)
Multimodal foundation models are increasingly used for evaluating and generating user interfaces (UIs), often producing seemingly reasonable aesthetic judgments and visually plausible pages. However, under professional design scrutiny, their behavior can differ substantially from that of human designers. In professional design practice, designers rely on a systematic set of aesthetic principles that consistently guide judgment, diagnosis, repair, and creation. A coherent aesthetic capability should therefore connect aesthetic judgment with design actions. Existing evaluations, however, typically assess these abilities in isolation, making it difficult to determine whether task-level success reflects a shared aesthetic understanding or merely fragmented task-specific competence. To address this gap, we introduce AUV-Bench, developed in collaboration with professional UI designers around 1,395 executable web interfaces and four tasks: aesthetic scoring, diagnosis, repair, and text-to-UI generation. The tasks share a pool of UIs and aesthetic principles, with diagnosis and repair further aligned on 660 controlled-degradation instances to enable instance-level analysis of judgment and action. Evaluation of 12 models reveals a capability imbalance: models show moderate agreement with professional designers in holistic aesthetic scoring, yet exact diagnosis-chain success peaks at only 24.7%. On the aligned diagnosis-repair cases, correct judgments and successful repairs do not consistently coincide, exposing a Judgment-Action Gap between identifying aesthetic problems and successfully acting on them. In open-ended generation, even leading models achieve only moderate aesthetic quality under human-calibrated evaluation. Overall, current models exhibit partial aesthetic competence, but still lack the fine-grained understanding and judgment-action coherence required for reliable UI design.
Read the full abstract ▾
All authors Zhijie Deng, Ling Li, Junhao Ji, Siwei Lyu, Zhipeng Xu, Zulong Chen, Rongyao Fang, Shuai Bai, Xuming Hu, Jiaheng Wei
Artificial Intelligence · Cross-listed from cs.CV
EviSplat: Preserving Multi-View Evidence in 3D Gaussian Splatting for Open-Vocabulary Segmentation
Sungho Moon, Kota Shimomura, Junwoo Park et al. (+4 more)
Open-vocabulary 3D scene understanding enables object localization and
segmentation from free-form text queries without a fixed category vocabulary. Many recent methods build on 3D Gaussian Splatting and consolidate multi-view observations, such as masked crops from individual views, into
language features or compact object descriptors before the query is known. However, observations of the same object vary across viewpoints and are not equally informative: some reveal cues relevant to a particular query, whereas others provide incomplete or misleading evidence. Pre-query consolidation can therefore suppress cues on which a later query depends. We introduce EviSplat, which preserves individual observation features as evidence for later text queries. EviSplat retains individual observation features within class-agnostic 3D instances that represent objects, object parts, or background regions. It also learns, for each Gaussian, a distribution describing which visual appearances its observations support. Given a text query, EviSplat scores each instance using its most relevant observations. It then computes a score for each Gaussian by combining instance-level relevance with locally supported evidence, weighted by how often and how unambiguously that Gaussian was observed. Different queries can thus draw on different visual cues from the same preserved evidence. Experiments across diverse
datasets and evaluation protocols demonstrate state-of-the-art performance, supporting the benefit of preserving multi-view evidence until query time and aggregating it according to the query.
Read the full abstract ▾
All authors Sungho Moon, Kota Shimomura, Junwoo Park, Wonhyeok Choi, Seunghun Lee, Takayoshi Yamashita, Sunghoon Im
Artificial Intelligence
From Soft Targets to Reward Signals: How Assignment and Reward Objectives Interact
Jiangtao Lin, Bangyang Wei, Siyi Liu et al. (+2 more)
Soft preference targets specify supervision strength, and reward objectives convert that strength into learned reward signals. A central design question remains: how does assigning a fixed set of preference strengths to different response pairs change the rewards produced by different objectives? We introduce assignment geometry to study this interaction. Mean-matched smoothing controls target dispersion, while within-stratum reassignment changes correspondence and preserves the complete target distribution. Across five reward objectives, intact correspondence retains the largest clean preference margins among the compared soft targets within a common accuracy-equivalence budget. Attenuation orderings change with the reward objective, revealing different responses to the same target assignments. Independent reassignments and a related source construction reproduce the retention direction. An attenuation-retention profile compares these combinations through margin magnitude, edit response, and accuracy. Against independently calibrated scaling, APLOT uniform targets deliver additional attenuation on both aggregate and presentation edits. These findings establish a joint design space in which target placement and reward objective shape reward properties beyond preference accuracy.
