Chat
-
A Night at the LLM Zoo: Data Conditioned Flow Matching for Generating Pretrained LLM Weights
2026-11-04 20:16:34Scott Biggs, Bedionita Soro, Saumya Gupta, Bruno Andreis, Sung Ju HwangAbstract
A challenge to Weight Space Learning as it expands from task specific and vision models to Large Language Models (LLMs) is the absence of a well curated and analyzed LLM population. To address this, we train such a model zoo for application to Weight Space Generation by systematically varying the data mixture composition between web text, books, mathematics, coding, and French across populations of 51M, 124M, and 355M parameter GPT-2 Models, each tier with count N = 100. We analyze these populations by cosine similarity, functional diversity, Leave-One-Mixture-Out modeling, and variance decomposition. We show that the zoo contains diverse models whose variation is structured by training mixture composition. We embed the training mixture composition to condition a Flow Matching model of complete pretrained LLM weights in Gram-PCA compressed weight space. By demonstrating zero-shot generalization to held out mixtures, measuring Continuous Ranked Probability Score skill, as well as finding minimal changes in downstream test-set perplexity and general capability benchmark scores, we show that our generator generalizes on the simplex of data mixtures to produce models that perform similarly to those in the zoo ex nihilo. Finally, we produce all source code and artifacts to support the continued expansion of Weight Space Learning and Generation into the LLM domain.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07103
PDF
-
When Verification Is Not Agreement: Cross-Agent LLM-to-Dafny Formalization
Abstract
A verified Dafny postcondition certifies that a formula holds, but it does not guarantee that the result was reached through genuine independent reasoning. We introduce a cross-agent formalization protocol where a Specifier model translates clinical trial criteria into a Dafny predicate, and an Implementer model writes an operational method checked against it. A same-model control establishes that even with no capability gap, independent re-extraction from identical text agrees only 59.3% of the time. Evaluating four model configurations on 96 clinical trial documents, we find that agreement is highly sensitive to how model capability is allocated across the two roles: the GPT-4.1-nano/GPT-4.1-mini configuration achieves 53.0% agreement when the stronger model is the Implementer, but only 14.3% when the roles are reversed. The strongest tested configuration, GPT-5.6-luna/GPT-5.4-mini, improves agreement to 34.4% but remains below the same-model baseline and is dominated by direct contradiction (42.7%). We also detect a critical verification artifact in which a weaker Implementer satisfies the postcondition by invoking the Specifier's predicate directly; after structural auditing, corrected agreement falls from 14.3% to 13.2%. Our results show that verification success alone is insufficient evidence of independent cross-agent agreement, and that model capability does not guarantee agreement when formalizing the same source independently.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07073
PDF
-
LLMs Don't Know What They Know: Benchmarking Temporal Self-Knowledge for Financial Backtesting
2026-11-04 17:24:02Lingfei Qian, Yan Wang, Xueqing Peng, Yupeng Cao, Yuechen Jiang, Zhuohan Xie, Anke Xu, Wenbo Cao, Jiarui Chen, Zehan Li, Jimin Huang, Alejandro Lopez-Lira, Yuehua Tang, Sophia Ananiadou, Jian-Yun NieAbstract
Financial backtests of large language models (LLMs) are meaningful only if the model did not already know the outcomes it is asked to predict. Practitioners guard against this by trusting a vendor's stated knowledge cutoff, by asking the model what it knows, or by instructing it to answer as of a past date. To verify whether any of these safeguards can be trusted, we introduce FinDendro, a benchmark of 2,226 dated U.S. facts from 1999 to 2026, covering monthly macroeconomic series, month-end stock prices and Federal Reserve decisions. Each fact yields four prompts: a value question, Recall and Predict questions that pair each candidate value with a claim of knowing or guessing without a declared date, and a Predict question with a historical declared date. Controls for persistence and dominant outcomes keep chance accuracy near 0.27. Results show that for most frontier models, self-reports understate knowledge. GPT-5 answers 76% of controlled facts correctly but claims to know 38%, and answers 61% of the facts it says it does not know. Knowledge claims can persist beyond the measured knowledge boundary, by up to seven quarters, and a declared date removes most of the claims of prior knowledge while leaving accuracy unchanged. Backtests inside a model's training window therefore cannot be certified leak-free by self-report, instruction or stated cutoff. These findings motivate behavioral measurement of temporal knowledge boundaries, and FinDendro provides a benchmark and procedure for selecting backtest periods based on demonstrated factual knowledge.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06808
