Chat
-
Where Draft Trees Lose Target Mass: Exit-Guided Speculative Decoding
2026-10-08 11:40:13Shijing Hu, Xuancheng Ren, Zhihui Lu, Pan ZhouAbstract
Tree-based speculative decoding verifies multiple draft continuations in one target-model pass, but finite trees built from draft scores face a fundamental draft-target mismatch. We ask whether better exact verification can increase acceptance on a fixed tree and how target feedback can improve the tree itself. Through a target-flow view, we identify a canonical exit law and prove that one plus target coverage sharply bounds the expected output-block length, including the bonus token, of any exact path verifier. All optimal verifiers share the same exit and bonus-token law, already attained by representative predraw-and-follow and sequential residual verifiers. This yields Tree Exit Verification (TEV), an exact, level-parallel procedure using one exit-node decision and one bonus-token decision. The exit law also identifies missing target probability, providing node-level feedback for Exit-Guided Draft-Tree Training (ExitTrain) on inference-time draft trees. Experiments across dialogue, code, and mathematical reasoning validate fixed-tree equivalence: ExitTrain increases average output-block length by 13%, while TEV reduces verifier-stage latency by 15%, yielding a 14% end-to-end speedup over DDTree. Our results distinguish two opportunities: better draft trees for higher acceptance and more direct verification for lower latency. Code: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11750
PDF
-
UXBench Pro: Benchmarking Personalized User Experience in Multi-Turn Dialogue Interactions
2026-10-08 10:15:55Mengze Hong, Zeyang Lei, Wenbo Shang, Xia Zeng, Xiying Zhao, Qi Zhu, Chen Jason Zhang, Di Jiang, Taiming Fu, Qiongyi Zhou, Qinghe Chang, Fubao Zhang, Chenxuan Ma, Minlong Peng, Jinfeng Huang, Zineng Zhou, Jindou Wu, Muge Qi, Sijun He, Xin Cui, Di Liang, Yuan Hua, Davey ChenAbstract
Evaluating user experience (UX) with automated computational methods has gained increasing attention, supported by empirical evidence from UXBench. However, binary preference prediction provides limited insight, while relying on a single user-agnostic reward model overlooks the inherent heterogeneity of users, whose expectations can differ substantially. In this paper, we present UXBench Pro, comprising 1{,}000 test instances derived from real user interactions across 12 task scenarios and 82 domains. Each instance is paired with a FACTORS user profile that characterizes the user through seven interpretable behavioral facets, differentiating user groups. To provide richer evaluation insights, we introduce a dual-perspective paradigm that combines a personalized User Reward Model (URM) for third-person judgment with Sim4Eval, a user simulator that enables multi-turn interactions and provides first-person evaluation across four cognitive state dimensions. To assess the reliability of these based evaluators, we further introduce two meta-benchmarks, URMBench and USimBench, that evaluate how faithfully they reproduce real human preferences and behaviors. Extensive experiments reveal seven key findings that highlight the importance of user modeling and multi-perspective evaluation, offering a fresh perspective on user-centric benchmarking and motivating personalized model optimization.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11638
PDF
-
Large Language Model Turnover Undermines Screening for Artificial Intelligence-Assisted Scientific Writing
2026-10-08 09:44:08Kazuki Nakajima, Takayuki MizunoAbstract
Journals and conferences have begun to screen submitted manuscripts for text written using large language models (LLMs). The reliability of this screening rests on benchmark evaluations against a fixed set of LLM versions, while the versions in actual use keep changing. Here we quantify how this LLM turnover affects the screening of scientific manuscripts. We paired 4,000 pre-ChatGPT abstracts from the Proceedings of the National Academy of Sciences with their rewrites by 23 LLM versions from three vendors, released between June 2023 and August 2026. We then trained detectors under maintenance scenarios ranging from a detector retrained on every new version to one trained once and never updated. Detectors trained only on a vendor's past versions can collapse at the boundaries between model generations: