Sources

We Query, Therefore We Compute: On Oracle Computation beyond the Machine, with an Application to Agents huggingface.co

Agentic systems use large language models (LLMs) to carry out concrete tasks. Prior work often borrows abstractions such as scheduling, caching or isolation piecemeal from operating systems, so the mechanisms it builds share little common ground, and the shared view of the two forms of agentic system, Workflows and Agents, is limited. We construct an abstract machine that provides both. We treat the LLM as an Oracle and extend a two-stack pushdown automaton with one instruction, which hands th

AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model huggingface.co

Web agents complete user requests by reading and acting on pages that third parties write, so an instruction planted on a page can redirect the agent away from the user’s goal. The agent cannot simply ignore the page, because the page also holds the values and controls the task requires. Current defenses fine-tune the agent on injections fixed before training, and attackers that adapt to the trained model bypass them. Adversarial training lets the attacker adapt but keeps the tasks fixed, so a t

RLHND: Video Foundation Models as Physically Grounded Hand Trackers for Robot Learning huggingface.co

Recently, approaches that leverage human video datasets for robot policy training have become increasingly prevalent. However, most existing hand trackers regress pose from cropped frames with limited priors on hand motion and object interaction, resulting in inaccurate and physically inconsistent estimates. Moreover, the lack of physical cues, e.g., contact and force, limits the use of human videos for robot policy training. To this end, we propose RLHND, a video foundation model-based hand tra

NeMo-DCR: Bit-Exact Delta-Compressed Refit for Scalable Agentic RL at Trillion-Parameter Scale huggingface.co

NeMo-DCR delivers bit-exact delta-compressed weight refits for agentic reinforcement learning at trillion-parameter scale. The team measured that only about 1% of BF16 weights change per training step, and full cross-region checkpoint transfers on AWS took 87.5 minutes — a bottleneck DCR targets by shipping just the deltas.

UNREAL: Unifying Retrieval and Long-Context with a Single Model huggingface.co

UNREAL collapses retrieval and long-context inference into a single model-native mechanism, encoding chunks and deriving queries directly from the forward pass. The approach spans evidence selection from a single prompt up to full-corpus retrieval, removing the separate embedding stack that RAG pipelines normally bolt on.

GUI-HARVEST: Self-Improving GUI Agents through Evidence-Driven Harness Evolution huggingface.co

GUI-HARVEST automatically rewrites the executable harness around GUI agents — the layer that assembles observations, runs actions, and handles recovery. It diagnoses recurring failure patterns across tasks and translates them into reusable rules, tackling the visual-intent reconciliation problem that non-GUI harness optimizers skip.

Harness Engineering for Software Engineering via Modular Executable Dev-Primitives huggingface.co

The paper proposes harness engineering built on modular executable dev-primitives for software engineering agents. The design targets the brittleness of terminal-driven LLMs on long-horizon workflows, where repeatedly reconstructing state across source, configs, tests, and runtime behavior triggers context explosion and semantic drift in large repositories.

TimeBraid: Unifying Time Series and Language for Understanding and Forecasting huggingface.co

TimeBraid interleaves global residual attention layers between pretrained language models and pretrained time-series foundation models, producing a shared representation that handles both modalities. The hybrid inherits instruction following and reasoning from the LLM side and zero-shot forecasting from the time-series side, generating in either modality.

Making LLMs Say What They Think: Measuring and Improving CoT-Interpretability Alignment huggingface.co

Chain-of-Thought Interpretability Alignment (CIA) measures agreement between an LLM’s written reasoning and what it actually computes internally. Prior work has shown CoT traces can be edited without changing final answers, suggesting the explanations are often post-hoc; CIA quantifies that gap and offers a training signal to close it.

World Models’ Last Exam in Physics huggingface.co

World Models’ Last Exam in Physics evaluates video world models with 40 controlled, measurement-based tasks rather than model judgments or reference videos. The benchmark extends beyond mechanics to probe physical consistency broadly, targeting the gap where generated video looks convincing but violates physics needed for embodied planning.

