AI News Archive: August 20, 2026 — Part 16
Sourced from 500+ daily AI sources, scored by relevance.
- Structured Affinity for Unsupervised Visual Class-Incremental Memory in Deep Artificial Immune Networks
Artificial immune networks (AINs) are naturally memory-forming systems, but conventional visual AINs often rely on flattened vector affinity that ignores spatial structure. This paper studies whether structured, gradient-free immune affinity can make Deep AINs viable as replay-free visual class-incr...
- Towards Professional Tennis Styles for Humanoid Robots with Adaptive Motion Planning and Tracking
Humanoid robots have recently demonstrated promising capabilities in real-world ball sports. However, achieving professional motion styles while maintaining strong task performance remains challenging. In this work, we propose AdaPT, an Adaptive Motion Planning and Tracking framework that learns pro...
- Evidence-Gated Task and Motion Planning with Vision-Language Models
Robots executing long-horizon manipulation tasks from natural-language instructions must reason about both semantic task structure and geometric feasibility. However, under partial observability, the availability of goal-relevant objects may be uncertain. In such cases, approaches that combine Visio...
- Let's Scale Step by Step: Compute-Efficient Hyperparameter Transfer for Large-Scale Mixture-of-Experts
Mixture-of-Experts (MoE) architectures significantly expand model capacity without a proportional increase in computational cost. However, optimizing their hyperparameters---particularly the learning rate---at extreme scales of both model size and token budget via sweeping remains computationally pr...
- EchoCoT: Extracting Hidden Chain-of-Thought from Large Reasoning Models
Hidden chain-of-thought (CoT) traces, especially those from frontier proprietary large reasoning models (LRMs), are valuable model assets. Yet whether these hidden CoTs can be directly extracted from black-box models remains largely unexplored. In this work, we systematically study whether hidden Co...
- Manifold Drift in Flow Preference Optimization: A Root Cause of Reward Hacking
Preference optimization is a standard alignment method for generative models, yet extending it to continuous-time dynamics remains non-trivial. In flow matching, reward-driven updates modify transport trajectories without an inherent constraint to the pretrained data manifold and can move terminal s...
- ExPhy: A Benchmark for Explicit Physical Property Learning in Multi-Object Trajectory Forecasting
Understanding object dynamics requires not only predicting future trajectories but also examining whether a model captures the physical properties that govern motion. However, existing benchmarks rarely expose object-level physical properties as explicit evaluation targets alongside trajectory forec...
- Rethinking Patch Based Multivariate Time Series Forecasting with Semantic Structured Partitioning
Multivariate time series forecasting (MTSF) is a fundamental task in many real world applications. Existing patch based forecasting methods generally fall into three categories: fixed partitioning, multi-scale partitioning, and extendable partitioning. Fixed partitioning often breaks meaningful temp...
- A Strong Linear Baseline for Whole-Heart Cardiac Shape Completion on CT, with an Open Eleven-Structure Statistical Shape Model
Public cardiac cohorts annotate different subsets of the heart, so shapes from separate sources cannot be pooled without shared correspondence. Among released cardiac shape resources, none we identified carries the atrial appendage, pulmonary veins, and caval stumps as separate blocks in one mesh. C...
- Bringing analytic rigor to agentic AI for science: The Brain Researcher platform for neuroimaging data analysis
AI agents can execute scientific analyses, but an analytic output becomes a defensible claim only after alternatives are weighed and the claim is limited to what the evidence supports. Agents may reproduce failures including selective analysis, premature declarations of success and optimization of i...
- ConceptGuard: Benchmarking Context-Sensitive Unlearning in Large Language Models
Large Language Models (LLMs) increasingly require selective removal of harmful or sensitive knowledge, called unlearning, yet existing methods and benchmarks fail to evaluate this capability completely. Current approaches rely on disjoint forget and retain sets composed of independent facts, and mea...
