AllyshipContent Radar

News 1647

Chủ đề cộng đồng đang thảo luận

Crawl live-1795068900000 · 13:22 19 thg 11, 2026 · Xuất bản 14:10 19 thg 11, 2026

171 / 1647 chủ đề đạt ngưỡng 55 trong khoảng này.

1

Orca - chạy một đội các coding agents bằng subscription của bạn

72

2 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · chưa có số tương tác · Nguồn crawl

stablyai, orca_build 0 bài viết · GitHub discovery: AI agents, X
Biên tập tiếng Việt
Chi tiết nguồn

Orca được mô tả là cho phép chạy một “fleet of coding agents” (ví dụ Claude Code, Codex) với subscription của riêng bạn. Nền tảng có sẵn trên desktop, mobile và remote runtime.

Orca lets you run a fleet of coding agents (e.g. Claude Code, Codex) with your own subscription. Available on desktop, mobile and remote runtime.

  • Orca lets you run a fleet of coding agents (e.g. Claude Code, Codex) with your own subscription.
  • Orca lets you run a fleet of coding agents (e.g. Claude Code, Codex) with your own subscription.
  • Available on desktop, mobile and remote runtime.
2

Archify - biến ý tưởng/plan/codebase thành sơ đồ tương tác

72

2 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · chưa có số tương tác · Nguồn crawl

tt-a1i, tom_doerr 0 bài viết · GitHub discovery: LLM, X
Biên tập tiếng Việt
Chi tiết nguồn

Archify được mô tả là chuyển mọi ý tưởng, kế hoạch hoặc codebase thành một sơ đồ tương tác “đẹp”. Nó là một agent skill cho Claude Code, Codex và nhiều nền tảng khác.

Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.

  • Turn any idea, plan, or codebase into a beautiful interactive diagram.
  • Turn any idea, plan, or codebase into a beautiful interactive diagram.
  • An agent skill for Claude Code, Codex, and more.
3

Nov 1997 vs Nov 2026

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

rauchg 0 bài viết · X
Nguyên văn nguồn
Chi tiết nguồn

Nov 1997 vs Nov 2026 Media

4

langgraph==1.2.23

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

github-actions[bot] 1 bài viết · langchain-ai/langgraph releases
Nguyên văn nguồn
Chi tiết nguồn

<p>Changes since 1.2.22</p> <ul> <li>release(langgraph): 1.2.23 (<a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="6482730562" data-permission-text="Title is private" data-url="https://github.com/langchain-ai/langgraph/issues/9742" data-hovercard-type="pull_request" data-hovercard-url="/langchain-ai/langgraph/pull/9742/hovercard" href="https://github.com/langchain-ai/langgraph/pull/9742">#9742</a>)</li> <li>release(prebuilt): 1.1.3 (<a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="6482729770" data-permission-text="Title is private" data-url="https://github.com/langchain-ai/langgraph/issues/9741" data-hovercard-type="pull_request" data-hovercard-url="/langchain-ai/langgraph/pull/9741/hovercard" href="https://github.com/langchain-ai/langgraph/pull/9741">#9741</a>)</li> <li>fix(langgraph,prebuilt): give Send-dispatched tool calls the same state as an edge (<a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="6472223558" data-permission-text="Title is private" data-url="https://github.com/langchain-ai/langgraph/issues/9728" data-hovercard-type="pull_request" data-hovercard-url="/langchain-ai/langgraph/pull/9728/hovercard" href="https://github.com/langchain-ai/langgraph/pull/9728">#9728</a>)</li> <li>chore(deps): bump opentelemetry-api from 1.45.1 to 1.45.2 in /libs/langgraph (<a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="6377648315" data-permission-text="Title is private" data-url="https://github.com/langchain-ai/langgraph/issues/9696" data-hovercard-type="pull_request" data-hovercard-url="/langchain-ai/langgraph/pull/9696/hovercard" href="https://github.com/langchain-ai/langgraph/pull/9696">#9696</a>)</li> <li>fix(langgraph): avoid warning races in dynamic schemas (<a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="6408559559" data-permission-text="Title is private" data-url="https://github.com/langchain-ai/langgraph/issues/9716" data-hovercard-type="pull_request" data-hovercard-url="/langchain-ai/langgraph/pull/9716/hovercard" href="https://github.com/langchain-ai/langgraph/pull/9716">#9716</a>)</li> </ul>