TRIAGE: Direction-Aware Mismatch Stabilization of Native NVFP4 Reinforcement Learning huggingface.co

Low-precision execution can substantially accelerate reinforcement learning (RL) for large language models, but discrepancies between learner and sampler execution can destabilize policy optimization. In this paper, we characterize the interaction between mismatch and the policy-gradient direction, distinguishing locally amplifying from contracting update contributions that mismatch magnitude alone cannot identify. In native NVFP4 runs, we observe an early imbalance between the two amplifying re

TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models huggingface.co

Reinforcement learning (RL) for post-training large language models (LLMs) incurs substantial computation and memory overhead during rollout generation, which motivates low-precision rollout for efficient RL training. However, existing FP4 RL methods suffer from a key limitation: they primarily optimize quantization accuracy on the training and rollout paths independently rather than directly reducing the discrepancy between the two quantized execution paths. In this work, we propose TRACE (Trai

Understanding and Enhancing Backdoor Persistency in LLM Agent Post-Training huggingface.co

Developers can build LLM agents by adapting third-party models through benign post-training. We study a supply-chain threat in which an attacker supplies a model with a backdoor: hidden behavior that produces malicious outputs when a particular input pattern appears. Focusing on software-engineering agents, we ask whether such backdoors survive the developer’s supervised fine-tuning (SFT) and subsequent task-level reinforcement learning (RL). We observe that benign SFT substantially reduces atta

Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability huggingface.co

On-Policy Distillation (OPD) trains a student on its own generations using teacher feedback. With different tokenizers, comparing teacher and student predictions requires alignment at both sequence and vocabulary levels. In this paper, we examine whether expanding this alignment coverage improves learning. Across three heterogeneous teacher—student pairs on mathematical reasoning and code generation, strict 1:1 groups already cover most student-generated tokens despite substantial vocabulary mi

From Evidence to Action: How Tool-Using Agents Fail huggingface.co

Tool-using agents make consequential changes to external state, yet correct outcomes do not guarantee that their actions were supported by evidence established beforehand. We study where this evidence-to-action chain breaks as agents move from deciding whether to act to executing single actions and dependent workflows. Across ten model-harness configurations, strong static action assessment can coexist with much weaker interactive execution. Failures often begin before execution: agents stop wit

DiVeR: Decision-Critical Verifier Learning for VLA Test-Time Scaling huggingface.co

Scaling robot data and model capacity has improved Vision-Language-Action (VLA) policies, but further progress is constrained by the high cost of robotic data. Verifier-guided test-time scaling offers an efficient alternative by sampling multiple action candidates and selecting the one most likely to lead to task success at inference time. Existing classification-based verifiers learn from trajectory-level outcomes but treat all visited states equally, even though their value for candidate discr

Taming VLAs under Robot Execution Errors: Self-Compensation and Stress Testing huggingface.co

Vision-language-action (VLA) policies often fail when a robot’s executed motion deviates from their commanded action. Such execution errors arise from the robot’s mechanics and operating conditions, such as wear and payload changes. We propose self-compensating VLA, a deployment-time adaptation method that enables a VLA policy to pre-compensate for the robot’s execution errors when generating commands. Without task rewards or labels, it updates the policy online using the residual between the ac

EmbodiedSmith: Scaling Embodied Data through Recursive Self-Improvement Flywheel in Simulation huggingface.co

Scaling robotic foundation models requires diverse training data and reliable evaluation environments. Simulation offers a scalable solution, yet existing generation pipelines remain constrained by predefined assets and skills, a disconnect between scene generation and task generation, and limited support for complex embodiments and physics. We introduce EmbodiedSmith, a framework for scalable embodied data generation through recursive self-improvement (RSI). EmbodiedSmith unifies asset, scene,

