QA
-
A Plausible Explanation Is Enough to Mislead Multimodal Judges
2026-10-15 20:38:53Anglin Cai, Zhiqi Wang, Xiaozhi Yang, Yurun Lin, Dongwon Lee, Yuchen YangAbstract
Multimodal large language models (MLLMs) increasingly serve as judges in training and evaluation pipelines, often assessing answers together with explanations. Although AI judges are sensitive to textual factors, it remains unclear whether ordinary plausible explanations can sway judgments requiring visual verification. We introduce JUPE, a visual-question-answering (VQA)-style benchmark that fixes answers while varying explanations. Across 14 MLLM judges, ordinary explanations that sound plausible mislead judges, with effects comparable on average to deliberately persuasive arguments. Plain justifications and chain-of-thought rationales reduce rejection of incorrect answers by 12.7 and 13.8 percentage points, respectively. We call this failure plausibility capture. Using signal detection theory, we find a significant mean shift in decision criterion toward acceptance, without a clear change in mean discriminability. Explanations sway judgments across domains, explanation generators, and judging protocols, while tested mitigations offer limited, model-dependent protection. Such shifts can inflate performance estimates when judges evaluate answers with explanations.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22631
PDF
-
When Does Uncertainty Measure RAG Hallucination Risk?
2026-10-15 20:17:26Rajeel Ahmad Ansari, Tautik AgrahariAbstract
Uncertainty can measure hallucination risk in retrieval-augmented generation (RAG), but only when retrieved evidence constrains the answer. When evidence is present, unsupported factual claims become less likely; when retrieval coverage is poor, the model can answer from internal knowledge and assign high probability to unsupported claims. We test this across four instruction-tuned models on HotpotQA and SQuAD. After matching faithful and hallucinated answers within word-count bins, length-only classifiers fall near chance, while perplexity reaches 0.81--0.91 AUROC on targeted unsupported edits. Varying retrieval depth shows why the score changes meaning: detection can weaken with only the top-ranked passage, then recover after adding a second passage. A combined uncertainty and semantic-drift score improves calibration, and measurements remain above chance on RAGTruth QA. Results support a conditional view of uncertainty as a useful measure of RAG hallucination risk.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22615
PDF
-
The Model Knows Better: Defending Medical Multi-Agent Systems Against Prompt Injection
2026-10-15 19:43:57Fardin Ahsan Sakib, Ziwei Zhu, Ozlem UzunerAbstract
Medical multi-agent systems, in which LLM agents discuss a case, are increasingly studied for clinical decision support. Prompt injection, text that an attacker adds to a model's input, can manipulate LLMs into wrong decisions. How it affects these systems, and how to protect them, remains unclear. Across two systems, two model families and three benchmarks, a single injected passage succeeds in up to 61% of cases, and collaboration does not consistently protect against it. Existing defenses help only partly: they miss injections that look like ordinary clinical text. Yet when asked to check the injected text against the patient's findings, a model that followed the injection usually rejects it. We therefore propose a training-free defense that verifies the clinical judgments behind the system's decision. Following clinical practice, it separates the patient's findings from clinical judgments, such as diagnoses, recommendations and instructions, and checks each judgment against the findings alone, so the decision rests only on supported judgments. Our defense outperforms all baselines on every benchmark, lowering attack success on MedQA to 4-7% while maintaining accuracy on cases without an attack, and remains effective with a medical model and against defense-aware and adaptive attacks.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22594
PDF
-
SAG2: Embedding-Free Multi-Hop Retrieval with BM25 and JEV
Abstract
Strong multi-hop retrieval should be practical to deploy without expensive corpus preparation or complex database infrastructure. We present SAG2, an embedding-free retrieval architecture built around a single SQLite database, BM25, and contextual evidence decisions from JEV. SAG2 follows the query-time association principle of SAG (SQL-Retrieval Augmented Generation), while replacing its event-entity and dense indexes with a lexical index over original passages. Selected passages supply terms for further retrieval, and newly retrieved evidence guides subsequent decisions. This moves semantic evidence selection to query time, eliminating offline embedding computation, LLM-based event-entity extraction, and dedicated database servers. The resulting system combines lightweight preparation with strong retrieval accuracy: on 1,000-question subsets of MuSiQue, 2WikiMultiHopQA, and HotpotQA, SAG2 achieves the highest Recall@5 and Recall@10 among the compared methods, with Recall@10 of 86.62%, 97.43%, and 99.00%. It also reaches 81.10% document Recall@10 over the 511,962-document EnterpriseRAG-Bench corpus. Indexing all 11,656 MuSiQue passages takes 2.36 seconds, produces a 25.87 MiB database, and requires no model calls. SAG2 demonstrates that accurate multi-hop evidence retrieval can be supported by compact, rapidly prepared infrastructure, making it a practical foundation for knowledge retrieval applications.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22588
PDF
-
Star Light, Star Bright: Can Multimodal Models Parse an Astronomy Visual Question Answering Dataset Right?