PDF
-
Measuring Risk, Not Harm: Detecting Psychological Harm Risk Factors in LLM Conversations
2026-11-04 17:22:23Nil-Jana Akpinar, Eugenia Kim, Natalie Isak, Amanda Minnich, Victoria Westerhoff, Matthew DressmanAbstract
Psychological harms from interactions with large language models cannot be monitored directly because they may emerge over repeated interactions and depend strongly on subjective individual user context. We propose measuring risk, not harm: detecting observable AI behaviors that constitute risk factors for psychological harm at the AI response level and aggregating these signals to support longitudinal monitoring. We operationalize eight such behaviors and construct a synthetic multi-label corpus of 47,062 AI responses and 373,873 response-factor labels, with targeted human annotations for validation and evaluation. We then compare trained embedding-based classifiers, direct LLM judging, and a classifier--judge cascade. All detectors are model-agnostic and operate only on LLM outputs, requiring no access to internal model states. We apply these detectors to several out-of-distribution human-AI conversation data sets from prior research. On held-out human-labeled data, the best cascade achieves macro precision of 0.86, recall of 0.76, and F1 of 0.79. On WildChat, it reduces LLM-judge calls by 97.1\% relative to direct judging. On DelusionEval, risk-factor detections cluster within conversations. Together, our results show that response-level behavioral risk-factor detection can provide a scalable measurement layer for longitudinal psychological-safety monitoring without conflating observable AI behavior with latent user harm.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06806
PDF
-
PyRUA-REAL: Robot Exploration and Adaptive Learning through RSI in the Real World
2026-11-04 16:46:03Qiang Wang, Jianxin Bi, Shulong Jiang, Ruiyang Si, Wenbo Huang, Kaiqi Chen, Jiaxin Li, Liyun Li, Xuanyi Li, Daquan ZhouAbstract
Coding agents powered by models such as GPT-6-Astra connect spatial reasoning with executable robot behavior, raising the question of how such agents can produce lasting improvements in robot capabilities from physical interaction. In this work, we study embodied recursive self-improvement (RSI) through real-world exploration, code refinement, and deployment using PyRUA-REAL, a framework in which coding agents retain interaction experience as persistent memory and reusable executable skills that inform subsequent exploration and improvement. Our empirical study places physical manipulation at the center of the improvement process, examining how agents collaborate, what kinds of execution feedback support effective code refinement, and how task specifications and previously acquired skills influence robustness and task transfer. We further investigate the efficiency and capability of the resulting programs when deployed without involving an online agent for decision-making. Across eight real-world tasks, PyRUA-REAL achieves an average success rate of 91.1%. In complementary evaluation on 42 tasks from the RoboDojo benchmark, it achieves an average success rate of 84.4%. This study provides empirical guidance for turning physical exploration into reusable robot skills that support continued improvement and robust, efficient deployment.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06768
PDF
-
Smartphone-Aided VR Exergames for HIIT: Gamifying Fitness with Real-Time Pose Estimation
2026-11-04 16:18:35Abhiram Kothagundu, Pheelip Pritipal Raipure, Abhijit Chandrakant Patil, Himangshu Sarma, Christian Eichhorn, David A. Plecher, Johanna PirkerAbstract
This paper introduces an innovative virtual reality (VR) exergame system designed to gamify High-Intensity Interval Training (HIIT) workouts through 11 predefined combo moves, including squat-punch combinations, bilateral arm strikes, and diagonal stretch combos. Unlike conventional tracking methods that often rely on wearable motion capture suits or limited headset-based sensors, our system uses a standard smartphone camera placed on a tripod to capture full-body movement. This approach offers a cost-effective and scalable alternative, particularly well-suited to the fast, dynamic motions typical of HIIT routines. The smartphone footage is processed in real time using a pose estimation algorithm, with extracted biomechanical data analyzed by a backend server built on the Model Context Protocol (MCP), Anthropic's open standard for connecting AI models to structured data sources and tools, and a GPT-4o large language model. The system generates personalized assessments of form accuracy, movement efficiency, exercise intensity, and potential injury risks, tailored specifically to high-impact, time-sensitive exercises. A within-subject study involving 20 participants (ages 18-25) compared experiences in VR and Non-VR HIIT sessions. Results indicated significantly higher enjoyment (Mean = 3.5 vs 2.8, p = 0.02), improved immersion/focus (Mean = 3.2 vs 2.8, p = 0.03), and increased likelihood to recommend (Mean = 3.2 vs 2.7, p = 0.04) under the VR condition. Confidence to continue did not differ significantly between conditions (p = 0.15), while perceived intensity remained comparable. The MCP system showed strong agreement with expert evaluation (87.5%, N = 10 sessions, one certified trainer), supporting its reliability as a feedback tool.