5

langgraph-prebuilt==1.1.3

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

github-actions[bot] 1 bài viết · langchain-ai/langgraph releases
Nguyên văn nguồn
Chi tiết nguồn

<p>Changes since prebuilt==1.1.2</p> <ul> <li>release(prebuilt): 1.1.3 (<a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="6482729770" data-permission-text="Title is private" data-url="https://github.com/langchain-ai/langgraph/issues/9741" data-hovercard-type="pull_request" data-hovercard-url="/langchain-ai/langgraph/pull/9741/hovercard" href="https://github.com/langchain-ai/langgraph/pull/9741">#9741</a>)</li> <li>fix(langgraph,prebuilt): give Send-dispatched tool calls the same state as an edge (<a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="6472223558" data-permission-text="Title is private" data-url="https://github.com/langchain-ai/langgraph/issues/9728" data-hovercard-type="pull_request" data-hovercard-url="/langchain-ai/langgraph/pull/9728/hovercard" href="https://github.com/langchain-ai/langgraph/pull/9728">#9728</a>)</li> <li>fix(prebuilt): make wrap_tool_call state overrides reach the tool (<a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="6473031915" data-permission-text="Title is private" data-url="https://github.com/langchain-ai/langgraph/issues/9730" data-hovercard-type="pull_request" data-hovercard-url="/langchain-ai/langgraph/pull/9730/hovercard" href="https://github.com/langchain-ai/langgraph/pull/9730">#9730</a>)</li> </ul>

9

Evidence-Based Credit Assignment for Search-Augmented Language Models

84

8 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · 3 tương tác đã đo · Nguồn crawl

Wen Wang, Jindong Wang và 6 nguồn khác 1 bài viết · Hugging Face Papers, arXiv cs.AI
Biên tập tiếng Việt
Chi tiết nguồn

Bài báo nói rằng reinforcement learning từ phần thưởng cuối cùng cho phép search-augmented language models xen kẽ suy luận và truy xuất mà không cần nhãn từng bước, nhưng giám sát theo kết quả gán credit giống nhau cho mọi lần tìm kiếm trong một trajectory, dù có truy xuất hữu ích hay không. Họ giới thiệu Evidence-based Credit Assignment (ECA) để bổ sung tín hiệu phụ (training-only) đo việc các tài liệu đã truy xuất cải thiện xác suất của câu trả lời tham chiếu. ECA dùng evidence-only prompt với chỉ câu hỏi và các tài liệu đã quan sát (đã loại trùng), để tách tiện ích của đoạn truy xuất khỏi biến thiên do câu chữ suy nghĩ/ truy vấn sinh ra.

Reinforcement learning from terminal answer rewards enables search-augmented language models to interleave reasoning and retrieval without step-level annotations, yet outcome supervision assigns identical credit to every search in a trajectory regardless of whether it retrieved useful information. This limitation is especially severe when all sampled rollouts for a question fail, collapsing group-centered outcome advantages to zero even when trajectories gather markedly different evidence. We present Evidence-based Credit Assignment (ECA), which augments terminal outcome rewards with a training-only auxiliary signal measuring how retrieved documents improve the likelihood of a reference answer. Rather than scoring the full dialogue prefix, ECA queries a frozen snapshot of the current policy under an evidence-only prompt containing solely the question and the deduplicated documents observed so far, isolating the utility of retrieved passages from surface variations in generated thoughts or search queries. Within this framework, we compare two return formulations, ECA-Step (which accumulates step-clipped potential increments) and ECA-Horizon (which preserves the telescoping horizon gain in potential), paired with cross-fold group normalization, novelty gating, and search-local token assignment. Across seven Search QA benchmarks, ECA-Horizon improves strict macro exact match over an outcome-only GRPO baseline by 1.03 and 4.80 percentage points on Qwen2.5-3B- and 7B-Instruct, respectively, outperforming both RLOO and GiGPO. Zero-shot evaluation on MultiHop-RAG further demonstrates strong transfer to multi-hop inference queries.