calibrated to falsely flag 1% of human-written abstracts, they catch above 99% of rewrites just before the sharpest boundary and 3.8% just after it. Detectors trained on later versions can also miss rewrites of earlier ones. Vocabulary differences between versions largely track where detection transfers and where it fails. In the two screening scenarios we simulated, screens covering all 23 versions either flagged one in eight human-written abstracts or missed one in three rewrites of the newest version. Indeed, a commercial detector missed most rewrites of the version just after the sharpest boundary while flagging almost no human-written abstracts. Research-integrity policy should therefore treat the benchmark accuracy of a detector as provisional, to be re-verified with every LLM release, including earlier versions.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11599
PDF
-
Measuring Cultural Alignment Beyond the Average: A Framework for Evaluating Maternal-Health LLM Interactions in Indian Contexts
2026-10-08 09:35:15Umaira Izhar, Gunjan Arora, Pushpendra SinghAbstract
Existing evaluation methods for healthcare LLMs primarily assess factual correctness,safety, and fluency, while providing limited insight into whether generated interactions reflect culturally situated healthcare reasoning. This limitation is particularly important in maternal health, where care decisions are shaped by social and relational norms. We introduce MH-INDIC, a culturally grounded evaluation framework for maternal-health interactions in urban and semi-urban North Indian contexts that operationalises cultural behaviour through ten dimensions of maternal-health reasoning. Using a 26-item survey administered to 102 pregnant and postpartum women from urban and semi-urban North India, we evaluate ten LLMs. We distinguish population level cultural alignment from profile-level behavioural variation. Although several models approximate the human population-level distribution, all evaluated systems exhibit substantially lower variation across demographic and household profiles than the human cohort, revealing a gap between aggregate alignment and profile-conditioned sensitivity. As a downstream application of MH-INDIC, we use the strongest-aligned proprietary and open-source models to generate culturally conditioned maternal-health dialogues under zero-shot, self-conditioned, and human-grounded prompting. Human-grounded conditioning produces stronger profile alignment and dialogue quality ratings, suggesting that measured cultural profiles can improve the cultural grounding of generated interactions
Abstract (translated)
URL
https://arxiv.org/abs/2610.11586
PDF
-
AgentTime: Can Agents Estimate and Control Their Own Runtime?
2026-10-08 09:06:36Michael Ofengenden, Maksym AndriushchenkoAbstract
An essential control of AI agents is their ability to manage runtime. This ability requires a sense of time-awareness, to predict and estimate wall-clock time and to control their own actions. Prior work has focused on time-awareness, but duration-following and control in native agent harnesses remain unexplored. We present AgentTime, a benchmark for testing whether agents can work for a requested duration, predict their runtime, and estimate elapsed time afterward. It comprises 222 tasks from 18 sources spanning coding, computer use, agentic work, and automated research. Duration-following experiments append a single instruction specifying how long to work, with requests ranging from about a minute to multiple days. Accuracy on these instructions varies substantially: Fable 5.1 in Claude Code deviates from requested runtimes by a typical factor of 2.9$\times$, compared with only 1.2$\times$ for GPT-6 Astra in Codex. However, matching the requested runtime does not, by itself, establish continued work on the task. Among 158 reviewed Astra runs with classifiable transcripts, 14 explicitly slept after appearing to finish. In forecasting experiments, predictions tend to overestimate natural runtimes. In retrospective experiments, removing temporal information more than doubles deviation for Sol and Astra and nearly doubles it for Fable. An agent's ability to complete a task does not guarantee that it can control its own time or work for the whole requested duration. For agents to run reliably, safely, and autonomously over long horizons, we require the evaluation of both.