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06734
PDF
-
LifeVal: Evaluating AI Model Performance on Personalized Agentic Consumer Tasks
2026-11-04 15:55:20Jenny Yang, Elizabeth Proehl, Anjan Bharadwaj, Emily Fan, Charlotte Cole, James Kim, Noam Brown, Phoebe Thacker, Amelia Glaese, Tejal PatwardhanAbstract
We introduce LifeVal, a benchmark evaluating AI model performance on personalized agentic consumer tasks. LifeVal covers the most valuable life tasks that a personalized digital superassistant could automate, representing over 1.7 trillion US dollars in annual willingness-to-pay across 148 consumer task categories (e.g., managing finances, moving apartments, searching for a job, finding childcare). To construct our activity distribution, we conducted a new survey of willingness-to-pay for a digital superassistant across a demographically representative sample of over 3,800 consumers, cross-referencing our results against the American Time Use Survey (Bureau of Labor Statistics, 2025) and the Multinational Time Use Study (Fisher et al., 2025). For the most valuable consumer activities, we recruited task creators to create AI evaluation tasks personalized using real ChatGPT conversations and memories, reference files, and personal context. Task creators had to pass our expertise threshold (including personally completing the task multiple times and seeing the results through in their real lives for over a year) and also write a rubric, ensuring that our evaluation measured the best personalized completion for that task. All tasks had to pass at least three rounds of human quality-control before acceptance into our final evaluation sets.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06687
PDF
-
Beyond accuracy: what AI assurance needs to establish in public services
2026-11-04 15:31:51Louise YorkeAbstract
Public bodies increasingly rely on AI-produced evidence, including classifications, summaries and assessments. These outputs can inform policy decisions and service delivery, making their reliability a matter of public accountability. Establishing whether this evidence can be relied upon requires testing its outputs and examining how organisations decide whether those tests are sufficient. We combine technical evaluation with analysis of AI governance requirements, informed by measurement theory and management-based regulation. We compare eight GPT-4o configurations classifying 1,200 UK Prime Minister's Questions into 21 policy topics, against human-coded labels and across unchanged repeats. Accuracy ranges from 68.2% to 70.3%, yet 24.3% of questions receive different labels, with changes in topic shares and rankings. Configurations agree more with one another than with human coding: agreement does not guarantee correctness. Under the implemented score-extraction procedure, the proportion flagged for human review ranges from 0.9% to 41.0%. We analyse 37 UK and EU policy documents. Both sets expect testing and oversight, but reporting expectations do not consistently cover changing answers, shared errors, selective evaluation, substantive conclusions or review routing. Some UK guidance explicitly addresses stability. The UK sample emphasises public bodies checking their own use; the EU places substantial testing duties on providers while leaving them important choices about measures and acceptance thresholds. Without appropriate checks, evidence could misrepresent policy issues, redirect attention or resources, and leave errors undetected. Public policy should require organisations to justify reliance through checks beyond aggregate accuracy, clear responsibility, access to expertise and scrutiny of results.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06655
PDF
-
MKD2World: A Typed Spatial MarkDown World Model For Web Agents
2026-11-04 14:11:56Zhihao Nan, Sifan Zhou, Yiming Cheng, Jinkai Zheng, Zheng Zhu, Si Shi, Ming Li, Fei YuAbstract