  • ECA-Horizon improves strict macro exact match over an outcome-only GRPO baseline by 1.03 and 4.80 percentage points on Qwen2.5-3B- and 7B-Instruct, respectively, outperforming both RLOO and GiGPO.
  • ECA-Horizon improves strict macro exact match over an outcome-only GRPO baseline by 1.03 and 4.80 percentage points on Qwen2.5-3B- and 7B-Instruct, respectively, outperforming both RLOO and GiGPO.
  • Zero-shot evaluation on MultiHop-RAG further demonstrates strong transfer to multi-hop inference queries.
  • Within this framework, we compare two return formulations, ECA-Step (which accumulates step-clipped potential increments) and ECA-Horizon (which preserves the telescoping horizon gain in potential), paired with cross-fold group normalization, novelty gating, and search-local token assignment.
10

Human-AI Mutualism Is Unstable under Capability Asymmetry

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

Aydin Mohseni 1 bài viết · arXiv cs.AI
Nguyên văn nguồn
Chi tiết nguồn

arXiv:2611.23322v1 Announce Type: new Abstract: One hope for a good human future alongside advanced AI rests on enduring mutualism: humans and AI will need each other, so the relationship will stay good for both. We argue that this hope fails as AI capability grows. Bargaining guarantees each side only what it would get if bargaining failed. For humans, this can be less than they had before AI. In a simple game-theoretic model, humans stay as well off as before AI without alignment only while they have leverage over the AI: either the AI depends on what they supply, or they can impose costs on the AI that are large relative to what the AI can produce. Once humans have neither kind of leverage, they stay as well off as before AI only if the AI is aligned with them. If the AI's goals are insatiable, the alignment required approaches perfect alignment as AI capability grows. Thus, mutualism is not a substitute for alignment. And when AI variants that keep more resources spread faster, alignment lasts only while misaligned variants are reliably sanctioned. In these two senses, human-AI mutualism is unstable.

11

Training Language Models for Introspective Oversight

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

Alex Lin Wang, Linus Yifeng Tang, Dami Choi, Neil Chowdhury 1 bài viết · arXiv cs.AI
Nguyên văn nguồn
Chi tiết nguồn

arXiv:2611.23365v1 Announce Type: new Abstract: Language models increasingly exhibit behaviors that are difficult to detect in transcripts, such as reward hacking, deception, and sycophancy. Asking the assistant follow-up questions about its actions is unreliable, since models are generally not trained to report their own misbehavior. As a result, approaches to oversight typically involve querying external models. These face limitations: external transcript monitoring operates only on visible model outputs, and activation decoders lack full context and are prone to confabulation. We introduce introspective oversight, which trains a new role in the model to answer arbitrary questions about the assistant, rewarding answers that are verified against the assistant's actual behavior. We implement this by adding a separate, third-person observer role that answers these queries, which we can train solely for accuracy and separately from the assistant. On five held-out oversight evaluations, an observer trained on Qwen3.6-27B obtains a mean AUROC of 0.907, outperforming honesty training (0.864), transcript monitoring (0.828), and activation oracles (0.796). We further find that training an observer makes the assistant itself easier to monitor, with every baseline method improving on average when applied to the fine-tuned assistant. These results suggest that training models to answer verifiable questions about themselves is a tractable approach to overseeing unintended behavior.

12

Where the Tokens Go: Heat, Entropy and Error in Agentic Coding

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

Al\'an Aspuru-Guzik, Varinia Bernales 1 bài viết · arXiv cs.AI
Nguyên văn nguồn
Chi tiết nguồn

arXiv:2611.23375v1 Announce Type: new Abstract: Coding agents are billed by the token, yet software engineering says nothing about what a token actually buys. Here we introduce a theory of software thermodynamics. The theory draws analogues from classical and stochastic thermodynamics, extends them, and applies them to modern agentic coding. We count the tokens an agent generates as its cost and divide that cost into work and heat. The test suite acts as a software Maxwell's daemon that judges every coding change. We test the theory with an analogue of the experiments in which a single molecule is pulled open and let fold again: an agent makes a change to a repository (coding) and then undoes it (uncoding), many times over, and we count the tokens of every model call. The cycle returns the requested edits to where they began, with each direction started from a stored reference tree, and the spread of its cost over repeated cycles defines a software temperature, which rose with the sampling temperature of the model. About 80 per cent of the tokens of a successful run are generated in model calls that leave the requested change where it was, and we call these tokens heat. The free energy of a change, which we estimate by analogy with the equality of Jarzynski, is 14 to 22 per cent of the mean cost of a successful coding run. Coding costs 1.1 to 1.5 times as much as uncoding. The daemon is imperfect: the verdict of a test suite varies with its environment, and a suite that accepts a broken change has a cost in tokens. The practical implication of the proposed theory could be new tools for analysing and optimising coding agents through the lens of thermodynamics.