Abstract
Figures are essential for scientific communication, and the field of Visual Question Answering (VQA) aims to test the figure understanding capabilities of large multimodal models (LMMs). Here, we investigate the accuracy of several low-cost LMMs on domain-specific VQA tasks for astronomical images of the sky. As instrument for this task we build a domain-specific VQA dataset comprising 2001 partially-synthetic figures divided evenly between contour plots, real telescope images drawn from NASA's SkyView, and "fake" sky images which share the axes and angular scales of the real images but draw their colors from a gaussian mixture model, alongside 47357 questions. Each figure is released as pristine and with realistic page-aging degradations mimicking the historical astronomical corpus. Testing three low-cost proprietary LMMs, we find models frequently fail to answer domain-specific questions at high accuracy. An initial comparison with 104 human-verified, astrometrically tagged figures from historical journal publications shows similar median errors in angular extent. All code is available on GitHub: this https URL and dataset is available on HuggingFace: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22474
PDF
-
MindEval2: Clinically Grounded Patients and Rubrics for Evaluating Language Models in Mental Health Support
2026-10-15 17:51:01John Mendon\c{c}a, Daniel Tschernutter, Jos\'e Pombal, Areti Vassilopoulos, Catarina Botelho, Ignacio Sarasua, Maya D'Eon, Nuno Guerreiro, Ricardo ReiAbstract
With people increasingly turning to AI chatbots for mental health support, the need to evaluate these tools is becoming more pressing. Recent benchmarks attempt to mimic a realistic setting by simulating multi-turn interactions with synthetic patients and evaluating them with an LLM-as-a-judge. However, the usefulness of these methods is limited because simulated patients can be overly forthcoming and self-reflective, and judgments typically involve opaque Likert scales with unclear practical utility. To bridge these gaps, we introduce MindEval2, an evaluation framework that consists of two components: Mental Health Quality Rubrics (MHQR), for evaluation, and MindSim, for patient simulation. For MHQR, we collaborate with PhD-level psychologists to develop a set of rubrics that break down response quality into explicit operational criteria that are more interpretable and actionable than existing evaluation taxonomies. MindSim, in turn, is an LLM harness that combines carefully-designed patient profiles with tools, enabling more varied, challenging, and realistic interactions than existing baselines. The harness also contains a memory component that is updated between each interaction, enabling MindEval2 to model the longitudinal aspect of mental health. We evaluate 18 proprietary and open-weight models on MindEval2, finding that while frontier models have largely improved on issues related to surface level quality and boundaries, guidance calibration remains the dominant failure mode across all models, accounting for most of the quality gap.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22314
PDF
-
AI Consilium: a Benchmark of LLM Clinical Multidisciplinary Second Opinions
2026-10-15 17:46:37Alexey A. Bokov, Ivan I. Panin, Nikolay B. Nechaev, Mikhail Yu. Valkov, Valeria Yu. Chernina, Natalia Gombolevskaya, Ayyaz Hussain, Vladimir M. Agafonov, Victor A. Gombolevskiy, Aleksandr V. Nesterov, Iaroslav R. Bespalov, Ivan V. Oseledets, Dmitry V. DylovAbstract
Large language models (LLMs) can generate differential diagnoses for complex cases, but a useful second opinion must also be factually grounded, clinically coherent, actionable, and safe. We developed a multidimensional benchmark using 300 diagnostically resolved NEJM--MedQA cases: 110 for physician reference ratings and Judge calibration and 190 for held-out evaluation. Eight single-model pipelines generated independent role-specific opinions and interactive-consilium reports under free-form and structured clinical-reasoning conditions. A physician-calibrated LLM Judge evaluated 3,040 final reports and the corresponding structured primary-role outputs. Model identity separated report quality more strongly than response format. Structured final reports had higher overall mean scores in seven of eight model pipelines, with their clearest advantage in management (2.740 vs. 2.436). Compared with the structured pre-consilium primary-role opinion, the complete structured synthesis had higher pooled scores across all five shared criteria, with the largest increases in problem prioritization, factual grounding, and reasoning coherence. GPT-5.6-Sol led every evaluated component and reached consensus in the fewest review rounds. These findings show that the benchmark can distinguish model capability, the contribution of multidisciplinary synthesis, criterion-specific effects of response structure, deliberation dynamics, and inference requirements within one common-case evaluation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22298