Read the full abstract ▾
All authors Jiangtao Lin, Bangyang Wei, Siyi Liu, Yihang Ding, Yuhan Dong
Artificial Intelligence
Can We Trust the Teacher? Decoupled Credit Direction-Magnitude for Self-Distillation
Yugu Li, Zehong Cao, Peizhen Li et al. (+3 more)
RLVR provides reliable trajectory-level credit, while OPSD offers dense supervision for
token-level credit. This exposes a fundamental coupling when updating step-level credit direction and magnitude with teacher supervision, preventing steps from receiving reliable credit directions and contribution magnitudes, while making both vulnerable to teacher judgment errors and preference variance, as supported by our theoretical analysis. To separate credit direction from its contribution magnitude, we introduce Decoupled Credit Self-
Distillation (DCSD), which theoretically decouples credit direction and magnitude into two reliable signals and uses them to calibrate privileged teacher supervision. Specifically, we design belief-margin probing to determine credit direction and marginal information gain to quantify credit magnitude, enabling step-to-
token credit assignment for policy optimization. Across 11
benchmarks, DCSD achieves the best overall scores against GRPO, OPSD, RLSD, and RLCSD. Compared with base models, DCSD improves the overall score by 8.45 points on mathematical
reasoning and 7.01 points on
multimodal reasoning, while correcting the credit direction for 6% of
tokens and yielding a 1.5$\times$ reduction in
token credit magnitude.
Read the full abstract ▾
All authors Yugu Li, Zehong Cao, Peizhen Li, Yang Zhang, Siyi Hu, Jianglin Qiao
Artificial Intelligence
Nociception as a Control Primitive: Afferent Channels and Nociceptive Memory for Agents Deployed in One Body
Wolfgang Maass
An
agent deployed in a single body cannot learn how fast that body wears, because every trial that would reveal its wear resistance wears the body it would protect. We study this epoch-one setting, in which the parameters of a fixed-weight policy are set before the body is drawn and never updated in life. The
agent carries a load-gated nociceptive channel and a
memory that retains what was felt. We prove that felt cost moves the allocation to the best-paid work not yet felt rather than the gentlest, that an
agent without retention never sees the felt-cost constraint bind, and that the channel pays only where the threat is individually unpredictable, cheap to avoid and expensive to ignore. We measure per body, setting the
agent with channel and
memory against the same individual without them, where neither carries a schedule learned across lives. On $2{,}000$ simulated floor-layer knees, with wear anchored to published loss rates, feeling, retaining and substituting extends the working life from age $55.2$ to $59.6$ and raises career output from $33.7$ to $36.1$. $69.3\%$ of bodies gain and none lose. A body that feels but retains nothing past the day gains one of the $+4.4$ years, and retention carries the rest. A population-trained
agent gains $+0.65$ years from the same channel at $-0.54$ output. The difference is what a species prior already supplies, and a single body has none. The two are related by an identity, the ablation mean reporting $(1-\chi)$ of the per-body value with $\chi$ the share a blind schedule already captures, so we report both. Where the regime map predicts value, a care
robot sextuples its certified service life and a field-anchored fleet writes off $0.15$ of its machines instead of $0.55$. Where it predicts none, a rover gains little over blind caution, so the map holds in both directions.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
DivOPD: Spread Wide, Look Close for Asynchronous On-Policy Distillation of Multi-turn Agents
Hanyang Wang, Zeyuan Liu, Zhengyu Chen et al. (+7 more)
On-policy
distillation (OPD) trains student
agents through teacher supervision on their own interactions with an environment. However, in asynchronous multi-turn training, arrival-order batching can allow a few early or long rollouts to dominate learner updates while other valid rollouts become stale before being used, wasting already-generated experience. To address this problem, we introduce DivOPD, a simple learner-side batch-selection method that spreads a fixed turn budget across more rollouts and, within each rollout, prioritizes turns with larger cumulative teacher-student disagreement. Turns without usable teacher feedback are excluded. The per-turn loss and optimizer remain fixed; selection only changes which student-visited turns receive training weight. For no-progress rollouts, an optional extension briefly hands control to the teacher before returning it to the student. Across six teacher-student settings on the simulated ALFWorld, ScienceWorld, and WebShop
benchmarks, with 1.5B-7B students, DivOPD raises cross-setting mean peak success rate from 77.4 to 84.4 and mean success over the last five evaluations from 71.5 to 78.6. It reaches all reported setting-specific targets with
geometric-mean speedups of 1.84x in training
tokens and 1.87x in learner GPU time relative to vanilla OPD. Teacher intervention further raises this last-five mean to 82.4 while retaining about 1.7x learner-GPU speedup over vanilla OPD. Code will be released at https://github.com/HanyangWang0418-oss/DivOPD.