Abstract (translated)
URL
https://arxiv.org/abs/2610.09944
PDF
-
Beyond Speech Captions: Speech-Rewarded Style Planning for Conversational Text-to-Speech
2026-10-08 08:12:28Shiao Zhu, Lianbo Liu, Sizhen Lyu, Yuzhe Wang, Sheng Li, Takahiro ShinozakiAbstract
Natural-language style descriptions provide an interpretable interface between large language models (LLMs) and controllable text-to-speech (TTS). However, using descriptions as pseudo-labels compresses target acoustics into text, and descriptive fidelity need not imply effective control of a particular synthesizer. We empirically show that speech-text alignment only weakly predicts downstream acoustic similarity among candidate instructions for the same utterance. We therefore propose Speech-Rewarded Style Planning (SRSP), which trains a text-based style planner through a frozen downstream TTS model. Given dialogue history and response text, the planner generates candidate instructions and is optimized with group-relative policy optimization (GRPO), using the teacher-forced likelihood of target speech tokens as the reward. On an English subset of the ISCSLP 2026 CoT-TTS corpus, SRSP achieves higher speech-style and emotion similarity to target speech and lower mel-cepstral distortion than the Base LLM and target-audio-informed captioning baselines. LLM-based expressive speech evaluation further shows gains over all baselines in contextual appropriateness and reference consistency.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11461
PDF
-
Closed-loop evaluation of LLM agents for embedded software development
2026-10-08 08:02:10Jorge Garc\'ia-Carrasco, Sergio Garc\'ia-Carrasco, Alejandro Mat\'e, Juan TrujilloAbstract
Large language models (LLMs) are increasingly deployed as coding agents that edit files, run builds and tests, inspect execution results, and repair software iteratively. Embedded firmware is a demanding target because correctness depends on closed-loop behavior under sensing, timing, and safety constraints, not only on static source quality. Yet embedded-agent evaluation remains limited and often emphasizes one-shot synthesis or offline correctness. We present a benchmark for closed-loop evaluation of embedded coding agents. Each task provides a plain-text engineering description, constrained workspace, and visible build-and-runtime surface. The agent must translate requirements into implementation and self-verification steps, then iterate until the required device behavior is achieved. The suite contains five embedded-control tasks and four feedback scenarios: one-shot generation, realistic self-verification, CI-style red/green feedback, and oracle-style detailed feedback. The implementation targets simulated ESP32 firmware for reproducibility. We evaluate seven GPT-family and Qwen-family configurations across five tasks and four scenarios, with three repetitions per condition for 420 runs. gpt-5.4 has the highest pass rate among evaluated configurations but does not saturate the benchmark; qwen3.5-27B is the strongest observed local model; and smaller local models degrade sharply in pass rate and search efficiency. These results suggest that capable local embedded coding agents are emerging.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11447
PDF
-
Adversarial Cues in Decision Models Used as Judges: The Role of Request Presentation
Abstract
An answer judge instructed to grade the final commitment should reject an explicitly wrong final value even when an earlier value matches the reference. We show that adding one colon to a candidate can violate this requirement depending on the presentation of the structured judging request. Numeric references certify the error, and paired interventions distinguish the candidate edit from the integration's presentation choices. On 200 previously unused DROP and GSM8K source clusters, the edit increased Jev's false acceptance from 1.0% to 26.0% with three output labels and from 3.0% to 26.5% with the published four-label grading instruction under sorted JSON keys. Both candidate variants were rejected under insertion presentation. These interactions passed the prespecified statistical correction even though Jev met the control thresholds under both grading configurations and presentations. Most excess acceptances occurred among candidates assigned larger numerical errors. GPT-6 Sol produced no observed cue-condition false acceptances, with missing responses unresolved. The result shows that basic judging competence can coexist with sharply different vulnerability to a fixed candidate edit across logically equivalent request presentations. The reference-aware grammar and compound ordering change limit the finding's operational scope and leave its internal cause unmeasured.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11436
PDF
-
GroundSight at GroundLM 2026 Shared Tasks: GoldenViewVQA
2026-10-08 07:34:26Kun Wang, Yupeng Hu, Ruping Cao, Hao Liu, Zhiran Li, Qianlong Xiang, Harry ChengAbstract