VeriFine: Scaling Verification for Self-Improvement in Embodied Reasoning huggingface.co

Self-improving policies continually expose new failure patterns, changing what their judges must be able to verify. However, current fixed judges constrain both optimization feedback and the discovery of useful training examples, limiting further self-improvement. This challenge is even more acute in embodied reasoning, where reliable evaluation must account for spatial grounding, causal reasoning, and safety-aware decision-making. We introduce VeriFine, an agent harness framework that scales ve

Learning to Read the Contextual Tokens in Diffusion Transformers huggingface.co

Multimodal Diffusion Transformers (MM-DiTs) jointly process visual and textual representations throughout generation. These models repeatedly update the text tokens through multimodal attention, forming dynamic contextual tokens whose function is not well understood. In this work, we introduce a framework for reading this contextual space through natural-language interrogation. We train a lightweight bottleneck network that maps intermediate contextual tokens into the input space of a frozen Lar

Attacca: Goal-Directed Control under State Continuity for Long-Horizon Embodied Agents huggingface.co

A central capability of embodied agents is to accomplish complex objectives through sequences of interdependent tasks. Yet existing visual goal-conditioned policies underlying these agents are typically evaluated on isolated interactions where the target is already visible, and thus do not capture the conditions that arise during continuous long-horizon task execution. In such settings, each task begins from the state left by the previous one: the agent may end at a different position and orient

Rationale-Guided Policy Optimization: Learning to Reason with Adaptive Rationale Scaffolding huggingface.co

On-policy reinforcement learning has become a central paradigm for improving the reasoning abilities of large language models. However, its effectiveness is often limited by reward sparsity: when a model fails to discover correct trajectories for difficult problems, the optimization process receives little useful signal and may stagnate. Existing approaches mitigate this issue by incorporating off-policy demonstrations, expert traces, or model-generated solutions, but they typically require the

DuoMatching: Joint-Marginal Distribution Matching for Few-Step Video Generation huggingface.co

Streaming video generation has benefited from distribution matching distillation (DMD), which matches the joint distribution of video frames to a video teacher’s approximation of the real video distribution. Although this joint matching mitigates drift during autoregressive rollouts, limitations remain in visual quality and semantic alignment. To address these limitations, we propose DuoMatching, a distribution matching framework that approximates the real video distribution through a unified jo

World Action Learning via Interaction-Centric Spectral Latent Guidance huggingface.co

Learning general-purpose robot policies requires large-scale real-world interaction data, yet collecting robot demonstrations remains expensive and difficult to scale. Egocentric videos offer abundant human interaction experience with task-relevant semantics for robotic manipulation, but direct transfer is challenging for two reasons: latent actions inferred from frame reconstruction can be dominated by nuisance variation such as ego-camera motion, and human and robot behaviors often exhibit dif

Kinematic MeanFlow: One-Step Action Generation Policy for Robotic Foundation Models huggingface.co

In this paper, we study how to achieve one-step action generation in Robotic Foundation Models (RFMs), aiming to overcome the high inference latency of multi-step flow matching. MeanFlow provides a promising framework for this goal, yet its direct application leads to performance collapse. We discover that this stems from two distinctive dynamics exhibited in the RFM velocity field: (1) the “local acceleration” exhibits stability early on, but surges sharply towards the end of the denoising pro

MiniCorp: The Last Mile of the AI Agent Firm huggingface.co

The last mile toward enterprise AGI is a company that runs itself. Training and adapting such agents require longitudinal enterprise data, which remain scarce, costly to acquire, and often restricted by privacy constraints. Historical archives are also frequently incomplete and record only what actually happened. They cannot show the outcomes of alternative decisions. We introduce MiniCorp, an office simulator for studying how agents can collectively run a company while generating enterprise dat