Graphical user interface (GUI) agents can improve decision-making with world-model foresight, provided that predicted states accurately reflect post-action interfaces. Existing state representations fail to jointly capture interface layout, UI semantics, and explicit locations. We introduce Typed Spatial Markdown (TSM), a Markdown-style textual state representation for desktop web interfaces. TSM serializes block-level and atomic-level UI elements according to their spatial relationships, jointly encoding their types, visual semantics, explicit locations, optional control states, and hierarchical membership. To train a screenshot-to-TSM renderer, we construct AtomBlock-WebUI, a dataset with precise annotations at both granularities. By injecting element-type labels into HTML and directly extracting bounding boxes after rendering, we avoid annotation errors caused by post-hoc inference from webpage structures. Building on TSM, we propose MKD2World, a desktop web world model trained in two stages for current-state description and action-conditioned next-state prediction. During inference, the web agent queries MKD2World as needed and performs a ``digest'' step, in which it interprets each predicted state and extracts task-relevant evidence for selecting the best action. Experiments show that MKD2World-9B achieves an EleF1 score of 26.50 on the out-of-domain test set, outperforming GPT-5.6-Sol(14.98) by 11.52 points. Across Online-Mind2Web tasks, MKD2World-9B improves the success rate of the Qwen3.5-35B web agent from 22.94% to 37.61%, achieving competitive performance among leading open-source GUI world models. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06544
PDF
-
A 3D foundation model unifying CT interpretation and segmentation
2026-11-04 13:07:27Yulu Xie, Zilong Li, Shen Xu, Yifan Bai, Liuhong Shi, Jiao Chen, Xianglei Kong, Wenchao Zhu, Na Shen, Xianghua Ye, Yang Yan, Jiaju Zheng, Yunsong Peng, Yanzhou Su, Chaohui Yu, Hao Luo, Fan WangAbstract
Radiologists interpret computed tomography (CT) scans by jointly determining what a finding represents and where it lies in three-dimensional (3D) anatomy. However, CT models have treated CT interpretation and 3D segmentation as separate tasks, leaving textual findings spatially unverifiable and overlooking potential synergy between clinical understanding and spatial perception. Here we present HoloCT, a generalist 3D foundation model unifying CT interpretation and voxel-level segmentation by jointly modelling whole-volume context and fine-grained anatomical detail, providing 3D masks as evidence. We curated HoloDATA, comprising 195,921 CT scans from 73 public datasets and six clinical cohorts, with 6.2 million instruction dialogues and 2.8 million CT-mask pairs. Across 346 tasks spanning segmentation, lesion screening, visual question answering, and report generation on 61 internal and 12 external datasets, HoloCT outperformed specialist and foundation models. In multicentre validation across 11,455 clinical CT scans from five hospitals, HoloCT outperformed competing models in lesion segmentation and report generation by 18.2 and 15.3 points. It also achieved 85.1% mean accuracy in screening thyroid tumours and colon lesions, exceeding all four participating radiologists in a retrospective reader study. Further analyses revealed bidirectional semantic-spatial synergy: language-guided segmentation delineated unseen anatomical structures and lesions as well as diffuse free-text findings, outperforming the leading approach by 22.1 points, whereas prompting the model to generate corresponding 3D masks alongside its textual outputs significantly improved interpretation performance. HoloCT shows that clinical understanding and spatial perception can be learned together within a single foundation model and offers a path towards more accurate and reliable CT analysis.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06471
PDF
-
Interactive Backdoor Attacks in LLM-Based Proactive Dialogue Systems
Abstract
LLM-based proactive dialogue systems provide goal-directed support through sustained interaction. Fine-tuning their underlying models on externally supplied dialogue data introduces backdoor risks. Existing LLM backdoor studies primarily focus on eliciting an attacker-specified response upon trigger activation. We present an interactive backdoor attack framework that uses training-data poisoning to steer post-trigger, multi-turn interactions toward an attacker-specified objective. Poisoned fine-tuning dialogues implant a trigger-conditioned guidance-policy bias that ordinary user utterances can activate, without deployment-time prompt modification or further attacker intervention. Specifically, we instantiate three complementary attacks under progressively expanded post-trigger interaction settings: (1) Direct Attack, which targets an immediate response deviation upon trigger activation, retaining the conventional trigger--response setting; (2) Constrained Progressive Attack, which progressively advances the attack objective along a predefined multi-turn trajectory; and (3) Unconstrained Progressive Attack, which extends target-directed steering to open-ended interactions with varied user continuations. Using psychological counseling as a representative setting, experiments on two LLM backbones and two dialogue datasets show that all three attacks effectively achieve their objectives under their respective interaction settings while largely preserving normal utility. Separate defense evaluations show that the tested training-data filters retain nearly all poisoned dialogues, while three post-admission baselines leave substantial residual attack-specific success.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06969