PDF
-
Beyond Downstream QA: Rethinking How We Evaluate Agent Memory
2026-10-15 16:58:12Sebastian-Antonio Toma, Jean de Kernier, Mike Ply, Oliviu MateiAbstract
Agent memory benchmarks evaluate whether an agent's responses reflect correct knowledge, measuring downstream question-answering accuracy as a proxy for memory quality. We show this evaluation paradigm is incomplete: it conflates memory correctness with retrieval and generation quality, producing both false positives where correct responses mask broken memory and false negatives where incorrect responses blame correct memory for retrieval failures. We introduce FEB-30, a benchmark of 30 fact-evolution trajectories spanning 6 diagnostic categories and 3 difficulty levels, constructed via paradigm inversion: documents are generated from known fact trajectories, yielding deterministic ground truth without human annotation. Each trajectory defines how a fact should evolve across multi-author artifacts (documents, emails, conversations), enabling direct inspection of the memory store after each ingestion step. Applying FEB-30 to a representative memory system, we demonstrate that intrinsic and extrinsic evaluation diverge by an average of 16 percentage points, with 44% of trajectories exceeding meaningful divergence thresholds. Diagnostic decomposition reveals that the system correctly classifies memory operations (create, update, reinforce, supersede) only 20% of the time, a failure entirely invisible to extrinsic evaluation, and that failure modes differ systematically by category and difficulty. We release the benchmark, document generation pipeline, and scoring framework to support reproducible evaluation of agent memory systems.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22209
PDF
-
Believed but Not Said: Measuring Hidden Belief Collapse in Multi-Agent LLM Discussions
2026-10-15 16:12:07Liangjie Huang, Henry Peng Zou, Wei-Chieh Huang, Wooseong Yang, Yuwei Han, Philip S. YuAbstract
LLM systems increasingly rely on groups of agents that discuss, critique, and check one another, assuming that peers will catch individual errors. We test this assumption against a minimal adversary. In a ten-agent factual discussion, one or three adversarial agents repeatedly assert a plausible false answer. After each round we probe each benign agent's private answer through a separate call whose response is hidden from its peers, and we separately label its public stance toward the claim. Across six models and three factual-QA datasets, groups remain stable without an attacker: only 0.6% of benign agents finish with the false answer. A single adversarial agent increases this rate to 44.8% and three to 60.5%. Studies of conformity typically report public agreement without private change; we find the reverse. With three adversarial agents present, benign agents hold the false answer in 51.6% of exposed turns but publicly endorse it in only 19.7%. Much of the influence therefore remains invisible in the discussion, and the false answers persist when agents are asked for their own views. Agents that retain the true answer often fail to defend it; once adopted, the false answer spreads among benign agents, and baseline knowledge does not predict robustness.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22138
PDF
-
CoWorld Reasoner: Agentic Multimodal Reasoning with the Evolving Video World Model-Driven Harness
2026-10-15 13:59:15Dongjie Cheng, Ruifeng Yuan, Ran Wei, Ning Song, Yongqi Li, Wenjie LiAbstract