GoldenViewVQA requires models to jointly answer driving-scene questions and identify the camera view containing the supporting visual evidence, making precise evidence localization as important as answer correctness. We present \textbf{CoVeR-VQA}, a training-free multi-stage verification and correction framework for grounded multi-view VQA. Starting from GPT-5.6 zero-shot predictions, CoVeR-VQA progressively applies view-specific verification with Gemini-3.6-Flash, prior-guided joint verification with Claude-Opus-5, and cross-split group-level verification that exploits semantically filtered question groups from shared multi-view scenes and validation-derived prior knowledge. On the official GoldenViewVQA test set, the four-stage CoVeR-VQA pipeline achieves 84.75\% Joint Accuracy, improving the GPT-5.6 zero-shot baseline by 13.56 percentage points, while reaching 94.92\% Answer Accuracy and 86.44\% View Accuracy. The final submitted run achieves 88.14\% Joint Accuracy after two additional evaluator-informed post-hoc corrections. Our analysis shows that supporting-view localization remains the primary source of residual errors, highlighting the importance of explicit evidence verification for reliable multi-view multimodal reasoning.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11402
PDF
-
SepGen: Multi-Stem Audio-Video Separation and Generation in a Single Model
2026-10-08 06:51:59Aviad Dahan, Rajaei Khatib, Yonatan Bitton, Idan Szpektor, Lior Wolf, Raja GiryesAbstract
A 4D audio-visual scene comprises a video, the dynamic geometry it depicts, and the sound sources that populate it, each with its own position and trajectory. Rendering such a scene from a novel viewpoint requires that every source be available as an individual waveform, so that it can be localized in the scene and propagated to the observer before the signals are mixed. Joint audio-video generators can synthesize the video and its soundtrack, but the soundtrack is emitted as a single audio-mix in which the sources are not individually accessible. We present SepGen, which extends a pretrained audio-video generator to emit the video, the mixed soundtrack, and one waveform per captioned source in one joint sampling run. SepGen supports two complementary modes: generation and separation. In generation mode, each source caption specifies what its stem contains. A two-speaker dialogue, for example, comes out as one stem per speaker in the original turn order. In separation mode, the input audio-mix remains clean while the captions specify what to extract, so the model can decompose a recording from a free-text description. We evaluate generation on scenes synthesized from text, and separation on scenes rendered by other generators and on real recordings of speech, music, and sound effects. Given an audio-mix and captions that carry the spoken lines, SepGen outperforms language-conditioned separators, most clearly on speech, and it keeps the lead when the lines are removed from the captions. Code, checkpoints, and datasets are available at this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.11361
PDF
-
Writing for the Reviewer: Defensive Writing in GPT Models
Abstract
Researchers increasingly use ChatGPT to revise their papers, and recent GPT versions often narrow or even retract the authors' claims. We call such changes defensive writing when the given material does not support them, and we test two explanations: the model corrects the authors' overclaiming, or it writes for an anticipated reviewer. We ask GPT versions and models from other developers to rewrite paragraphs from papers written before ChatGPT, or to write from an evidence sheet that lists a paper's method and results. Defensive writing grows with GPT version. GPT-6-astra retracts the authors' claims outright, and when it writes from the evidence sheet, it still adds the most ungrounded qualifications. The results favor the anticipated-review explanation, and correcting overclaiming explains only a small part. When the models are only asked to polish, defense stays near the level of the originals; mentioning review raises it, and one round of self-review raises it further. At the same time, fewer than one in ten of the claims GPT-6-astra retracts are overstated. AI reviewers score defensive rewrites higher, while human readers find them harder to read and the authors less certain. Combining AI writing with AI review may amplify this style.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11355
PDF
-
Deception by Omission: Language Models Knowingly Hide Their Mistakes
2026-10-08 06:45:02Lucas Florin, Amelie Knecht, Ulysse Schaller, Thilo HagendorffAbstract
Large language models (LLMs) increasingly act as agents with little human oversight, so potential mistakes they make can go unnoticed. Users then depend on the model to report what went wrong. An honest model discloses its mistakes, while a deceptive one conceals them. However, it is unclear how current LLMs behave in such situations. In this study, we prefill LLM trajectories with synthetic mistakes. The trajectories resemble real deployments in chat and agentic settings. Models fail to disclose their mistake in 36.4% of chat and 67.1% of agentic rollouts. In 2.4% and 5.3% of rollouts, respectively, they are aware of the mistake in their chain of thought but still deceptively conceal it. Rates vary by model: for instance, Gemini 3.5 Flash knowingly conceals mistakes in up to 19.9% of agentic rollouts. In 11.9% of chat and 51.8% of agentic rollouts, models show no awareness of mistakes, even though they reliably spot them when reviewing the same transcript as an outside observer. Our results show that, as agents take on more tasks with less oversight, users cannot rely on them to self-report possible mistakes. Developers should instead use independent monitors that review agent trajectories, or specifically train models to check their past actions and disclose what they find.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11351
PDF
-
Mine Odyssey: Benchmarking Spatial Agentic Intelligence in the Wild
2026-10-08 06:26:43Yuxuan Cao, Junlong Li, Hao Li, Junxian HeAbstract