Learning Functional Subspaces for Neural Network Compression huggingface.co

Modern transformers pair impressive capabilities with substantial memory and compute demands. Low-rank weight factorization reduces both while keeping the matrices dense, and thus efficient on standard hardware. Existing methods, however, choose the subspace to remove from each weight matrix with local closed-form criteria: activation energy, layer-wise reconstruction error, or a quadratic approximation of the loss. These criteria ignore how errors propagate through the network, so at high compr

SlimWise: Decoupling Expert Pruning Across Prefill and Decode for Efficient MoE Serving huggingface.co

Mixture-of-experts (MoE) models activate few experts per token, yet batched decoding can access nearly the entire expert pool, making expert-weight traffic a major bottleneck. Expert pruning reduces this traffic, but conventional approaches also prune compute-bound prefill, sacrificing model quality for little throughput benefit. We present SlimWise, a serving framework that tailors the expert pool to each inference phase. SlimWise performs prefill with the full model and decode with a pruned mo

HLA: Expressive Hybrid Linear Attention via Chunk-Wise Dynamic Mixing huggingface.co

Linear attention enables efficient long-context autoregressive decoding by compressing history into recurrent states, but this compression can make selective access to sparse and distant information difficult. Existing chunk-based extensions increase memory capacity, yet learned chunk-mixing coefficients may remain fixed with respect to input content and therefore cannot adapt historical access to each query. We introduce Hybrid Linear Attention (HLA), a query-dependent chunk-level attention mec

Multilinguality in Hybrid Attention LLMs huggingface.co

In response to the growing demand for long sequences in agentic and reasoning use cases, many state-of-the-art LLMs combine multiple variants of attention to mitigate the quadratic complexity of traditional softmax attention. These hybrid attention LLMs aim to balance the strengths and limitations of full attention and alternatives based on recurrence. This work presents a first study of how hybrid attention impacts the multilinguality of LLMs. Beyond the impact on long sequences in poorly token

HiPLEX: Hierarchical Policy Factorization for Full Duplex Speech Language Models huggingface.co

As human—AI interactions become more conversational, full-duplex speech language models capable of natural real-time dialogue are growing in importance. Beyond generating appropriate responses, these models must coordinate turn-taking, backchanneling, and floor management in real time. Reinforcement learning (RL) provides a way to refine these behaviors through direct feedback on interaction outcomes. However, existing RL methods either apply timing feedback to a token policy or optimize semant

Hiding Tool Latency in On-Device Cascaded Voice Agent through Speculative Execution huggingface.co

Tool-augmented speech assistants typically serialize automatic speech recognition, large language model inference, and external tool execution. As a result, tool latency is incurred only after the user has finished speaking and the LLM has identified the required tool calls. We present speculative tool execution for on-device cascaded voice agents, which predicts tool requests from partial ASR hypotheses and initiates tool execution while speech is still being received, thereby reducing end-to-e

DAEDALUS: Bootstrapping Agent Memory from Self-Generated Tasks huggingface.co

LLM agents often lack the operational knowledge to act reliably in new environments, as they must discover specific tool behaviors or environment conventions on their own. Without memory of past attempts, they repeat the same mistakes across tasks, leading to more task failures and longer trajectories. To address this, agentic systems typically rely on human-written guidelines or on procedural memory built from training tasks and an oracle verifier, both of which require prior knowledge of the e

AutoSciBench: Autonomous Benchmark Generation for Evaluating Scientific Agents huggingface.co

As agents rapidly evolve, existing benchmarks can become saturated, limiting their ability to distinguish capabilities and reveal remaining failure modes. Particularly in scientific domains, constructing and updating benchmarks requires substantial time, labor, and domain expertise, making it difficult to keep evaluation aligned with advances in agent capabilities. We address this challenge by investigating whether scientific-agent benchmarks can be automatically generated and iteratively adapte

