All Updates

Page 1129 of 1528

March 19, 2026

๐Ÿ“„
ArXiv AIโ€ข110d ago

RideJudge: AI Framework for Ride Disputes

RideJudge introduces a progressive framework aligning visual and logical reasoning for ride-hailing dispute adjudication, addressing limitations in multimodal LLMs. Key innovations include SynTraj for trajectory synthesis, Adaptive Context Optimization, and Ordinal-Sensitive RL. The 8B model achieves 88.41% accuracy, outperforming 32B baselines.

#multimodal-llm#adjudication#ride-hailing
๐Ÿ“„
ArXiv AIโ€ข110d ago

PIER RL Cuts Shipping Fuel Waste 9-Fold

PIER is a physics-informed offline RL framework that learns fuel-efficient, safety-aware maritime routing from historical AIS data and ocean reanalysis, without needing online simulators or forecasts. It reduces mean CO2 emissions by 10% versus great-circle routing and slashes catastrophic fuel waste from 4.8% to 0.5% of voyages on 2023 Gulf of Mexico routes. The method shows 3.5x lower fuel variance and transfers to other domains like wildfire evacuation.

#offline-rl#physics-informed#maritime-routing
๐Ÿ“„
ArXiv AIโ€ข110d ago

LLMs Struggle in Clue Reasoning Test

Researchers built a text-based multi-agent Clue game to evaluate LLMs' multi-step deductive reasoning with GPT-4o-mini and Gemini-2.5-Flash agents. Across 18 simulated games, agents secured only four correct wins, struggling with consistent reasoning. Fine-tuning on logic puzzles did not reliably enhance performance and sometimes increased verbosity without precision gains.

#deductive-reasoning#llm-benchmark#game-eval
๐Ÿ“„
ArXiv AIโ€ข110d ago

Kumiho: Graph-Native Memory for AI Agents

Kumiho introduces a graph-native cognitive memory architecture for AI agents, grounded in formal AGM belief revision semantics. It unifies cognitive memory and versioned assets using primitives like immutable revisions and URI addressing. Achieves SOTA results on LoCoMo (0.565 F1) and LoCoMo-Plus (93.3% accuracy), outperforming Gemini.

#ai-agents#belief-revision#graph-database
๐Ÿ“„
ArXiv AIโ€ข110d ago

InfoDensity Rewards Dense Reasoning Traces

Large Language Models generate verbose reasoning traces that waste compute. InfoDensity proposes an RL reward framework using AUC-based and monotonicity signals, weighted by length, to favor concise, high-quality steps. It matches SOTA accuracy on math benchmarks while cutting token usage.

#reasoning-efficiency#rl-reward#entropy-tracking
๐Ÿ“„
ArXiv AIโ€ข110d ago

Geometry-Switching Fixes Agent Cascade Failures

New method introduces cascade-aware routing for multi-agent AI systems using spatio-temporal sidecars and adaptive geometry switching between Euclidean and hyperbolic models. It boosts Genesis 3 benchmark win rates from 50.4% to 87.2%, especially in tree-like graphs prone to exponential failures. The lightweight 133-parameter MLP selector uses topology stats for geometry decisions.

#multi-agent#graph-geometry#failure-cascades
๐Ÿ“„
ArXiv AIโ€ข110d ago

GenAI Workflow for Participatory Planning Models

Researchers propose a templated LLM workflow to accelerate problem conceptualization in socio-environmental planning under deep uncertainty. It uses models like ChatGPT to extract components from stakeholder descriptions, unify perspectives, and generate Python implementations iteratively. Demonstrated successfully on lake and electricity market problems.

#socio-environmental#deep-uncertainty#llm-workflow
๐Ÿ“„
ArXiv AIโ€ข110d ago

Draft-and-Prune Boosts Auto-Formalization Reliability

Draft-and-Prune (D&P) is an inference-time framework that improves auto-formalization by drafting diverse natural-language plans, pruning incorrect formalizations, and aggregating via majority voting. It achieves 78.43% accuracy on AR-LSAT with GPT-4 and 78% with GPT-4o, outperforming baselines like MAD-LOGIC and CLOVER. D&P reaches near-ceiling performance, including 100% on PrOntoQA and LogicalDeduction.

#auto-formalization#logical-reasoning#inference-time
๐Ÿ“„
ArXiv AIโ€ข110d ago

CRAFT: Hidden-State RL for Jailbreak Defense

CRAFT is a red-teaming framework that aligns reasoning models using hidden representations to boost robustness against jailbreaks. It combines contrastive learning with RL to separate safe/unsafe trajectories in latent space. Achieves 79% reasoning safety and 87.7% response safety gains on Qwen3-4B-Thinking and R1-Distill-Llama-8B, outperforming IPO and SafeKey.

#alignment#jailbreak#latent-space
๐Ÿ“„
ArXiv AIโ€ข110d ago

AI Scientist via Synthetic Task Scaling

Researchers developed a synthetic environment pipeline for training machine learning agents using the SWE-agent framework. The pipeline generates verified ML challenges grounded in real Huggingface datasets with self-debugging. Student models trained on GPT-5 trajectories improved MLGym benchmark performance by 9% for Qwen3-4B and 12% for Qwen3-8B.