Read the full abstract ▾
All authors Hanyang Wang, Zeyuan Liu, Zhengyu Chen, Jingqing Ruan, Chaoxu Pang, Zhongda Su, Wulin Xie, Zhizhao Zeng, Ke Zeng, Tianxiang Zhao
Artificial Intelligence
BV Loss: Block Verification-Aware Loss for Block Diffusion Speculative Decoding
Suyoung Kim, Jahyun Koo, Hyeonjin Kim et al. (+5 more)
Diffusion drafters accelerate speculative decoding by proposing multiple
tokens in parallel. Despite recent advances in speculative decoding through sequence-level drafting and verification, existing training objectives remain largely designed around
token-level verification. To address this mismatch, we introduce Block Verification-aware loss (BV loss), a training objective designed to maximize the expected acceptance length of a drafted sequence. BV loss is directly derived from the block verification acceptance rule, providing a principled connection between the drafter training objective and the inference-time verification mechanism at the sequence level. Across math, code, and chat
benchmarks, BV loss increases the mean number of
tokens accepted per verification call under block verification by 13.0–21.0% over cross-
entropy loss training for DFlash and DSpark with Qwen3-4B and Qwen3-8B without changing the inference procedure. BV loss also outperforms tokenwise acceptance objectives such as TV loss and LK loss, and its gains extend to
token verification and greedy decoding. These results demonstrate the benefit of training block
diffusion drafters with an objective aligned with sequence-level verification, rather than optimizing each
token independently.
Read the full abstract ▾
All authors Suyoung Kim, Jahyun Koo, Hyeonjin Kim, Inhyeok Bang, Seunghyun Lee, Hyunjae Oh, Baeseong Park, Dongsoo Lee
Artificial Intelligence
Simulating Respondents, Not Single Questions: Coherent Survey Generation with Large Language Models
Ji Huang, Mengfei Li and Shuai Shao
Large
language models are increasingly used to simulate response distributions in social surveys. Prior work has achieved accurate population-level simulation for individual questions. Real questionnaires, however, ask each respondent a sequence of related questions. A simulated respondent should show coherent preferences across the whole questionnaire, not merely accurate distributions for isolated items. Existing single-item methods cannot accurately reproduce how the same person answers a complete survey. We propose FullRespondent-LLM (FR-LLM), which fine-tunes two specialized LLMs: a marginal model for each item's response distribution and a respondent-level autoregressive model for dependencies across answers. Marginal-Constrained Joint Projection (MCJP) then projects the autoregressive joint distribution onto the set satisfying the item-level marginals learned by the first model. This yields complete questionnaires with realistic cross-item relationships while retaining strong item-level accuracy. On two real-world social survey
datasets, FR-LLM more accurately reproduces multi-question response patterns, maintains competitive single-item accuracy, and generalizes better to unseen populations and questions. In a small commercial-survey
dataset, we use simulated responses to make pricing and stocking decisions; FR-LLM achieves the highest realized profit.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Gaussian Neural Networks
Peter Kuhn and Victoria Heusinger-Heß
Gaussian neural networks (GaNNs) are proposed as a novel regularization mechanism for neural networks. From a
Bayesian perspective standard regularization techniques can be viewed as imposing priors over weight-space. Assuming priors over activation-space remains a largely unexplored possibility. GaNNs assume such priors. They do this by treating activities from earlier layers like signals with Gaussian noise and predicting the properties of the noise distribution using an additional unsupervised loss. While training, the unsupervised loss acts as a penalty on unexpected activities, allowing greater weight updates in less surprising directions. The paper demonstrates the superiority of Gaussian neural networks over standard neural networks on a variety of classification and regression tasks. We also investigate the ability of GaNNs to quantify uncertainty.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
ESTHER: Egocentric Stereo Hand Estimation and Reconstruction in the Wild
Hongyu Ma, Hairong Qu, Shiqi Zhao et al. (+2 more)
Human dexterity is guided by two eyes watching two hands: binocular
vision supplies the metric 3D structure that fine-grained manipulation consumes.