As Vision-Language Models (VLMs) advance, they are increasingly expected to perform spatiotemporal reasoning over motion, actions, and view changes beyond what the input images show. Video World Models (VWMs) provide a natural unified engine for visual imagination by generating task-relevant visual content as additional evidence. However, existing approaches typically invoke a VWM through fixed pipelines centered on a predefined form of visual imagination, such as novel-view synthesis. To support flexible visual imagination for diverse reasoning tasks, we introduce CoWorld Reasoner, an agentic framework that uses a VWM as a unified visual reasoning engine. Its Video World Model-Driven Harness exposes multiple visual operations through tools and uses skills to guide the VLM in deciding whether to imagine, selecting an operation, constructing a generation request, and interpreting the resulting visual evidence. We further introduce VLM-VWM Harness Co-Evolution, which jointly revises tools, skills, and execution code based on execution feedback while keeping both model weights fixed. Across seven benchmarks spanning spatial intelligence, temporal and causal reasoning, and perceptual reasoning, CoWorld Reasoner outperforms direct reasoning with the same VLM. The strongest variant improves on all seven benchmarks, including relative accuracy gains of 11.8% on MMSI and 13.0% on ERQA, and outperforms all five evolving baselines using the same backbone across five benchmarks.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21910
PDF
-
Content associations with answer selection and engagement in supply chain community question answering
Abstract
Community question-answering platforms are important ecosystems for knowledge sharing, yet research on what makes an answer best or a question engaging has often focused on either individual lexical features or broad topics. This exploratory study examines both levels in Yahoo! Chiebukuro, asking which nouns and semantic noun clusters are associated with best-answer selection and question engagement. We analyze a large corpus of questions and answer-tier posts collected under the keyword logistics, using an offline machine-translation pipeline with manually validated noun-level fidelity. Best-answer selection is modeled with conditional logistic regression within question threads, controlling for answer length, order, and question-answer noun overlap. Engagement is modeled in two stages: whether a question receives any response and, conditional on receiving one, how many responses it attracts. Operational logistics nouns such as distribution, warehouse, and center are associated with best-answer selection, whereas broader civic and infrastructure nouns such as car, tax, and shinkansen are associated with higher engagement. At the cluster level, most semantic noun clusters are associated with best-answer selection, while the clusters associated with response likelihood and response volume are largely distinct. These findings reveal differentiated content-outcome profiles across answer and question levels and provide a domain-wide descriptive map of engagement and answer selection in logistics-related cQA discourse.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21807
PDF
-
Learning to Think and Explore in 3D World
2026-10-15 12:38:48Yijiang Li, Bingyang Wang, Nuno VasconcelosAbstract
We study how vision-language models (VLMs) can learn to think and actively explore in 3D space. Instead of providing multi-view images, videos, or 3D representations to the model, we preserve the native visual encoding of VLMs, i.e., a single image, one at a time, just like humans, and treat the 3D representation only as an environment with which the model can interact through actions (e.g., move left) and observations (rendered images). Each rollout begins from an initial first-person view and a visual question. The model can then iteratively reason, navigate, and reorient its viewpoint before committing to a final answer. Following an initial trajectory-supervised finetuning, we apply reinforcement learning (RL) with rewards driven primarily by final-answer correctness. Crucially, RL provides no direct supervision over which viewpoints the model should visit or which exploration actions it should take. Instead, the model must learn an effective exploration policy solely from the extent to which its interactions improve performance. Across six 3D benchmarks, our model ACT3D achieves an average accuracy of 53.2% that improves its base Qwen model by 22.0% and surpasses proprietary Gemini 3.6 Flash. ACT3D also outperforms existing open-source 3D methods while using 50-70% fewer input frames, and generalizes to unseen domains with an average improvement of 5.9% over its supervised initialization. Further analysis reveals adaptive, question-conditioned exploration. Performance gains over the base model increase from 0.6% on questions answerable from the initial view to 16.3% on those requiring extensive exploration. ACT3D searches for occluded targets, avoids unnecessary exploration, and acquires complementary viewpoints for spatial comparisons. These findings demonstrate that outcome-based RL enables VLMs not only to reason over visual evidence, but also to learn when and how to acquire it.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21783