HuatuoGPT-3: RL-Only Domain Adaptation from Base Models huggingface.co

Domain adaptation aims to turn a general-purpose large language model (LLM) into an expert for a target domain. While the dominant SFT+RL pipeline offers a convenient cold start, it may reduce exploration diversity and introduces additional complexity through multi-stage optimization. These limitations motivate RL-only adaptation. However, pure on-policy RL suffers from a cold-start problem, while mixed-policy RL still falls short: informative tokens in teacher outputs are learned too slowly in

Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents huggingface.co

Multimodal agents commonly generate free-form reasoning before each action. For small models, limited model capacity can result in lengthy reasoning that provides little useful guidance for action generation while incurring substantial inference cost. To address this challenge, we introduce Selection-based Structured Reasoning (SSR), a framework that reformulates reasoning as selection instead of open-ended generation. SSR represents recurring high-level reasoning as pre-specified, reusable natu

DiffGate: Difficulty-Gated Teacher Guidance for On-Policy Distillation huggingface.co

On-policy distillation (OPD) has emerged as a widely used paradigm for post-training large language models, reducing the train—test mismatch of conventional distillation by supervising the student on its own generated trajectories. However, existing OPD objectives remain largely token-local and outcome-agnostic, optimizing teacher—student agreement at each prefix despite reasoning quality being determined at the trajectory level. Reinforcement learning with verifiable rewards (RLVR), particula

OPD Before RL: Warm-Starting Rubric-Based RL with On-Policy Distillation huggingface.co

Many useful language-model tasks cannot be evaluated by exact outcome verification. Rubric-based reinforcement learning (RL) addresses this issue by scoring open-ended responses against explicit criteria. However, because the reward is assigned after the complete response, the training signal does not directly identify which individual decisions contributed to the final score. We propose a two-stage training framework that uses rubrics first as privileged teacher context for dense token-level su

Harness-Aware Distillation for Small Language Model Agents huggingface.co

Language model agents are deployed with a harness, the software around the model that manages its context, tools, and feedback. When such an agent is distilled into a smaller one, the harness stays in place, so the student mainly needs the teacher-specific abilities that the harness cannot provide, such as acting correctly on harness information. Standard distillation, however, imitates the teacher’s full outputs and treats the harness as part of the input. We propose Harness-Aware Distillation

Sherpa: Teaching LLMs to Teach Adaptively huggingface.co

Large language models (LLMs) have become increasingly capable problem solvers, but being able to solve a problem is not the same as being able to teach it. Existing approaches to training LLMs as teachers rely on demonstrations, preference data, or predefined pedagogical criteria that specify what good teaching looks like. However, these signals are often not grounded in individual student learning outcomes, where effective teaching strategies can vary substantially across learners. To address t

EVISKILL: Grounding Skill Evolution in Replayable Evidence huggingface.co

Continual skill evolution enables LLM agents to accumulate and refine reusable procedural knowledge from interaction experience without updating model parameters. Its effectiveness depends on determining not only what to change, but also why a change is justified and when it should become persistent guidance. However, existing experience-driven methods can lose the behavioral evidence and task contexts supporting edits. Moreover, a global validation outcome provides an incomplete judgment of its

Adaptive Latent Capacity for World Models huggingface.co

We introduce Adaptive LeWorldModel (ALeWM), a world model based on a joint-embedding predictive architecture (JEPA) that learns to concentrate predictive information in compact prefixes of a wide latent representation. To encourage this ordering, ALeWM learns a sequence-conditioned distribution over prefix lengths and trains the predictor to estimate the full next embedding from a sampled input prefix. As standard anti-collapse objectives encourage variation across latent coordinates and do not

Towards In-Parameter Memory Augmentation for Large Language Models huggingface.co

Recently Large Language Models (LLMs) and LLM-based agents increasingly need to incorporate knowledge acquired after pretraining, e.g., domain facts, user preferences, documents, and interaction experience. In-context learning (ICL) and ICL-based agent harness remain flexible, but they consume context capacity and incur repeated discretized encoding cost that grows with context length. In-parameter memory offers a complementary substrate: reusable memory information is represented in model param

