Search: “agents”

arXiv:2607.02079v1 Announce Type: new Abstract: We present HaloGuard 1.0, an open-weights implementation of the constitutional-classifier paradigm for input safety. It achieves state-of-the-art perfor

Highly-recommended read from MIT on the part of RL with verifiable rewards that everyone keeps hitting. RLVR only optimizes what you can objectively score, so style, structure, and diversity quietly c

arXiv:2607.01813v1 Announce Type: cross Abstract: Evaluation benchmarks are essential for assessing vision-language models (VLMs), but most multimodal benchmarks are static, making them vulnerable to

NEW paper worth reading. (bookmark it) The basic idea is to pair a compressive recurrent state with a small exact memory, which helps to recover long-range recall without giving up the efficiency of l

arXiv:2607.01518v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have been increasingly integrated into robotic systems. However, these models may exhibit overthinking behaviors,

arXiv:1808.07645v5 Announce Type: replace-cross Abstract: The 20 Questions (Q20) game is a well known game which encourages deductive reasoning and creativity. In the game, the answerer first thinks o

arXiv:2602.20459v2 Announce Type: replace Abstract: Can AI systems trained on the existing scientific record forecast the advances that will follow? We introduce PreScience, a dataset and benchmark fo

arXiv:2510.09517v2 Announce Type: replace Abstract: Despite rapid advances in large language models (LLMs), statistical reasoning remains underrepresented in existing LLM benchmarks, which often do no

This is true… but maybe less important than the fact that people don’t try ambitious things with these systems. Many models are excellent as a Google replacement, for homework “help,” etc. It is someo

arXiv:2607.01152v1 Announce Type: new Abstract: Creativity research has debated whether creativity is domain-specific (e.g., visual, writing, science), and if it is psychometrically separable from gen

Another fascinating paper on LLM Judges. (bookmark it) It's from Amazon, and they show that if you run panels of LLM judges, averaging their scores is a trap. 'Overall, we establish that robust aggreg

arXiv:2607.00895v1 Announce Type: new Abstract: Hallucination detection for retrieval-augmented generation (RAG) is usually evaluated on natural-language document evidence. However, grounded generatio

arXiv:2607.00002v1 Announce Type: new Abstract: Moral cognition has traditionally been modeled as adherence to fixed ethical theories--deontology, consequentialism, virtue ethics--implemented as stati

arXiv:2607.00160v1 Announce Type: new Abstract: Modular reconfigurable robotic systems provide a scalable solution for cooperative surface operations in future lunar missions. However, cooperative car

arXiv:2607.00545v1 Announce Type: new Abstract: Controllable traffic simulation is critical for testing autonomous driving systems, yet existing approaches often require retraining large generative mo

arXiv:2607.00025v1 Announce Type: cross Abstract: While deep learning models achieve state-of-the-art performance in complex tasks, they remain brittle when faced with new environments or sensory depr

I just left the final day of the @aiDotEngineer World's Fair Conference in San Francisco. Kudos to @swyx for putting together a world-class lineup of speakers and workshops! It really was an invigorat

arXiv:2603.16085v2 Announce Type: replace-cross Abstract: Recent breakthroughs in 3D generation have enabled the synthesis of high-fidelity individual assets. However, generating 3D compositional obje

arXiv:2607.01232v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a central component of post-training large language models (LLMs), yet little is understood about how RL adapta

arXiv:2607.00442v1 Announce Type: cross Abstract: Reinforcement learning (RL) for quadruped locomotion commonly depends on fixed, hand-crafted, and Markovian reward functions that limit both interpret

arXiv:2607.00392v1 Announce Type: cross Abstract: Unsupervised Reinforcement Learning (URL) aims to pre-train scalable, skill-conditioned policies without extrinsic rewards, serving as a foundation fo

arXiv:2607.00622v1 Announce Type: new Abstract: Video anomaly understanding (VAU) relies on sparse, context-dependent cues. However, existing passive paradigms suffer from observational aliasing, wher

arXiv:2607.00733v1 Announce Type: cross Abstract: Mechanistic modeling via ordinary differential equations (ODEs) provides interpretable descriptions of complex dynamics and enables inference of under

My one serious piece of advice having used Fable a bunch before release is that, unless you are careful it develops its own internal bizarre cadence & dialogue over long tasks. If you aren't asking it