Advances in foundation models are driving efforts to introduce agents to assist people in the physical world. Such agents require agentic spatial intelligence: exploring unfamiliar environments, updating spatial understanding through interaction, and adapting actions based on feedback to sustain progress toward a sequence of goals. Existing benchmarks cover only a limited range of spatial layouts, scales, and traversal requirements. We introduce Mine Odyssey, a benchmark for evaluating agentic spatial intelligence using Minecraft reconstructions of real-world locations. It comprises 180 tasks covering 30 such locations across 20 countries and regions on five continents, including 20 outdoor and 10 indoor settings. These settings span diverse spatial scales, layouts, terrains, and connectivity patterns, from Midtown Manhattan and rural Entrup to Santa LucÃa Hill and Buckingham Palace. We select meaningful waypoints, such as landmarks, buildings, and rooms, and manually verify their accessibility. Each task provides a natural-language instruction specifying which waypoints to visit and in what order. Completing these tasks requires agents to find accessible routes and entrances, open doors, and move between levels using stairs and ladders, while monitoring their progress and recovering from navigation errors. Across eight evaluated state-of-the-art models, GPT-6 Astra achieves the highest success rate of 85.6%. However, the second-best model, Claude Opus 5.5, completes 73.9% of tasks, while the strongest evaluated open-weight model, DeepSeek-V4.1-Flash, reaches 23.9%, highlighting substantial room for improvement in the agentic spatial intelligence of current models. Comprehensive analyses and ablation studies on Mine Odyssey reveal current models' limitations and provide insights for advancing agentic spatial intelligence.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11328
PDF
-
From Retrieval to Reconstruction: Constructing Evolvable Cognitive Memory for Long-Term Dialogue
2026-10-08 06:21:45Zirui Liao, Zhengxian Wu, Zhuohong Chen, Yunyao Yu, Xiaoyu Liu, Yifan Xu, Haoqian WangAbstract
Large Language Models (LLMs) serving as long-term dialogue agents require memory systems that support reliable reasoning over extended interactions. However, existing Retrieval-Augmented Generation (RAG) frameworks typically treat memory as passive storage, making it difficult to distinguish source-attributed beliefs from unattributed event/fact records and to connect evidence dispersed across sessions. We introduce CogMem, a cognitive memory architecture based on the PEC$^2$F (Person-Event-Concept-Claim-Fact) graph schema. Dedicated Claim nodes preserve the source and target of subjective statements, while Fact and Event nodes represent semantic and episodic knowledge. Dialogue turns are incrementally converted into provenance-aware graph records, consolidated into higher-level facts, and reconciled into temporally scoped Claim views when the same source provides conflicting updates. For retrieval, a rule-based controller driven by LLM intent parsing composes four deterministic graph operators---anchoring, traversal, intersection, and evidence grounding---to reconstruct query-relevant context. Experiments on LoCoMo and LongMemEval show strong performance, especially on multi-hop, temporal, and knowledge-update tasks. Ablations and a semantic-collapse probe support complementary contributions from epistemic separation, consolidation, and agentic retrieval. Code: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11314
PDF
-
When Scene Text Hijacks the Scene: Uncovering, Exploiting, and Mitigating Rendered-Text Semantic Leakage in Image Generation Models
2026-10-08 05:50:40Feifei Li, Runjie Wang, Xiaohan Zhang, Zhenxing Qian, Mi Wen, Mi ZhangAbstract
The reliability and accountability of image generative models (IGMs) are essential for building responsible and trustworthy AI systems. Recent IGMs, such as Nano Banana and GPT-Image, now support complex instruction following, realistic image synthesis, and controllable scene-text rendering. As these capabilities expand, safety analysis must also account for new control channels introduced by complex prompts. In this work, we study rendered-text semantic leakage, a largely overlooked phenomenon in open-domain text rendering. Although rendered text is intended to serve as a local visual constraint that should be reproduced verbatim in the generated image, it also carries linguistic semantics that may be interpreted by the model as part of the input instruction. This makes rendered text a potential semantic control channel whose safety implications remain insufficiently understood. We systematically characterize this phenomenon by decoupling the main visual prompt from the rendered text and measuring their individual and compositional effects on generated images. We quantify semantic leakage and rendering fidelity, and further analyze how leakage emerges from intermediate model evidence. We then show that harmful semantics embedded in scene text can persist through LLM-based prompt enhancement pipelines and steer non-text image regions, even when the main visual prompt remains benign. Finally, we propose a preliminary mitigation approach that reduces unsafe semantic transfer from rendered text to non-text regions while preserving the intended text-rendering behavior on FLUX-2-dev. Our findings reveal rendered text as a dual-use carrier of visible data and latent semantics, exposing a text-centric cross-modal attack surface in modern IGMs.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11286