13

HardwareDx: A Foundational Graph Model System for Datacenter Machine Repairs

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

Yuanlin Wen, Elan Markowitz, Zubo Gu, Sami Abu-El-Haija, Bryan Perozzi, Mikhail Galkin, Ali Parviz, Aayush Gupta, Venkata Chivukula, Griffin Hadfield, Aravind Akella, Daniel J. Frame, Vahab Mirrokni, Amin Vahdat 1 bài viết · arXiv cs.AI
Nguyên văn nguồn
Chi tiết nguồn

arXiv:2611.23398v1 Announce Type: new Abstract: The rapid scale-up of AI infrastructure has made datacenter reliability a cornerstone of the cloud business economy. Since hardware failures in hyper-scale AI clusters can stall multi-million dollar training workloads, the downtime of individual machines can cause outsized economic losses. Minimizing machine downtime, therefore, is more important than ever. To address this, we present Hardware Diagnoser (HardwareDx), an AI-driven hardware diagnosis system that applies a graph foundation model approach to automated datacenter maintenance. It allows a single model to diagnose many platforms and accelerate onboarding of new hardware products. Deployed at production scale at Google, HardwareDx yields substantial efficiency gains across diverse compute architectures. Real-world evaluations demonstrate that it reduces production downtime by 18.3% on GPU platforms and 16.1% on TPUs. Furthermore, it significantly accelerates hardware deployment, cutting quality assurance (QA) time by 28.3% for GPUs and 25.1% for TPUs. These results establish HardwareDx as a field-tested solution for maximizing the reliability and cost efficiency of next generation AI fleets.

14

RFBench: A Simulator-Grounded Multimodal Benchmark for Passive RF Layout Design and Understanding

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

Jiarui Cui, Boxun Yan 1 bài viết · arXiv cs.AI
Nguyên văn nguồn
Chi tiết nguồn

arXiv:2611.23410v1 Announce Type: new Abstract: While multimodal language models can interpret diagrams and generate structured outputs, their capacity to connect passive radio-frequency (RF) design intent, layout geometry, and electromagnetic behavior remains largely untested. To address this gap, we introduce RFBench, a simulator-grounded dataset and benchmark for passive RF layout design and understanding. The dataset contains 10,000 two-port planar layouts simulated using ADS Momentum, with each layout represented by editable geometric primitives, a raster image, a 16x16 occupancy grid, complex S-parameters at 201 frequency points, a structural category, and an RF response label. Building on these aligned representations, we define seven tasks spanning specification-conditioned layout generation, representation translation, response prediction, simulator-based validation, design diagnosis and improvement, structural understanding, and response classification. Extensive baselines across seven multimodal language models reveal systematic weaknesses in generating structurally valid layouts and predicting electromagnetically faithful responses. We show that RF-specific fine-tuning increases T1a structural validity from 0.0% to 83.2% and the T3 primitive-input within-2-dB rate from 17.7% to 62.8%, demonstrating the value of domain adaptation while leaving considerable room for further progress. RFBench establishes a common testbed for evaluating multimodal RF capabilities and guiding the development of models that connect design intent and layout representations with physical behavior.

15

Why Sub-4-Bit Vision CNNs Collapse and Where Mixed-Precision Recovery Stops

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

Michael Schroeder 1 bài viết · arXiv cs.AI
Nguyên văn nguồn
Chi tiết nguồn

arXiv:2611.23445v1 Announce Type: new Abstract: Deep vision models operating in resource-constrained environments depend heavily on low-bit quantization, yet compressing weights below 4 bits frequently induces catastrophic accuracy collapse. While mixed-precision recovery strategies aim to rescue accuracy by selectively retaining high-precision parameters, the fundamental mechanics of where and why these models collapse remain poorly understood. In this study, we systematically analyze the anatomy of quantization collapse across standard Vision CNNs (including ResNet and EfficientNet backbones) evaluated on the full 50,000-image ImageNet-1k validation set. First, we map the exact progression of degradation, demonstrating that collapse is highly non-linear and concentrated in late-stage pointwise projections and depthwise layers. Second, we introduce a structured, multi-step recovery waterfall that evaluates selective integer precision (INT4/INT8) and selective floating-point scales. We show that keeping less than 5% of critical layer activations in 8-bit precision recovers up to 92% of the accuracy lost during aggressive sub-4-bit compression. Finally, we bridge the hardware reality gap by evaluating deployment performance on standard ARM and x86 CPU architectures. We show that while low-bit quantization reduces memory storage requirements, standard runtime software bit-unpacking introduces a 1.48x to 21.5x execution slowdown depending on batch size, highlighting a critical trade-off between model footprint and actual edge throughput. Our findings provide a practical blueprint for navigating the limits of sub-4-bit deployment without sacrificing hardware performance.