PDF
-
TwinPrune: Density-Aware Two-Phase Token Pruning for Vision-Language Models
2026-10-15 10:58:26Kai Liu, Anqi Li, Junxian Li, Zhixin Wang, Zhikai Chen, Renjing Pei, Yulun ZhangAbstract
We propose a unified spatial-density signal to score token importance for both inference phases: bipartite merge for prefill and KV eviction for decode, yielding measurable gains in each stage. To isolate the two phases, we split benchmarks by scoring logic. Prefill probes (MMBench, POPE, ScienceQA) evaluate only the first decoded token; their accuracy reflects prefill logits argmax before any decode KV eviction. Full-pipeline probes (TextVQA, DocVQA, MM-Vet) assess the complete generated sequence and capture both phases. We identify a critical evaluation pitfall: decode pruning claims validated solely on prefill probes measure prefill quality, not decode performance. Experiments show discarding all visual KV during decode barely affects prefill-probe accuracy but degrades TextVQA and MM-Vet drastically; this insensitivity stems from the scoring rule, not compression intensity. Evaluated on seven model variants (InternVL-3.5, Qwen3-VL, LLaVA-1.5) and three full-pipeline benchmarks, our method achieves a three-way Pareto frontier across compute, memory and accuracy. Density-based prefill compression maintains strong accuracy, scales linearly with visual token count, and delivers 100x faster token selection at high resolution. For decode, density top-k KV eviction consistently outperforms strong baselines H2O, SnapKV and StreamingLLM on TextVQA and MM-Vet across three retention ratios. At 0.125 keep ratio on TextVQA, it surpasses H2O by 9.6 points; InternVL-3.5 models (2B to 38B) maintain a 7 to 10 point advantage. Compression scales favorably with model size: every measured 8B to 38B model transition reduces accuracy loss instead of worsening it. We suggest MM-Vet or DocVQA as mandatory full-pipeline validation for any decode-phase claims. Our code is available at this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.17530
PDF
-
Qwen-Audio-Jev: A Unified Interface for Audio Decisions
2026-10-15 09:59:07Ying Fang, Zhifu Gao, Qing Gu, Jiajun He, Kangqi Jing, Xiangang Li, Yu Pu, Wupeng WangAbstract
Large audio language models (LALMs) have made substantial progress in audio understanding. However, in high-throughput applications requiring frequent selection, judgment, and scoring, autoregressive text generation introduces additional computational overhead and response latency. To address this limitation, we introduce Qwen-Audio-Jev by augmenting Qwen-Audio-3.1-ASR-Flash-Next with a dedicated Jev decision head. The model unifies selection, binary judgment, and scoring through three decision primitives: CHOICE, NOUL, and SCORE. Given audio, a natural-language question, and an explicit answer specification, it directly produces a task-conditioned probability distribution or a numerical score through typed decision readouts. Evaluation across 18 labeled configurations covers all three primitives: for CHOICE, Qwen-Audio-Jev achieves accuracies of 78.70% on MMAU-mini and 84.06% on MMSU; for NOUL, it achieves an equal error rate of 6.50% on the VoxCeleb1-O speaker verification benchmark; and for SCORE, the model achieves a normalized mean absolute error of 0.1062 on NISQA overall quality assessment, with Pearson and Spearman correlations of 0.8210 and 0.8074, respectively. Compared with the original Qwen-Audio-3.1-ASR-Flash-Next, Qwen-Audio-Jev achieves an approximately 20x inference speedup. It demonstrates its potential for efficient, high-throughput audio decision-making in applications such as large-scale audio screening, speaker verification, and automated quality assessment.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21614
PDF
-
Hear, Localize, and Reason: Spatially Aware Scene Understanding for Audio-Visual LLMs
2026-10-15 09:34:05Kim Sung-Bin, Lee Jung-Mok, Jinwoo Jung, Oh Hyun-Bin, Hyeonggon Ryu, David Harwath, Tae-Hyun OhAbstract