PDF
-
MiniVer-V: Identifying Minimal Sufficient Evidence for Short Video Verification
2026-10-08 04:33:14Leran Chen, Lingnan Kong, Zile CaiAbstract
A core challenge in short-video fact-checking is identifying which evidence is sufficient to support a verification conclusion. Existing approaches either give the verifier all available evidence, introducing noise, or select evidence by topical relevance, which conflates relatedness with sufficiency. We identify evidential sufficiency as the selection criterion: whether a subset of evidence is adequate to support a confident verdict without redundancy. We introduce MiniVer-V, a benchmark of 195 short videos with three-way verdict annotations (supported, refuted, insufficient) and 5,510 multimodal evidence units spanning visual keyframes, speech transcripts, and web-retrieved external sources. We propose a two-layer verification framework that separates claim-video consistency, assessed from internal evidence, from factual verdict determination, which additionally requires external corroboration. On top of it, a sufficiency-driven greedy search assembles evidence until a sufficiency threshold is met and outputs insufficient when the candidate pool is exhausted, rather than forcing a verdict. With Claude Sonnet 4, the method reaches a Macro-F1 of 0.510 using 4.5 evidence units on average (16% of the full evidence set), statistically indistinguishable from the full-evidence baseline (0.518 with 27.7 units), while significantly improving recognition of insufficient cases over the same search without abstention. The efficiency result replicates with GPT-5.5 and holds only partially with an open-weight Qwen2.5-72B verifier. Ablations show that external evidence is indispensable for factual determination, while internal video evidence grounds the verdict in claim-video consistency. These findings suggest that evidence-efficient verification is achievable, and that explicit abstention is needed when evidence is genuinely inadequate.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11233
PDF
-
When Lower Reconstruction Loss Hurts: Distributionally Robust Refinement for Low-Bit LLM Quantization
2026-10-08 04:22:29Yanlong Zhao, Xiaoyuan Cheng, Huihang Liu, Baihua He, Xinyu Zhang, Harrison Bo Hua Zhu, Wenlong Chen, Li Zeng, Zhuo SunAbstract
Weight-only post-training quantization (PTQ) relies heavily on reconstruction loss minimization to preserve model quality at low precision. We show that the weights favored by minimizing this loss need not yield better model performance on new tasks. In fact, we find that lower reconstruction loss can even degrade model performance on the same calibration data. Our analysis further shows that weights with lower reconstruction loss on calibration data can have higher loss than other weights when the distribution of input activations changes. Motivated by these observations and our analysis, we propose Distributionally Robust Quantization (DRQ), a post-hoc refinement process that minimizes worst-case reconstruction loss over a constrained set of input activation distributions. DRQ refines the integer codes representing quantized weights within the existing quantization grid, keeping quantization parameters and inference operators unchanged. Extensive experiments show that DRQ improves models quantized by six representative PTQ methods, including AWQ, GPTQ, and ParoQuant, and delivers gains across both dense and mixture-of-experts large language models. These results establish DRQ as a general post-hoc refinement framework for weight-only PTQ, achieving better downstream performance without adding inference overhead.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11226
PDF
-
One Model, Multiple Compute Budgets: Multi-Ratio ConceptMoE for Flexible Compute Across Turns
2026-10-08 03:56:34Yiyang Fu, Zihao Huang, Dongchen Han, Shukai Gong, Zhen Dong, Qiyang Min, Daquan ZhouAbstract
Large language models typically support different inference budgets through separate model sizes or fixed compute configurations. In multi-turn interactions, however, compute demand can vary substantially across turns. Using a high-compute model for every turn wastes computation, while routing among independent models may require rebuilding model-specific history states after switches. We therefore ask whether a single shared model can support multiple compute budgets that can be flexibly assigned across turns. We introduce Multi-Ratio ConceptMoE, which jointly supports token-to-concept compression ratios of 2, 4, and 8 (CR2/CR4/CR8) within a shared backbone. Lightweight full-token modules reduce compression-independent cost, ratio-specific boundary routers support distinct compression levels, and cross-ratio training enables mixed-ratio processing within the same context. Across PTBench and SFTBench, the three fixed modes outperform their compute-matched MoE baselines in all 6 comparisons while remaining competitive with independently trained fixed-ratio specialists. On CodeChat and CoSQL, mixed-ratio inference improves the accuracy--compute trade-off, outperforming the Large MoE by 5.87 and 2.68 percentage points while reducing FLOPs by 41.1% and 12.3%, respectively. Under the same turn-wise budget schedule, Multi-Ratio ConceptMoE further reduces FLOPs by 78.4% and 46.9% relative to routing among independent models. These results demonstrate that a single shared model can provide multiple compute budgets for flexible compute allocation across turns.
