Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
The article discusses how Google Antigravity, combined with DeepMind’s Cheminformatics Skills, can speed up drug discovery processes. It explains how these tools help researchers search for compounds and suggest new rigidified macrocycles. The focus is on accelerating workflow efficiency in pharmaceutical research.
Predictive models for laser powder bed fusion (LPBF) are rarely used on the shop floor because querying them requires programming and model-specific knowledge. We present AgentAM, a large language mod...
The article discusses a recent paper titled "Sparks of Weight‑Space Programming," which shows that advanced language models such as GPT‑6 Astra can read and modify the raw weights of neural networks. The authors demonstrate that these models can interpret what a network was trained to do, write new small game‑playing networks from scratch, and even improve the math performance of Qwen‑3.5‑0.8B by editing a tiny fraction of its weights. The author notes that Qwen 3.8 27B running on a laptop can perform similar weight‑space programming tasks.
Although existing candidate trajectory evaluators have substantially improved end-to-end planning accuracy, their underlying mechanism remains suboptimal. Model-based evaluators typically make scoring...
Large language models are deployed as long-horizon agents that compose diverse tools across MCP services into executable workflows. Existing MCP environment-scaling methods are data-centric: they firs...
LLM agents often give conflicting answers to the same question, and many deployed agents are variants of one base model, so their errors are correlated. We study truth discovery among such agents: inf...
The article titled "Your Agent Works in the Demo. Now Make It Survive Monday" discusses the transition from a simple demonstration to a more robust, real‑world application. It highlights the challenges of ensuring an agent remains functional beyond a controlled demo environment. The piece appears on Towards Data Science.
We study cooperative multi-agent reinforcement learning with decoupled dynamics and a monotone submodular reward function over joint trajectories. Due to the non-additive reward, an optimal policy may...
Multimodal perception is central to many computer vision applications, including robotics and autonomous driving, where different sensing modalities provide complementary cues. Self-supervised learnin...
The article explains three methods for comprehending a codebase when coding agents generate code. It covers using Claude Code to produce feature memos, reviewing pull requests, and creating visual HTML explainers. These techniques help developers grasp what the agents deliver.
AI agents can make incorrect decisions or waste resources even when their tools and infrastructure work normally. Their nondeterministic behavior makes these problems difficult to reproduce and diagno...
The paper introduces ANGLER, an adaptive framework that uses state-based verifiers from the REEF benchmark to guide the evolution of web‑agent attacks. REEF provides 9 verifier‑grounded websites and 5 attack types, enabling realistic red‑teaming of VLM‑based agents. ANGLER improves attack success rates to 20.36% versus 15.24% for non‑adaptive methods and lowers benign task success from 61.9% to 44.4%.
Ax-Prover is a multi‑agent framework that uses Large Language Models (LLMs) combined with Lean tools via the Model Context Protocol (MCP) to generate formally correct proofs in mathematics and quantum physics. It can operate autonomously or collaboratively with human experts, and its performance on public math benchmarks and new Lean benchmarks in abstract algebra and quantum theory shows it is competitive with state‑of‑the‑art provers and often outperforms them. The system also demonstrated practical assistant capabilities by helping a mathematician formalize a complex cryptography theorem.
AutoAnalysis is an automated, self‑updating meta‑analysis that aggregates evidence on human‑AI collaboration. Its latest run includes 1,955 effect sizes from 420 papers, showing that human‑AI combinations outperform humans alone on average but still lag behind the best of either humans or AI alone. The tool continuously incorporates new studies, offering cumulative insights into when and how human‑AI synergy occurs across different agents, tasks, and processes.
The study examines how the choice of large language model (LLM) used to write job application cover letters influences hiring decisions, independent of the applicant’s qualifications. Using a multi‑model audit with eleven writer agents and nine evaluator agents across ten job descriptions, the authors find a consistent ranking of writer models—locally hosted models are disadvantaged and evaluators often favor their own outputs. The hierarchy has tangible effects, with up to 1.8 of 25 qualified candidates being rejected solely due to model mismatch, and the patterns are explained by shared stylistic cues that both writers and evaluators reward or penalise.
The paper introduces an open, reproducible biomedical knowledge graph ecosystem built on the Rust-native Samyama graph database. It details three foundational knowledge graphs—Pathways, Clinical Trials, and Drug Interactions—along with their expansion into a 22‑graph, 2‑cohort biomedical store containing over 328 million nodes and 1.44 billion edges, including synthetic patient data. The authors describe a reproducible ETL workflow, cross‑graph integration via query‑time joins and identifier deduplication, and a schema‑driven Model Context Protocol that achieves high accuracy on the BiomedQA benchmark.
The paper introduces a privacy‑preserving safety auditing paradigm for large language model agents that interact with online services via tool calls. It separates audit computation from plaintext access, using trusted representation construction, encrypted audit computation, and trusted decision interfaces to protect sensitive user data. The authors implement this paradigm in SealCall, which employs learned audit representations and CKKS‑based encrypted similarity computation, achieving a mean F1 score of 0.840 on 1,252 public binary candidates while maintaining plaintext audit decisions and completing encrypted scoring in 0.176 s.
Hierarchical World Models with Implicit Dynamics (ID‑WM) introduces a two‑level approach that separates state‑space reachability from local control. A high‑level model samples feasible transitions across the state manifold, while a low‑level world model acts as an inverse dynamics solver to translate these transitions into precise actions. This design enables planners to identify reachable subgoals without being constrained by low‑level execution details, producing novel long‑horizon plans that outperform state‑of‑the‑art policy and diffusion‑based planners by 38.5% and single‑level MPC by 135% in complex, unseen configurations.
The paper defines superintelligent software engineering as building and evolving software with agents whose capability exceeds that of human engineers, emphasizing that governance must scale with capability. It argues that correctness depends on decisions and contracts beyond code, that knowledge decays, and that when agents outpace reviewers, stale knowledge grows. The authors introduce OSTEON, a governance framework that tracks decisions, contracts, and knowledge decay, and report no measured effect of the system while outlining questions that could falsify their thesis.
SecPO introduces a principled adversarial training framework to defend large language models against prompt injection attacks. By approximating an ideal injection‑invariant reference model and employing a new SecPO loss, the authors improve security while preserving utility. Combined with an efficient adversarial training pipeline that synthesizes strong injected inputs, the resulting SecPO + AT model significantly reduces attack success rates compared to existing defenses and maintains performance across multiple benchmarks.