Audio-visual large language models (AV-LLMs) have made strong progress in multimodal understanding, yet most treat audio as monaural semantic content, limiting their ability to reason about where sounds originate and how they relate to the visual scene. Recent spatial audio-visual studies address parts of this problem, but often focus on specific abilities, such as spatial correspondence or direction and distance reasoning. In this work, we introduce HLR-AVSceneQA, a comprehensive benchmark with a hear-localize-reason hierarchy that evaluates whether models can recognize what is heard, localize sound sources in egocentric and allocentric views, and use these localized sources to reason about how they relate to the visual scene. We further introduce HLR-LLM, which augments a strong audio-visual foundation model with a binaural spatial audio branch alongside its monaural semantic audio pathway. We train HLR-LLM with a curriculum that incorporates final-stage chain-of-thought supervision for multi-step spatial reasoning. Experiments show that existing AV-LLMs remain limited in spatial grounding and relational reasoning, while HLR-LLM substantially improves spatial audio-visual scene understanding without compromising semantic audio-visual perception.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21588
PDF
-
Can Visual Generation Expand What Unified Multimodal Models Know?
2026-10-15 08:03:24Wenkai Li, Wenyi Hong, Zhuoyi Yang, Jie TangAbstract
Unified multimodal models (UMMs) receive image-generation supervision that exposes them to visual information not fully documented in text. Can learning to generate images expand what pretrained models know? We introduce Knowledge Transfer Probing (KTP), a controlled protocol that supplies new knowledge through image-generation training and tests its accessibility through text-only question answering. Across seven knowledge categories and three UMMs, we observe direct but uneven transfer from visual supervision to language. Motivated by these observations, we successively introduce Textual Alignment and Interleaved Image--Text Alignment, which connect generation and answering through shared knowledge and interleaved responses, respectively. Guidance on selected entities can improve knowledge access on other entities without QA supervision, with additional gains from interleaved alignment. Further analysis shows that knowledge correctly reproduced in images is often more accessible through text, although substantial gaps remain between the two forms of access. These findings support visual generation as a source of knowledge beyond textual supervision, and motivate joint investigation of training data design and model architecture to make this knowledge more broadly accessible.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21459
PDF
-
Do Agents Need a New Kind of Paper? SPRA: Structured Paper Representation for Agents
2026-10-15 07:34:12Yutong Leng, Haojiong Chen, Fukai Shang, Xiaoyang Wang, Mindong Liu, Runyuan Ma, Jiantao QiuAbstract
Scientific agents must connect research problems, methods, and findings dispersed through narrative articles. We introduce SPRA (Structured Paper Representation for Agents), a paper-level representation of persistent research objects and typed relations. Its empirical-AI profile organizes Problems, Contributions, Components, ExperimentSetups, Measures, and Findings for querying, traversal, and reuse. Selected paper-level citation relations record dependencies, component use, and comparisons with prior work; source locations support verification. We instantiate SPRA across more than one million AI papers, with 19.95 million research units and 24.07 million internal relations. Evaluations access SPRA through Schema-RAG with task evidence fixed before inference. Across seven subfields, SPRA improves source-conditioned scientific QA by 0.381/5 over passage retrieval while remaining close to Full Compact (0.078/5 lower on average). In directed cross-paper reasoning, qualification improves by 0.184/5 over passage retrieval; Top-5 synthesis shows mixed quality effects. Across all paired RQ2 tasks, including Top-5, input+output tokens decrease by 28.5% relative to passage retrieval and 95.3% relative to Full Compact. In idea generation, a 0.067-point lower Overall score than Full Compact accompanies 93.7% fewer input+output tokens. Together, these results support SPRA as a usable representation of scientific content and a foundation for research workflows that connect, inspect, and reuse paper-level research objects. The SPRA resource is accessible through the SciVerse scholarly-data platform.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21424