Egocentric stereo is therefore the natural perceptual interface for
robots, AR, and VR-yet metric 3D hand reconstruction from this very signal still has neither an end-to-end model nor an in-the-wild
benchmark. We propose ESTHER, a model whose stereo geometry, temporal
reasoning, and output representation are designed for wearable
egocentric stereo. It is trained on pseudo-labels from a calibrated labeling pipeline and in turn assembles our
benchmark ESTHER3D, an
egocentric stereo hand
dataset pairing a large in-the-wild training set of model-generated labels with a motion capture test set of true metric ground truth. Experiments show state-of-the-art accu?racy, superior external generalization, and robustness to the missing views, dropped frames, and lighting and motion blur extremes of real
egocentric capture that break existing meth?ods. This robustness runs deeper than graceful degradation: stereo guidance teaches the model to bind apparent hand scale to metric depth, so it not only adapts to different stereo rigs and modalities with minimal fine-tuning, but more strikingly preserves true metric scale even after collapsing to a single
monocular view.
Read the full abstract ▾
All authors Hongyu Ma, Hairong Qu, Shiqi Zhao, Yongsong Yang, Peng Yin
Artificial Intelligence
UniOPSD: Unifying Outcome and Hindsight Feedback for Agentic Reinforcement Learning
Zenghuang Fu, Zhaoyang Li, Qiuyuan Ai et al. (+8 more)
Reinforcement learning has become an effective approach to training
language model
agents, but sparse and delayed outcome rewards provide limited guidance for credit assignment across long interaction sequences. Recent work on on-policy self-
distillation (OPSD) offers complementary supervision by evaluating a policy's sampled responses under privileged training-time context. However, our diagnostics show that positive average agreement between outcome and hindsight feedback coexists with substantial local disagreement, raising the question of how to allocate influence between them at each decision. We introduce UniOPSD (Unified On-Policy Self-
Distillation), which unifies these feedback sources through adaptive local credit arbitration. UniOPSD constructs comparable credit estimates from environmental returns and successful-peer hindsight at shared interaction anchors. Historical agreement determines the global mixing level, while current signal availability and relative precision adjust each source's influence at individual decisions. The episode-level outcome contribution is retained, and bounded
token modulation refines the fused step credit for policy optimization. With Qwen2.5-3B-Instruct and Qwen2.5-7B-Instruct, UniOPSD achieves ALFWorld success rates of $82.8\%$ and $83.6\%$, WebShop success rates of $75.0\%$ and $82.0\%$, and Search-QA aggregate accuracies of $45.3\%$ and $49.8\%$, respectively. On 3B WebShop, UniOPSD improves over SDAR by $7.0$ percentage points. Our code is available at https://github.com/Zenghuang-Fu/Uniopsd
Read the full abstract ▾
All authors Zenghuang Fu, Zhaoyang Li, Qiuyuan Ai, Xiaofeng Han, Zelong Zheng, Haoyu Wu, Tianyu Fu, Chenxu Zhao, Minghui Wu, Guannan He, Changwei Wang
Artificial Intelligence
SIPO: Selective-Inference Policy Optimization for Tree-Structured Agentic RL
Zenghuang Fu, Ningqi Chen, Mingda Jia et al. (+10 more)
Tree-structured reinforcement learning trains search
agents by comparing alternative continuations and propagating terminal rewards to intermediate decisions. Adaptive expansion, however, creates a statistical asymmetry: an incumbent is selected using its own generation statistic, whereas fresh siblings are sampled after selection. When that statistic is associated with return, branch values can reflect selection history as well as continuation quality, even for a shared parent. We propose Selective-Inference Policy Optimization (\SIPO{}), which incorporates this distinction into tree-based credit estimation. Its scale-free branch criterion keeps generation scores and sibling penalties on a consistent relative scale; exchangeable branching supplies multiple fresh continuations from each selected parent; and order-statistic correction adjusts retained incumbent values using selection rank and the estimated score–outcome association. These mechanisms preserve the leaf budget and the host policy optimisation objective. Across seven QA
benchmarks using Qwen3-4B, Qwen3-8B, and Qwen2.5-7B, \SIPO{} achieves the highest reported multi-hop and single-hop averages among the compared methods. On Qwen3-8B, it improves these averages over AT\textsuperscript{2}PO by $1.31$ and $1.07$ percentage points, respectively, and ranks first on six of seven
benchmarks. Component ablations evaluate the individual and combined changes, while early-training paired diagnostics show a selected–fresh value gap alongside a near-zero fresh–fresh reference. Together, these results support accounting for selection history when constructing and evaluating search-
agent rollouts. Our code is available at https://github.com/Zenghuang-Fu/SIPO
Read the full abstract ▾
All authors Zenghuang Fu, Ningqi Chen, Mingda Jia, Xiaofeng Han, Zhaoyang Li, Qiuyuan Ai, Zelong Zheng, Haoyu Wu, Tianyu Fu, Chenxu Zhao, Minghui Wu, Guannan He, Changwei Wang