#ai-agents#synthetic-data
๐Ÿ—พ
ITmedia AI+ (ๆ—ฅๆœฌ)โ€ข110d ago

Anthropic's 80K Claude User Survey

Anthropic surveyed ~80,000 Claude users across languages, revealing strong demand for expert-level AI capabilities with 80%+ reporting practical value. Concerns include reliability issues and loss of autonomy, especially cognitive decline fears in East Asia like Japan.

#user-survey#ai-trust#regional-differences
๐Ÿ‡ฆ๐Ÿ‡บ
iTNews Australiaโ€ข110d ago

Metcash Adds AI Search to B2B Platform

Metcash has introduced AI-powered search to its B2B marketplace. The SAP-based platform is now augmented with Coveo's AI technology. This upgrade aims to enhance search capabilities for wholesale users.

#ai-search#b2b#enterprise
๐Ÿ’ฐ
้’›ๅช’ไฝ“โ€ข110d ago

Aliyun Compute Shortage Sparks Token Surge

Alibaba Cloud faces acute computing power shortages amid the AI agent boom. Token prices are surging dramatically. The article analyzes Aliyun's valuation in this new era.

#compute-shortage#token-surge#cloud-valuation
๐Ÿฏ
่™Žๅ—…โ€ข110d ago

Frore Unicorn: $112B AI Chip Cooling Funding

Frore Systems raised $143M Series D at $1.64B valuation for liquid cooling tech serving Nvidia, Qualcomm, AMD chips. Pivoted to liquid cooling post-Nvidia CEO advice amid AI data center heat surge. Neutral positioning benefits from all AI chipmakers' growth.

#liquid-cooling#ai-hardware#unicorn-funding
๐Ÿ’ฐ
้’›ๅช’ไฝ“โ€ข110d ago

CarbonBase and Wukong Burn Tokens for New AI

Carbon-based tech and Alibaba's Wukong collaborate on intensive token-burning compute tasks. This partnership yields a groundbreaking new AI species. Teases larger developments post-super individuals.

#ai-collaboration#token-burn#new-ai-species
๐Ÿ“Š
Bloomberg Technologyโ€ข110d ago

Xiaomi AI Models Spark Shares Surge, SU7 Facelift Nears

Xiaomi Corp. shares rallied Thursday after releasing its latest artificial intelligence models. The company is also preparing to launch a refreshed version of its SU7 electric vehicle.

#stock-rally#ai-release#ev-update
๐Ÿงง
Qwen (GitHub Releases: qwen-code)โ€ข110d ago

Qwen-Code v0.13.0 Preview with Agent Arena

Qwen-Code releases v0.13.0-preview.0 featuring system prompt customization in SDK/CLI, hooks extension mechanism, and agent collaboration arena for multi-model competition. Performance boosts via concurrent task tool execution and truncation support for MCP outputs. VSCode enhancements include fuzzy search, token usage display, and Tab-fill completions.

#sdk#cli#agent
๐Ÿ’ฐ
้’›ๅช’ไฝ“โ€ข110d ago

China's First Robot-Majority City in Yizhuang?

Yizhuang is set to become China's first location where robots outnumber residents. The article recommends that every tech entrepreneur visit this emerging robotics hotspot.

#robotics#embodied-ai#china-hub
๐Ÿฏ
่™Žๅ—…โ€ข110d ago

Why AI Rationality Fails Leaders

Mearsheimer's prescient warnings on wars ignored due to arrogance, fear, and power's emotional logic. Rational analysts like him or AI provide clear insights but lose to emotion-driven politics. Humans' ancient emotional systems override rationality in high-stakes decisions.

#decision-paradox#ai-limitations#realpolitik
๐Ÿ”ฅ
36ๆฐชโ€ข110d ago

Zhongqing & Duolun Launch Qing'an Robotics

ๆฑŸ่˜‡ๆ“Žๅฎ‰ๆฉŸๅ™จไบบๆœ‰้™ๅ…ฌๅธ่ฟ‘ๆ—ฅๆˆ็ซ‹๏ผŒ่จปๅ†Š่ณ‡ๆœฌ1ๅ„„ๅ…ƒ๏ผŒ็ถ“็‡Ÿ็ฏ„ๅœๆถต่“‹ๆ™บ่ƒฝๆฉŸๅ™จไบบ็ ”็™ผ้Šทๅ”ฎใ€AIๆ‡‰็”จ่ปŸ้ซ”้–‹็™ผ็ญ‰ใ€‚่‚กๆฑ็‚บๅคšๅ€ซ็ง‘ๆŠ€่ˆ‡ๆทฑๅœณ็œพๆ“ŽๆฉŸๅ™จไบบ็ง‘ๆŠ€ใ€‚

#robotics#new-company#ai-platform
Page 1129 of 1528