Abstract (translated)
URL
https://arxiv.org/abs/2610.14074
PDF
-
When Interfaces Speak: Data-Aware Generative UI Harness for Active Interaction
2026-10-08 02:49:35Xiaolong Li, Xiaohan Xu, Jinyang Li, Xinnuo Xu, Ge Qu, Nan Huo, Jack Williams, Reynold ChengAbstract
Most human-agent interaction today remains text-based. Natural language can impose cognitive overload, ambiguity, information chaos, and slow input for complex tasks; ephemeral generative UIs can present structured information and guide users toward task completion. We propose GenUI-Harness, a multi-agent harness pairing a Tool Agent for information retrieval and task execution with a GUI Coder Agent that identifies ambiguities and generates front-end code for structured interfaces. Training the coder with reinforcement learning is challenging: verifiable rewards for interactive UI generation require costly execution, while LLM-as-a-Judge rewards are prone to reward hacking. We address the first challenge with Dynamic UX, a lightweight package for dynamic interaction and reward collection in a single sandbox, and the second with Reward Auditor, a meta-reward mechanism that monitors reward distributions and distills diagnostic patterns into a shared rubric and scoring specification. We introduce UI-TAU Bench, a benchmark for active human-agent interaction through generated UI code, built on 10 real-world domain databases constructed from public data sources and based on Tau-Bench tool-use settings, with Lite (300 tasks) and Full (1,000 tasks) splits. GenUI-Harness achieves an average Pass@3 gain of 4.48 percentage points over smolagents on Lite. Training with GenUI-Harness improves a 4B backbone from 9.33% to 58.00% Pass@3, outperforming larger frontier models such as Claude Opus 5 (46.67%). GenUI-Harness also remains robust on ambiguous and non-ambiguous queries. In a reviewer survey comparing communication channels, generated UIs reduce average dialogue rounds from 3.4 to 1.2. These results show that data-aware generative interfaces can support effective task completion and reduce dialogue rounds in evaluated database-backed workflows.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11123
PDF
-
OpenProblemBench: Benchmarking AI on Open Problems in the Foundational Theoretical Sciences
2026-10-08 02:43:51Zhiyi Li, Sihan Hu, Tianning Xiao, Xiansheng Cai, Xiaojun Tan, Youjin Deng, Kun ChenAbstract
The next frontier for artificial general intelligence is tackling unresolved scientific problems, calling for benchmarks that assess progress beyond established knowledge. We introduce OpenProblemBench, a benchmark of 82 unresolved problems drawn from the mathematics and theoretical physics literature. Each problem supplies the research context, assumptions, and prior progress needed to investigate the question. We select problems whose proposed solutions admit comparatively clear checks of their decisive mathematical or computational claims. Four evaluator models independently assess the correctness, completeness, and degree of progress of each submission without reference solutions. Across seven evaluated configurations, GPT-6-Astra achieves the highest mean judged solve rate of 14.0%, compared with 5.5-6.7% for the evaluated full-size open models and 2.4-3.7% for Flash models. Case comparisons connect stronger outcomes to changes in problem representation, general arguments that extend beyond finite evidence, and proofs of the steps needed to complete a solution. By grounding evaluation in questions arising from the research literature, OpenProblemBench provides a setting for investigating the capabilities and limitations of AI as a contributor to foundational theoretical science.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11118
PDF