- FormalTCS: Benchmarking End-to-End Frontier Formal Theoretical Computer Science Research of Large Language Models
Large language models (LLMs) have shown growing potential for automated theoretical computer science (TCS) research, yet existing benchmarks remain far from realistic research settings. We introduce \ourbenchmark, an expert-validated benchmark for evaluating LLMs on frontier, end-to-end TCS research...
- Multi-Agent Orchestration with the Common-Sense Reasoning Capabilities of LLMs for Autonomous Driving
Autonomous vehicles require robust perception and decision-making capabilities to operate in diverse and unseen scenarios. While reinforcement learning and rule-based methods can provide effective control and safety mechanisms, their performance may degrade in situations requiring contextual reasoni...
- When Text and Numbers Disagree: Evidence Arbitration in Large Language Models
Large language models (LLMs) are increasingly used in settings where textual summaries, numerical observations, and external tool outputs may provide conflicting evidence. We study how LLMs arbitrate between such sources when they support opposing decisions. To do so, we introduce a controlled synth...
- Shape
The agentic IDE for designers and programmers
- Reward-Guided Autoregressive Graph Generation for Efficient Multi-Agent Communication Topology Design
LLM-based Multi-Agent Systems (MAS) achieve strong performance on complex reasoning tasks by coordinating multiple agents, but at the cost of substantial token consumption. Recent work on automatic topology design, ARG-Designer, has reframed this problem as autoregressive graph generation. However, ...
- Auditing Cross-Lingual Fairness in Language Model Watermarking
Watermarking schemes for large language model output are evaluated almost exclusively on English text using each scheme's detection threshold and a narrow set of quality measurements. Multilingual deployment exposes evaluation-design choices that are inconsequential on English but determine conclusi...
- Robust Incomplete Multimodal Sentiment Analysis via Iterative Proxy Correction
Multimodal sentiment analysis aims to infer affective states by integrating language, visual, and acoustic cues. However, real-world multimodal inputs are often incomplete or corrupted, which can weaken cross-modal complementarity and introduce misleading information into downstream fusion. Existing...
- Dynamic Gated Cross-Modal Fusion with Sarcastic-aware Contrastive Regularization for Multimodal Sarcasm Detection
Multimodal sarcasm detection aims to identify sarcastic intent from multimodal content, where inconsistencies between literal meaning and contextual cues often signal irony. This task has attracted increasing research attention. However, accurate detection remains challenging due to instance-depende...
- Learning how to Forget: Fine-tuning for Long-Context Sparse Attention
A lot of prior work addressed key-value (KV) cache selection and compression by sparse attention to enable long-context inference for transformer language models without excessive hardware budgets. We provide a new method for fine-tuning models with sparse attention. It works for any KV cache policy...
- Interrupting the Loop: Periodic Subject Changes Raise Judged Surprise and Connection in Base Language Models
Where does the novelty a base language model produces with no task come from, and what can an LLM judge of a long stream actually see? We dismantle a cognitively inspired generation loop over 24 conditions on three base models. Most of its effect lives in one operation: a new subject injected every ...
- EnvHarness: Awakening Static Worlds for Agent Learning
LLM agents learn by interacting with environments, yet these environments are hand-built and static: blind to an agent's weaknesses, and quickly left behind as it improves. While recent environment generation methods attempt to address this, they require domain-specific pipelines, rely on expensive ...
- PolicyGuide: From Guarding One Action to Guiding the Whole Workflow for Policy-Compliant LLM Agents
Customer-service LLM agents must follow organizational policy when acting on a user's behalf. Compliance failures arise from either forbidden actions, such as granting an ineligible change, or omitted procedural requirements, such as identification or confirmation. Runtime safeguards can intervene o...
- MileGPO: Milestone Inference with Local Evidence for Graph-Based Policy Optimization of Long-Horizon LLM Agents
Credit assignment is challenging in long-horizon agentic reinforcement learning, where supervision often comes only from final rewards. Existing methods refine trajectory-level signals into step-level credits through step grouping or graph-based advantage estimation, but can overlook meaningful inte...