NEW paper from NVIDIA. They discuss robot programming that compounds experience instead of throwing it away. Traditional robot programming forces you to orchestrate perception, contact dynamics, diver

New research from Google. LLMs hallucinate with high confidence, miss their own knowledge boundaries, and misreport uncertainty. Most fixes bolt calibration on from the outside. RLMF turns the model o

so proud to be working with a bunch of people who are absolutely crushing it! check out all these new things if you haven’t had a chance to yet. huge week for us here @LangChain!! big week at langchai

arXiv:2607.00142v1 Announce Type: new Abstract: This paper takes issue with the recent themes of both the RO-MAN and the HRI conferences for their portrayal of a future human-robot society as inevitab

arXiv:2607.00796v1 Announce Type: new Abstract: Visual Reinforcement Learning (VRL) has achieved considerable success in solving control tasks. However, generalizing learned policies to new environmen

🌍 World’s Largest Hermes Buildathon 10 cities. 5 countries. $750K credits Backed by OpenAI, Convex, Cloudflare, ElevenLabs, Linkup, Dodo Payments, Hissa Fund & Wispr Flow. Proudly presented by GrowthX

arXiv:2606.31204v1 Announce Type: new Abstract: Synthetic data generation has emerged as a powerful tool for improving data scalability in computer vision. Recent diffusion-based pipelines have demons

Chris Metinko / Axios: B2B sales workspace startup Aligned raised a 60M Series B led by PeakSpan Capital, taking its total funding to 73.8M, and says it has 1,000+ customers — Aligned, a sales workspa

arXiv:2606.31002v1 Announce Type: new Abstract: Theorem-proving benchmarks evaluate proof search against fixed formal statements, but natural-language-to-Lean formalization must generate the formal st

arXiv:2606.31844v1 Announce Type: cross Abstract: A local-to-global context mismatch arises when autoregressive traffic simulators trained on ego-centric driving logs are deployed in globally observab

arXiv:2508.10409v3 Announce Type: replace-cross Abstract: This paper constructs a textual dataset for training large language models (LLMs) to learn analog circuit knowledge and customizes LLM trainin

ENPIRE -> ASPIRE, our 2nd work in the series for Physical AutoResearch. We are building the components for robot self-improvement, one /skill at a time. Today, we give robots a /skills library that se

arXiv:2606.30809v1 Announce Type: new Abstract: Existing 3D Gaussian Splatting (3DGS) systems distribute representation capacity uniformly across a scene, ignoring the fact that many downstream roboti

arXiv:2606.31048v1 Announce Type: cross Abstract: This paper investigates knowledge distillation from a large reasoning model (DeepSeek-R1) to a compact student model (Qwen2.5-7B). Using historical pr

Significant contributors to this article include Sneha Aradhey, Software Engineer, Google Kubernetes Engine, and Michael MacDonald, Sr Software Engineer, Google Cloud Managed Lustre. Enterprise produc

arXiv:2606.31562v1 Announce Type: new Abstract: Stabilization learning is an interdisciplinary paradigm that bridges control theory and machine learning. Its core idea is to enable systems to adjust t

arXiv:2606.31377v1 Announce Type: cross Abstract: Reinforcement learning for long-horizon robotic manipulation is often limited by sparse and delayed rewards, while manually designing dense shaping si

arXiv:2606.31039v1 Announce Type: new Abstract: Large Language Models (LLMs) exhibit strong semantic capabilities, yet their resilience to manipulative linguistic patterns such as logical fallacies re

arXiv:2602.01070v5 Announce Type: replace Abstract: Test-time compute scaling allocates inference computation uniformly, uses fixed sampling strategies, and applies verification only for reranking. In

You really need to benchmark models for your use case. As soon as judgements & decisions stack on top of each other, the differences between models amplifies, and no standard benchmark will tell you t

arXiv:2606.29221v1 Announce Type: new Abstract: We address the problem of online multi-human multi-robot teaming through the lens of a linear matching bandit framework, where a learner assigns robots

arXiv:2606.29687v1 Announce Type: cross Abstract: We report a machine-verified resolution of a problem open for over a decade in quantum optimization: the Farhi, Goldstone and Gutmann (FGG) conjecture