PDF
-
Twists and Turns: A Graph-Based Benchmark and Framework for Long-Term Memory in Exploration Tasks
2026-11-04 12:13:52Chongyuan Dai, Yaling Shen, Zirui Song, Junfeng Liao, Jinpeng Hu, Xiuying ChenAbstract
Long-term problem-solving processes, such as scientific research and software development, proceed along an evolving trial-and-error trajectory toward a central goal. We term these \textit{exploration tasks}, which require models to remember not only facts but also how solutions are tested against intermediate outcomes and early attempts are continually revised or revived. However, existing long-term memory research focuses on factual recall and updates, overlooking the interconnected nature of exploration. We observe that exploration processes naturally form graphs, with branching approaches linked by revisions and reconsiderations. Motivated by this, we propose \textsc{LExMem}, a graph-guided benchmark designed to evaluate \underline{\textsc{Mem}}ory in \underline{\textsc{L}}ong-term \underline{\textsc{Ex}}ploration tasks. We model exploration processes as graphs and introduce an evolutionary mechanism to increase their structural complexity, yielding 224 dialogues and 2,018 question-answer instances derived from graph structures. Building on the same insight, we propose \textsc{LExGraph}, a graph-based memory framework that incrementally organizes dialogues into interconnected memory nodes and retrieves evidence through hybrid retrieval and neighbor expansion. Extensive experiments demonstrate that \textsc{LExMem} poses a significant challenge to existing retrieval- and memory-based systems, whereas \textsc{LExGraph} achieves superior performance and generalizes effectively to external benchmarks. Codes and datasets are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06414
PDF
-
Where Should a KV-Cache Repair Budget Go? Distractor Structure and Contextual Compatibility in Non-Prefix Reuse
2026-11-04 12:02:58Yuxing Peng, Zhiqing Tang, Weijia JiaAbstract
Non-prefix KV-cache reuse encodes retrieved chunks independently and concatenates their caches. To find where a small repair budget should be spent, we vary the chunks around the answer-bearing one (the target) across three 7B-8B models and four datasets of dialogue memory, open-domain QA and API documentation. Reuse loses 19-100% of the context-dependent questions that full prefill answers, and it loses more when the other chunks are of the same kind as the target. Because the recoverable damage is spread over these other chunks, restoring a few of them recovers little, and the budget is better spent on the target. This works through contextual compatibility: recomputing the target against the reused cache beats inserting its full-prefill KV in all seven settings tested, although the recomputed KV stays far from the full-prefill KV. Question attention over reused caches, however, selects the target in at most 18.8% of development questions. A retriever finds it more often, and recomputing its top chunk after moving it next to the question significantly beats InfoFlow-style reordering at the same 5% budget in six of nine open-domain QA and API-documentation settings. On dialogue memory, though, recomputing chunks never significantly beats the token-level selector chosen for each setting.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06397
PDF
-
Evolving Support Priorities in Empathetic Reinforcement Learning
2026-11-04 10:29:50Pengyu Huang, Zhiyuan Han, Wenwen Tong, Hewei Guo, Jiangnan Chen, Sirui Chen, Lewei Lu, Beier Zhu, Xun YangAbstract
We identify a fundamental mismatch in empathetic reinforcement learning: support priorities evolve with the dialogue state, yet existing methods typically optimize predefined reward specifications that remain fixed across turns. To model these evolving support priorities, we organize empathetic support along cognitive, affective, and proactive empathy, and propose Context-Adaptive Rubric Evolution (CARE). At each turn, CARE generates a context-adaptive rubric by adjusting both the weights of these three empathy dimensions and their fine-grained evaluation criteria. The rubric generator is trained with turn-level rubric supervision and human preference data through supervised fine-tuning followed by preference-based reinforcement learning, and then serves as an adaptive reward interface for online empathetic RL. Integrated with both RLVER and MICA, CARE achieves state-of-the-art performance across SentientBench, EQBench3, and EMPA under three independent LLM judges. Notably, on EMPA, CARE improves EPM-Idx over the strongest baseline by at least 13 points under all three judges, including an increase from 28.11 to 83.54 under Gemini-2.5-Pro. Further analyses show that learned rubric priorities systematically vary across dialogue stages and user emotions, demonstrating that CARE adapts what is rewarded as support needs evolve. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.34249