- Stopping and Routing LLM Judge Panels
LLM evaluation pipelines often have many candidate judges: general LLM-as-a-judge prompts, reward models, safety classifiers, confidence variants, and task-specific verifiers. The deployment question is not only which judge is best, but which judges should be called, on which examples, and when pane...
- LoRA-GA$^2$: Low Rank Adaptation with Multi-step Gradient Adaptive Alignment
Low-Rank Adaptation (LoRA) is a prominent fine-tuning method for large models, achieving competitive performance with reduced memory overhead. However, a persistent performance gap remains between LoRA and full fine-tuning. Recent studies have sought to narrow this gap by employing one-step gradient...
- Credit Without Ground Truth: Auditing Step-Level Credit Assignment in LLM Agents Against Executed Replay
Audited against causal ground truth from executed replay in a single-agent tool environment (ALFWorld), none of the step-level credit signals used to train LLM agents -- LLM-judge scores, outcome-conditioned logprob ratios, or the policy's own confidence -- identifies which steps causally matter bet...
- FlashPrefill V2: Block-Sparse Prefill Attention for Long-Context LLM Serving
Long-context modeling is a pivotal capability for Large Language Models, yet the quadratic complexity of attention remains a critical bottleneck, particularly during the compute-intensive prefilling phase. Our previous work, FlashPrefill, mitigates this cost through instantaneous pattern discovery a...
- PersonalBench: Measuring the Authorship Gap in LLM Personalization
Personalized text generation aims to make LLMs write in a specific individual's style, yet existing benchmarks measure task accuracy or preference alignment rather than whether the model's output actually resembles the target author's writing. We introduce PersonalBench, a benchmark that evaluates i...
- Projector Is All You Train
The typical training process of a multimodal large language model (MLLM) involves adapting both the language model backbone and the projector between the backbone and a modality-specific encoder. We ask whether fine-tuning the backbone of an MLLM is necessary to adapt it to a new modality. Through e...
- The Asymmetric Harms of LLM Compression
Large language models (LLMs) compression reduces deployment costs, but standard aggregate metrics like perplexity and accuracy often mask underlying behavioral shifts. In this work, we systematically evaluate 3 LLMs across 11 compression methods to investigate the effects of compression on knowledge...
- ReCache: Efficient KV Cache Reuse and Compression for Tool-Augmented LLM Agents
Agentic language models repeatedly encode tool and skill schemas that recur across requests in different combinations and orders, preventing standard prefix caching from reusing their key--value (KV) states. We introduce \textbf{ReCache}, a framework for independently caching resource representation...
- Can Agent Memory Systems Track Evolving State?
As LLM-based agents are deployed for longer and higher-stakes tasks, their memory systems continue to have crucial gaps. While existing memory benchmarks focus largely on recall-shaped tasks, we argue an effective memory system must track the evolving state of the world; as facts, constraints, and d...
- Mitigating Identity Essentialism in LLM Agents with Longitudinal Life Trajectories
Large language models (LLMs) offer a scalable approach to social simulation, but their credibility depends on how agents are constructed. Existing methods can partially reproduce population-level patterns, yet often fail to capture human-like diversity. Our analysis shows that static-profile agents ...
- Forking Fast: Efficiently Estimating Uncertainty Dynamics in Text Generation
LLM reasoning is stochastic, and so understanding a model requires grappling with the distribution of reasoning chains that it might produce for a given question, i.e., its uncertainty. Resampling-based analyses characterize this distribution, revealing which steps of a rollout determine how the mod...
- PEA-DPO: Perception-Enhanced Alignment Direct Preference Optimization for MLLMs Alignment
Direct Preference Optimization (DPO) has emerged as an effective approach for aligning large language models (LLMs) with human preferences. However, its adaptation to multimodal settings remains unexplored. Through representational analysis, we identify a key limitation in multimodal preference opti...