16

LusoClin: A Synthetic Clinical Note Dataset for Medical Information Retrieval in European Portuguese

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

Carla Teixeira Lopes, Daniel F\'elix 1 bài viết · arXiv cs.AI
Nguyên văn nguồn
Chi tiết nguồn

arXiv:2611.23454v1 Announce Type: new Abstract: Access to large-scale clinical text collections is crucial for advancing medical information retrieval research, including clinical note search, patient cohort identification, and domain-adapted retrieval models. However, real clinical notes are rarely available due to privacy regulations, which particularly limits progress for low-resource languages such as European Portuguese. We present LusoClin, a publicly released dataset of synthetic clinical notes in European Portuguese, created to support privacy-preserving research on clinical text retrieval. LusoClin was generated by pre-processing real clinical data, fine-tuning the open-source Llama 3.2 (3B) instruction-tuned model using Quantized Low-Rank Adaptation, and applying prompt-based clinical note generation. To facilitate semantic indexing and clinical search, the notes are automatically annotated with clinical entities using a BERT-based model. We evaluate LusoClin in terms of utility, fidelity, diversity, and privacy using automatic metrics and human evaluation. Results indicate that the dataset captures clinically relevant language patterns and can support downstream IR applications such as clinical document retrieval and domain-specific model adaptation, although annotators can often distinguish synthetic from real notes and some medical inconsistencies persist.

17

VeriMath: Human-in-the-Loop Generation and Verification of Curriculum-Aligned Mathematics Assessment Items

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

Quy P. Nguyen, Duong Q. Nguyen, Dinh P. T. Nguyen, Truong-Giang T. Le, Truong A. Bui, Vi H. Vo, Quang-Thinh Bui, My-Phuong Ngo, Trong N. Do, Thao P. Le, Phuc M. Nguyen, H. Nguyen-Xuan 1 bài viết · arXiv cs.AI
Nguyên văn nguồn
Chi tiết nguồn

arXiv:2611.23456v1 Announce Type: new Abstract: Automatic generation of mathematics assessment items is a growing area in educational artificial intelligence, yet classroom deployment remains challenging. Generated questions must satisfy multiple constraints: mathematical correctness, curriculum alignment, appropriate cognitive difficulty, and educator reviewability. While prior work has advanced text generation, reliable assessment authoring requires granular control over localized examination formats and expert educational judgment. To address this challenge, we present VeriMath, a generalized, human-in-the-loop framework for generating rigorous, curriculum-constrained mathematics assessment drafts. Using annotated reference items, the framework anchors generation to the requested examination section and cognitive reasoning level, then applies sequential automated verification and guided repair before submitting drafts for expert review. We evaluate VeriMath through a national curriculum case study using 4,555 mathematics items from the Vietnamese Grade 12 curriculum and 50 distinct generation requirements covering multiple-choice, true/false, and short-answer formats. Across two model backbones, the framework produces verifier-accepted drafts for 94% (47/50) of requirements per run. Blind expert evaluations confirm high mathematical accuracy and curriculum alignment, with strict teacher-readiness assessments accepting up to 56.8% of generated items. Analysis of rejected drafts reveals persistent domain-agnostic challenges involving formatting, statement validity, and solution-step completeness. These findings demonstrate that VeriMath can bridge generative AI and dependable educational applications by producing highly reviewable assessment drafts within tightly constrained national curriculum frameworks.

18

GUARD: Stabilizing Recursive Self-Improvement with Regret Guidance

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

Minghe Zhang, Xuetao Kang, Yifei Ming, Yanfei Chen, Han Yu, Yufan Zhuang, Chen-Yu Lee 1 bài viết · arXiv cs.AI
Nguyên văn nguồn
Chi tiết nguồn

