AI Agents news and analysis on Web Pulse: 13496 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
Researchers introduced CoC-Seduce, a benchmark for testing LLM rule adherence in semi-open textual environments, revealing that frontier models like GPT-5.4, Claude Sonnet 4.6, and Gemini 3.5 Flash are vulnerable to Rhet…
Researchers propose ASK+, an uncertainty-gated framework that improves small language model (SLM) guidance for reinforcement learning agents under partial observability. By providing trajectory-aware context and structur…
Researchers propose Object-Centric Environment Modeling (OCM), a method that organizes LLM agent experience into executable object-centric code bases, improving performance and reducing invalid actions across benchmarks.
Researchers introduced MedCalc-Pro, a benchmark for evaluating LLMs on complex medical calculations involving multiple calculators and nested scales, covering 2,268 cases across 14 departments. They also proposed a gener…
Researchers introduced Incognita, a framework for evaluating generative agents in socially distributed task environments where knowledge is partitioned across role-isolated participants. Testing on 18 retail tasks showed…
Researchers formalized medical diagnosis as an iterative evidence-seeking task and used reinforcement learning with verifiable rewards to train large language models to autonomously gather clinical evidence. Their framew…
Researchers introduced APeB, a benchmark for evaluating personalization in LLM-powered agents, finding that models struggle with raw, underspecified queries due to ineffective use of interaction histories. A proposed pip…
Researchers propose an organizational memory for LLM-based agents to automate business process execution, addressing the challenge of fragmented organization-specific knowledge. The shared, governed reference layer aims …
A study in a graduate-level mobile robotics course found that a Socratic-Guidance (SG) tutor, which uses dialogic questioning, led to higher learning gains and more understanding-driven prompting strategies compared to a…
A new study on agentic AI policy repair in a hotel-pricing simulator shows that LLM-based editors can nearly match benchmark performance using only region-level diagnostic feedback, achieving RevPAR 108.47 vs. benchmark …
A July 5, 2026 arXiv paper proposes a Generative AI Control Framework to help financial institutions align generative AI governance with the Federal Reserve's SR 26-2, which modernizes model risk management. The framewor…
By 2026, AI agents moved from demos to production, introducing runaway costs from tool calls and recursive reasoning. A VentureBeat survey found 79% of enterprises took financial hits from autonomous agents, while Uber b…
Researchers introduced CAGE-1, an evaluation framework for enterprise agentic AI that assesses control, assurance, and governance before deployment. The framework tests authority, policy enforcement, retrieval quality, m…
Researchers introduced SkillOpt-Lite, a minimal skill optimization pipeline for autonomous agents that accelerates convergence and improves performance, achieving +8.8 points on LiveMath with GPT-5.5 and +25.4 points wit…
Theo Browne published a guide for running GPT-5.5 as a subagent within Claude Code workflows, ranking models by cost, intelligence, and taste. The approach uses GPT-5.5 for bulk mechanical work via the Codex CLI, while r…
A developer explores balancing Claude 4.8 and GLM 5.2 in structuring prompts for mid-level coding agents, aiming to optimize performance in automated code generation tasks.
Anthropic released Claude Fable 5, a new AI model that improves agentic coding by helping developers discover their unknowns. The model's effectiveness depends on users' ability to clarify their intent, making the skill …
A developer explains how the Model Context Protocol (MCP) differs from traditional APIs by enabling ongoing, context-aware conversations between systems rather than one-off requests. MCP allows programs to remember past …
Anthropic's Claude Sonnet 5 reduces costs for agentic AI, while agent frameworks like Konsistent, RF-DETR Keypoint, Search Toolkit, and Koog 1.0 ship stable APIs and tooling. Konsistent enforces structural code conventio…
Neander, a purpose-built language for agentic systems, makes API discovery a first-class language feature through its 'discover' verb. The language unifies finding and calling APIs into a single 'submitProgram' operation…