- Remember, Verify, or Ask? Cross-Family Evaluation of Memory Commitment in LLM Agents
Persistent memory can personalize an LLM agent, but an incorrect durable update can silently distort future behavior. We study the memory-clarification boundary: whether interaction-derived information should be persisted, used only in the current context, re-verified, or clarified with the user. MC...
- OenoBench: A Wine-Domain Benchmark for Knowledge-Grounded Evaluation of Large Language Models
We introduce OenoBench, a wine-domain knowledge benchmark of 3,266 multiple-choice questions across six pillars (regions, grape varieties, viticulture, winemaking, producers, business) and four difficulty tiers. The corpus is built from 38,104 atomic, source-anchored facts extracted by 35 provenance...
- HealMed: Multilingual Evaluation of Large Language Models in Medicine
We present HealMed, an expert-reviewed benchmark for multilingual evaluation of large language models in medicine. HealMed contains 1,000 examples in each of nine languages, drawn from nine datasets and covering three task formats: MCQA, NLI and open-ended QA. The benchmark was developed over two ye...
- Natural Language Code Retrieval for 1C:Enterprise: An Open Benchmark and Efficient Bi-Encoder
Natural language code retrieval is a rapidly evolving task in computer science. However, the 1C:Enterprise ecosystem combines Russian syntax with highly domain-specific terminology, for which open datasets and specialized models have been virtually non-existent. We present a comprehensive pipeline f...
- A knowledge-guided agentic framework for mitigating patient-context ambiguity in health queries
Patients often submit short, underspecified queries to healthcare chatbots that lack the patient-specific information needed to determine an appropriate response. Although these queries may be linguistically clear, they can support multiple plausible answers depending on undisclosed factors such as ...
- Towards Clinically Faithful Medical Image Captioning via Enhanced Vision-Language Alignment
Medical image captioning is a technique that accelerates early-stage diagnostic workflows and enhances the interpretability of medical diagnostic AI systems. However, unlike general image captioning, clinically reliable captioning remains challenging due to grayscale-based modalities, subtle anatomi...
- SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science?
Software increasingly functions as part of the scientific instrument itself, making failures in scientific code capable of compromising not only program behavior but also the evidence underlying scientific conclusions. Yet existing evaluations of coding agents largely emphasize aggregate task succes...
- Truncate Bad, Upweight Good: BoN-Style Distillation via Rank-Based Classification
Inference-time selection methods, such as Best-of-N, improve generation by sampling a pool of candidates and selecting the top-ranked completion according to a reward model. Distillation seeks to amortize this procedure into a single policy by replacing raw rewards with in-pool ranks and learning a ...
- One Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business Workflows
Recent agent benchmarks increasingly ground evaluation in executable environments, from code repair to web navigation, app APIs, and function calling. Yet completing consequential work beyond code requires more than producing a plausible response or valid tool call: agents must gather missing inform...
- TempJail: Temporal Jailbreak Attack against Large Vision-Language Models via Subtitle Scheduling
Large vision-language models (LVLMs) have achieved remarkable progress in video understanding and reasoning. Despite extensive studies on text- and image-based jailbreaks, video jailbreaks against LVLMs remain largely unexplored. Existing video jailbreak methods mainly manipulate textual content emb...
- bitdrift.ai
The world’s first agentic mobile observability platform
- Reliable Financial Named Entity Recognition under Domain Shift
Financial AI systems often train information extractors on one textual register and deploy them across filings, news, and user-generated content, while standard F1 scores do not indicate which predictions remain safe to automate when the input distribution changes. We study confidence estimation and...
- Inter-X++: A Comprehensive Benchmark for Multimodal Human-Human Interaction Analysis
The capability to perceive and synthesize human-human interactions is fundamental to developing intelligent digital human systems. However, existing datasets and modeling approaches are fundamentally constrained by low-fidelity kinematics, the omission of dexterous hand gestures and a severe lack of...
- GoPoint
From Plain English Prompt to Garmin GPX in Seconds.