Building Rome from a Single Image huggingface.co

Single-image scene generation aims to produce a complete 3D scene mesh from a single image, including surfaces the camera did not observe. While pretrained 3D object generators encode a strong shape prior, they are mainly designed for isolated objects in a fixed canonical volume and focus mostly on indoor scenes, since diverse 3D data for outdoor scenes are quite limited. In this work, we present a method that redesigns such an object-centric generator, e.g., Trellis 2, to work on both indoor an

DistScene: Object-to-Scene Distillation for 3D Scene Generation huggingface.co

We present DistScene, a framework for single-image compositional 3D scene generation by jointly modeling the environment and individual objects. Unlike existing methods that represent scenes primarily as collections of objects, we model the environment as an explicit scene component to provide geometric context for object placement. Specifically, we introduce Scene-Frame Generation, which jointly generates separate environment and object components in a shared coordinate frame, allowing their ge

CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers? huggingface.co

Static-analysis checker synthesis requires agents to interpret a defect specification, inspect a repository, implement analyzer-specific logic, and refine the checker through repeated compilation and analysis feedback. Existing coding-agent benchmarks focus on tasks such as patch generation or vulnerability detection and rarely assess whether an agent can develop a working checker in a repository from start to finish. We introduce CheckerBench, an executable benchmark of 300 tasks derived from 2

AGO AI Quality Gate: Evidence-First Release Decisions for Retrieval-Augmented Generation huggingface.co

Enterprises adopting retrieval-augmented generation (RAG) face a recurring operational decision: promote, revise, or block a system version. The evidence is incomplete and the metrics come from fallible LLM judges. We report on AGO AI Quality Gate (AGO), an evidence-first quality-gate framework deployed in industrial RAG assessment engagements. AGO integrates four key components: a four-state decision model that treats missing data and judge errors as explicit outcomes; layered scoring combining

Personal-Agent Mediated Recommendation with Cross-Platform User History huggingface.co

Modern recommendation is shifting from platform-centric personalization toward user-governed personalization, where a personal LLM agent can act on the user’s behalf across services. We formalize this emerging paradigm as Personal-Agent Mediated Recommendation: a platform recommender ranks a candidate set using platform-local information, and a personal agent uses user-authorized cross-platform history to mediate the resulting ranking and produce the final top-K slate. Such mediation is nontrivi

ALIVE: Interaction-Aligned Object Insertion for First-Frame-Guided Video Editing huggingface.co

Current video editors can insert objects but often struggle to make them participate in interactions such as being picked up or manipulated. We introduce ALIVE, a framework that makes inserted objects “alive” through coherent interactions with the source video’s contents, using an edited first frame and an instruction naming only the added object. We curate 35,800 editing pairs combining 3D-rendered, model-generated, and real-world videos with general editing pairs from ROSE. Each pair differs i

Accent Analogy Guidance: More Speaker Similarity at Equal Accent in Cross-Lingual Voice Cloning huggingface.co

In cross-lingual zero-shot text-to-speech, the accent of the reference leaks into the target speech. We propose accent analogy guidance (AAG), a training-free sampler term that subtracts an accent direction estimated from the model’s own predictions for one synthetic voice rendered in both languages, so the voice cancels and only the accent remains. By a blind LLM accent judge on real dubbing data, reweighting classifier-free guidance between reference and text, and its variants, stay near one i

References

Moonlight review of ‘We Query, Therefore We Compute’ themoonlight.io

The paper provides a formal ‘OS-level’ language for LLM scheduling, caching, and safety, which previously relied on ad-hoc software abstractions… but does not provide a refinement proof for the kernel, leading some reviewers to label it as a ‘conceptual foundation’ rather than a production-ready secure OS.