PDF
-
Editing Large Language Models with Geometry-Aware Regularization
2026-11-04 09:02:10Bingqing Liu, Wei Liu, Jun Wang, Xiaobo Sun, Yuhua Li, Ruixuan LiAbstract
Knowledge editing has become a key technique for updating knowledge in large language models. However, existing methods neglect the geometric structure of the knowledge representation space, leading to two key limitations: they cannot distinguish which pre-trained knowledge should be preferentially preserved (core vs. non-core) nor which new edits are inherently difficult (hard vs. easy). To address this, we propose GEdit, a geometry-aware framework built on a Low-Rank Plus Diagonal (LR+D) factor model that captures the intrinsic low-rank structure of Transformer FFN hidden representations. GEdit features two complementary mechanisms. First, the low-rank regularization applies targeted protection on a low-rank core knowledge subspace. Second, the adaptive regularization dynamically adjusts the regularization strength based on each edit request's editability: relaxing constraints for hard edits to ensure success, and tightening them for easy edits to better preserve pretrained knowledge. Extensive experiments on GPT2-XL, GPT-J, and LLaMA-3-8B under large-scale editing scenarios, including both mini-batch and fully sequential editing settings with up to 10,000 continuous updates, show that GEdit consistently and significantly outperforms state-of-the-art baselines in both editing success and knowledge preservation.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06185
PDF
-
Can Astra Solve RoboMME without Breaking the Bank?
2026-11-04 09:01:53Bingao Chen, Haoquan Fang, C. Karen LiuAbstract
Robotic manipulation often requires remembering information that is no longer visible, such as an object's location before occlusion or the order of a demonstrated action sequence. A large vision-language planner can read this history, but calling it before every action chunk is slow and costly. We present a three-tier system for the RoboMME benchmark. GPT-6 Astra (System 2) selects a grounded subtask from stored visual history, a $\pi_{0.5}$ vision-language-action policy (System 1) executes it, and a fine-tuned Qwen3-VL-4B monitor (System 1.5) checks after each action chunk whether the subtask is finished. The instruction is kept until the monitor reports completion or a task-specific event occurs, while the policy keeps acting on new observations. On RoboMME, the system succeeds in 79.13% of episodes with an average of 3.63 Astra calls and 80.84 seconds per episode. This is 34.62 points above the best published non-oracle baseline and 4.95 points below GroundSG+Oracle, which gives the low-level policy ground-truth subgoals.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06184
PDF
-
UniCompress: From Multi-LoRA Experts to One Compact Model for Edge Intelligence
2026-11-04 07:18:55Mingkang Liu, Peipei Jiao, Weiming Meng, Tianyuan Liu, Lichen Pang, Junyan LiAbstract
Embodied and edge systems increasingly rely on vision-language models (VLMs) to support heterogeneous skills, yet deploying a separate task adapter for each skill while retaining a high-precision backbone creates substantial memory and management costs. We present UniCompress, a deployment-oriented framework that converts multi-task expertise into one compact, adapter-free model. Starting from a consolidated BF16 Qwen3-VL-4B teacher, UniCompress constructs an asymmetric INT2 student using GPTQ initialization and teacher-guided quantization recovery. The approach jointly quantizes and recovers the projection weights in the vision encoder and language backbone, enabling aggressive compression of the complete vision-language model while preserving its multi-task behavior. We evaluate UniCompress on four heterogeneous embodied tasks: posture recognition, household-safety understanding, multimodal dialogue routing, and mobile-GUI action prediction. UniCompress reduces the approximate weight storage from 8.9 GB in BF16 to 2.1 GB in INT2, corresponding to a reduction of approximately 76%. It improves the INT2 macro task score by 34.3 percentage points over GPTQ-INT2 while remaining within 0.9 points of the consolidated BF16 teacher. These results demonstrate the potential of teacher-guided joint vision-language INT2 recovery for deploying a single multi-skill VLM on resource-constrained embodied platforms.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06075