arXiv:2611.23476v1 Announce Type: new Abstract: Autonomous AI agents pair a frozen base model with an editable harness of prompts, skills, tool rules, and memory. Recursive self-improvement (RSI) adapts this harness from experience without weight updates, yet self-editing without external graders often backfires: reflection and scalar scores conflate what an edit newly broke with what remains unsolved, causing local regressions, skill forgetting, and memory bloat. We introduce GUARD (Grader-free Unsupervised Environment Design [UED] with Adaptive Rule Distillation), a closed-loop framework for reference-free continual harness evolution. Our key insight is to decompose each task into pre-execution self-checks and guide harness updates via directional regret. Each round grades trajectories against these checks, pinning mastered rules while prioritizing newly broken behaviors, and selects among parallel candidate edits by critic-free group-relative fitness. A Soft-HURT gate then promotes an edit only when gains outweigh regressions, scoping specialized fixes to prevent over-triggering and guaranteeing non-regression on its gated buffer. At test time, one frozen harness runs in a single pass. Across benchmarks on memory, skill evolution, continual task streams, and domain reasoning, GUARD consistently improves performance without catastrophic forgetting or memory pollution while substantially cutting deployment token usage.

19

Diagnostic Accuracy and Navigation Behavior of Vision-Language Model Agents Reading Emergency CT and MRI Examinations

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

Jonathan Lichtle, Aymen Meddeb, Antonin Birot, Ibrahima Niang, Lisa Gastaud, Riyad Hanafi, Sofiane Dujardin, Corentin Selomme, Guillaume Cachard, Aghiles Hamroun, Gr\'egory Kuchcinski, Su Hwan Kim, Bastien Le Guellec 1 bài viết · arXiv cs.AI
Nguyên văn nguồn
Chi tiết nguồn

arXiv:2611.23480v1 Announce Type: new Abstract: Purpose. To evaluate the diagnostic accuracy and image navigation behavior of vision-language model (VLM) agents under varying exploration strategies. Materials and Methods. In this retrospective study, six VLMs read 100 emergency CT and MRI examinations published in a public archive (March 2025-August 2026) under four conditions (free navigation, navigation from a key slice, and all slices or key slices in a single request), twice each (4800 runs). Nine radiologists read 30 of those cases. A large language model judge validated against two radiologists graded the answers. Conditions were compared with generalized estimating equations clustered by case. Results. Pooled accuracy was lowest under free navigation (32.6%; 391/1200), followed by navigation from a key slice (37.9%; 455/1200; P = .003), and highest with all slices (42.2%; 506/1200) or key slices (42.5%; 510/1200) in one request (both P < .001). On the 30 cases read by radiologists, freely navigating models were correct in 30.0% of runs (108/360) versus 77.0% for radiologists (208/270; P < .001). Models formed a first hypothesis after a median of 10.8% of the slices and kept it in 63.1% of runs (755/1196); final answers were correct in 12.4% of runs after a wrong first hypothesis (110/885) versus 90.4% after a right one (281/311; P < .001). Median stated confidence in the final answers was 90%, whereas 38.9% of them were correct (1861/4778). Conclusion. Across all exploration strategies, VLM agents remained far less accurate than radiologists. They adopted an early hypothesis and usually kept it, seldom correcting a wrong one.

20

SpecLook: Speculating Where to Look for Fast and Reliable Agentic MLLMs

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

Xi Ding, Jiawei Zhang 1 bài viết · arXiv cs.AI
Nguyên văn nguồn
Chi tiết nguồn

arXiv:2611.23483v1 Announce Type: new Abstract: Agentic multimodal large language models (MLLMs) that think with images interleave reasoning with zoom-in tool calls. However, this sequential loop is slow, and its answers carry no reliability score. Prior speculation of tokens, reasoning steps, or answers keeps the loop, and answer speculation also accepts confident errors. We find that the loop mostly adds one zoom-in step, with which a small model is ahead of the agent on most splits. Our key insight is to speculate the agent's next observation, which, unlike a drafted answer, can be verified, corrected, and used to test the answer. We propose SpecLook, a training-free speculate-and-verify framework with three levels. A small model drafts a glimpse and re-answers from it, and the question ends if the answer is unchanged and confident. Otherwise, the agent's large model verifies and corrects the glimpse without tools, and their answers are fused. Only questions that still lack evidence reach the agent, in one forward pass that SpecLook-Fast skips, so no question runs the loop. The trace scores every answer's reliability without labels. Extensive experiments on V*, HR-Bench, and POPE show that both are more accurate than every baseline on every split. SpecLook reaches 87.2% and 86.2% mean accuracy with 7.7x and 4.7x speedups over the DeepEyes-7B and Thyme-RL agents, and SpecLook-Fast reaches 9.9x and 6.3x.

1–20 / 171
Trang 1 / 9