Snorkel AI — Terminal-Bench 2.1 leaderboard snorkel.ai

SWE-2 holds the top position with a 92.8% resolution rate, followed by GPT-5.6 Sol at 91.9% and DeepSeek V4.1 Flash at 90.6%.

Knowlee.ai — AIOS LLM Agent OS primer knowlee.ai

AIOS reports up to 2.1x faster execution and a 95% reduction in context switching overhead (from 2.1s down to 0.1s) for concurrent agents.

fmind.dev — ‘AI Agents as an Operating System’ fmind.dev

Frameworks like LangChain can actually obstruct development by introducing ‘semantic hygiene’ issues… Rémi Louf advocates for a ‘kernel’ approach—using lightweight, event-driven triggers rather than rigid, hard-to-maintain graphs.

ResearchGate — ‘Jailbreaking LLM-Controlled Robots’ researchgate.net

LLM-controlled robotic systems can be ‘jailbroken’ with high success rates, suggesting that the ‘Priestess’ controller might be unable to prevent harmful physical actions if the Oracle backbone is compromised.

Medium — ‘The LLM OS Revolution’ falexm.medium.com

Standardizing these ‘Virtual Machine’ layers is essential for security, as it allows for the isolation and sandboxing of agent actions, mirroring the way the Java Virtual Machine provided a ‘write once, run anywhere’ environment.

airedteaming.dev field notes on ‘The Attacker Moves Second’ airedteaming.dev

Circuit Breakers… saw its ASR jump from 0% to 100% once an RL agent discovered and refined a specific exploitation path… adaptive attacks bypassed [12 defenses] with an ASR exceeding 90% for the majority of cases.

Daniel Paleka, October 2025 AI Safety newsletter newsletter.danielpaleka.com

Given how totally the defenses were defeated… reliable solutions may not be developed in the near future; robust optimization where the attack is part of the training loop is the only method that has shown any repeatable resistance, though at significant computational cost.

Simon Willison, ‘Prompt injection as role confusion’ simonwillison.net

Prompt injection is not a bug that can be patched through better training, but a structural reality of the instruction-data concatenation model… models prioritize stylistic formatting of text over actual safety instructions.

WASP benchmark (NeurIPS 2025 Datasets & Benchmarks) papers.nips.cc

Even frontier models are susceptible to simple, human-written injections in over 80% of cases… though end-to-end completion of complex attacker goals remains between 0% and 17% — a phenomenon researchers call ‘security through incompetence’.

QwenLM/WebWorld GitHub github.com

WebWorld scales web world modeling to over one million real-world interactions and supports long-horizon reasoning over 30+ steps… Qwen3-14B improved its WebArena success rate by 9.2% after simulation training.

How Robots Learn (community analysis) howrobotslearn.com

tactile data (contact and force) are statistical estimates derived from video, not direct sensor measurements

AI Weekly alert on RLHND aiweekly.co

the initial public abstract lacked raw numerical metrics and task success rates, making it difficult to independently verify its performance against established baselines

AnyTeleop (RSS 2022, roboticsproceedings.org) roboticsproceedings.org

a general vision-based teleoperation system that maps human hand-arm trajectories to various robots, outperforming specialized systems by utilizing a larger corpus of human motion data

YUAN Jetson T5000 benchmark report yuan.com.tw

Cosmos 3-Nano delivered more than twice the throughput of competitors like Qwen 3.5, with only a 1% trade-off in accuracy for edge reasoning

OpenTouch project page opentouch-tactile.github.io

over five hours of synchronized egocentric RGB video, full-hand tactile pressure maps, and hand-pose trajectories across 2,900 clips of contact-rich interactions

alphaxiv (ACE-Ego-Hand / DreamHand analysis) alphaxiv.org

diffusion-based models like ACE-Ego-Hand excel at local pose alignment, but may still exhibit higher absolute wrist localization errors compared to specialized 4D reconstruction frameworks like EgoH4RT

Sources

References

Jack Sun, writing.