PDF
-
ProcessPrefBench: Evaluating Cross-Task Transfer of Individual Process Preferences from Naturalistic Human-AI Interaction
Abstract
In natural human-AI dialogue, users' corrections, requests, and self-descriptions carry reusable signals about how they want work to be done. These signals reveal individual process preferences, user-specific standards for evidence, depth, analytical focus, procedure, and delivery. We ask whether a preference revealed in one dialogue can shape an assistant's later answer when the task does not restate it. ProcessPrefBench uses three months of natural dialogues from two knowledge workers to build 66 source-target cases separately judged for source evidence and target applicability. Sources are preselected, so the benchmark tests application rather than retrieval. We test three models with target-only, full-history, and distilled-preference prompts. Target-specific 0-2 rubrics score preference realization, and a task gate flags severe failures. Compared with target-only prompting, full-history and imperative distilled-preference prompting raise preference realization by 0.204 and 0.244 points on the 0-2 scale, respectively, with no reliable advantage from distillation. Fabricated-evidence failures rise from 5.8% under target-only prompting to 10.1% under full-history and 10.4% under imperative prompting. ProcessPrefBench highlights a tension in learning from dialogue, where drawing on prior interactions can improve preference realization yet also invite fabricated evidence. We hope it helps build assistants that honor a user's process preferences without sacrificing factual reliability.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06065
PDF
-
Reglos: A Self-Evolving Personal Memory Agent with Recursive Self-Improvement
2026-11-04 06:56:04Sen Yang, Jiaduo Lin, Zehong Huang, Wen LiuAbstract
Personal agents draw on past conversations to tailor their responses to each user. Their memory systems store and update what each user says, and coding agents now also rewrite the harness that turns this memory into the model's context. Such patches risk overfitting, because one tested only on the failures it targets can fix those cases and help nowhere else. We present Reglos, a training-free personal memory agent that tests whether harness changes help beyond the failures they were written to fix. Its self-evolving memory adds to each user's append-only record with every conversation, as new preferences supersede old ones and facts can be forgotten. Its harness improves through recursive self-improvement, in which a coding agent proposes patches from failure traces and a critic from a second model family screens each one for benchmark gaming. After the harness is frozen, a fixed evaluator decides which further patches to accept. With the same backbone behind every system, Reglos outperforms state-of-the-art memory systems such as Mem0, MemOS and EverOS, reaching 61.3% and 84.0% on PersonaMem-v2 and LongMemEval-S with Qwen3.8-27B, and 57.5% and 87.2% with GPT-5.6 Luna.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06049
PDF
-
Selective, Risk-Controlled Emotion Forecasting in Conversation: From a Persistence Barrier to Departure Detection with Conformal Guarantees
2026-11-04 03:39:22Bin Wen, Dai-Qiao Zhang, Tien-Ping TanAbstract
Forecasting emotion in conversation is increasingly framed as predicting the next emotional state's value. We show this targets a hard quantity in a state-observed testbed and propose a learnable, deployable reformulation instead. On valence-arousal-dominance trajectories from a dyadic corpus, repeating a speaker's own previous state sets a persistence baseline that no frozen-encoder correction meaningfully improves upon and a state-space filter exceeds; the floor requires the historical state to be observed, since an estimated anchor collapses persistence below a direct forecaster. What survives is the timing of a departure from persistence, learnable on three of four corpora and near chance on the highest-base-rate corpus, a negative result we report. We recast the task as selective departure forecasting: a lead-time-weighted metric with a leakage protocol, and commitment policies whose best choice switches with the departure rate. A dialogue-level conformal risk control bounds the expected loss of committed predictions, meeting the target in all twelve configurations tested, though the guarantee is bought through abstention, with coverage and alarm recall falling sharply on the hardest corpus. One tested language model's confidence fails as a ranking signal where another succeeds, a model-dependent failure not yet attributable to family versus scale. Code and result logs are available from the corresponding author upon request.
Abstract (translated)
URL
https://arxiv.org/abs/2611.05896
PDF