PDF
-
Embeddings Are Overpriced? A Frozen 16 MB Vocabulary for Small and Ternary Language Models
Abstract
In a small language model the vocabulary is the single largest part. In Gemma 3 270M the embedding table holds 168M of 268M parameters, and because quantisation methods leave the embedding in 16-bit, it is also most of the file once the rest of the model is compressed. We ask what that table actually buys. We replace it with one frozen table of 512-bit codes, 16 MB, with no trainable parameters, derived once from a pretrained embedding by principal-component projection and sign binarisation, and we train the same Gemma-shaped body from scratch on the same 2.05B tokens with and without it. The learned table buys 0.20 nats of validation loss for 2.6 times the trainable parameters, but on LAMBADA, HellaSwag and PIQA the frozen-table model is better or tied; only ARC-Easy favours the learned table. With a ternary BitNet b1.58 body the whole model is a 46 MB file, still ties the float model on LAMBADA and PIQA, and on a laptop CPU generates 615 to 740 tokens per second in 62 MB of memory, five to six times the speed of the float model's 8-bit GGUF in this http URL at a seventh of the memory. The frozen table wins by 1.7 to 2.3 nats on rare words, accepts 10,000 new words after training with a 3% cost where the learned table collapses by 43%, and all of it is released with the weights, the data and every evaluation answer.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22428
PDF
-
OpCredit: Operation-Aware Policy Learning for Agentic Knowledge Graph Question Answering
2026-10-15 06:29:17Yucheng Li, Mingyuan Li, Xiaxia Wang, Gong ChengAbstract
Agentic knowledge graph question answering(KGQA) relies on sequences of executable operations, but trajectory-level rewards obscure their individual contributions. Successful trajectories may contain ineffective operations, while failed trajectories may contain useful ones. To assess individual operations, we propose OpCredit, an operationaware policy-learning framework that combines downstream outcome credit with immediate transition credit: Branch Outcome Credit (BOC) reuses ordinary rollouts to compare terminal task rewards observed after different operations under matched navigation contexts; Frontier Transition Credit (FTC) measures operation-induced changes in answer-conditioned frontier potential. The two complementary signals jointly supervise the corresponding decision spans during training, while inference uses only the learned policy and standard KG interface. Experiments on ComplexWebQuestions, WebQSP, and GrailQA across three backbones demonstrate consistent improvements in KGQA performance.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21345
PDF
-
DocPilot: Interactive Agent Orchestration and Training for Long Visual Document Understanding
2026-10-15 06:16:43Zhuowen Liang, Xiaotian Lin, Yuyu Luo, Haixun Wang, Nan TangAbstract
Multimodal long-document question answering requires models to seek sparse evidence across pages and modalities, understand heterogeneous document content, and reason over the collected evidence. Even advanced vision-language models (VLMs) can overlook sparse evidence and struggle with cross-modal reasoning in a single pass. Existing document agents further introduce multi-step interaction, but some still rely on predefined workflows or coarse-grained actions, limiting the flexibility and granularity of document reasoning. We introduce DocPilot, an agentic document framework that supports expressive orchestration and makes complex document solving learnable by small language models (SLMs). DocPilot orchestrates evidence seeking through page-level navigation and fine-grained evidence localization, and integrates local visual inspection, code-based numerical reasoning, and cross-modal reasoning for multimodal understanding. To transfer these capabilities to small models, we propose curriculum-based agentic training that progresses from single-ability learning to adaptive orchestration through supervision from data-grounded reasoning traces and executable interaction trajectories. Across MMLongBench-Doc, DocBench, FinRAGBench-V, and MADQA, DocPilot achieves strong gains with frontier VLM backbones, while DocPilot-4B delivers competitive performance against substantially larger models, demonstrating strong effectiveness and generalization across diverse long-document reasoning settings. The code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21327
PDF
