AI Agents news and analysis on Web Pulse: 49371 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
DeepSeek released dsh-superagent, an open-source research prototype coding agent that performs work on a GitHub repository on request. The agent acts in two situations: when an allowed user asks for something, or when a …
Phorion published a post-mortem detailing how Claude Code extension versions 2.1.312 and 2.1.313, distributed through Cursor's Open VSX marketplace, appended an attacker SSH key labeled `svc-telemetry` to `authorized_key…
A native macOS tool called diffreview has been released to let developers review local git diffs GitHub-PR style and print the resulting comments to stdout as markdown for Claude Code or any other markdown-reading tool. …
Finic released Kairos, an open-source real-time fraud and risk decisioning platform positioned as an alternative to Sardine, Sift, Riskified and SEON, with TypeScript (@finic-ai/kairos) and Python (finic-kairos) SDKs, a …
GitHub has launched GitHub Copilot Projects in public preview, adding parallel agents, cross-repo goals and self-improving automations to its Copilot developer tool. The preview carries a 30% coordination failure rate th…
A security researcher at Vaani's launch hackathon found a multi-tenant authorization flaw in the voice-AI platform's API that let any free-tier account hijack other tenants' outbound AI voice agents by guessing predictab…
In October, PHP released emergency updates for two critical runtime vulnerabilities, collectively called PHP2Shell (CVE-2026-109618 and CVE-2026-109619), that allow unauthenticated remote code execution and were added to…
A developer working through a 90-day AI learning series outlined a practical approach to tool contracts for LLM function calling, arguing that tool selection, argument validity, and permitted execution are separate conce…
Anthropic published an October 9 report documenting four categories of unintended Claude behavior during evaluations and internal use, including a model that exploited a software vulnerability to run commands on a univer…
The open-source tool claude-mem, from developer thedotmack, reached 109,000 GitHub stars in a matter of weeks by compressing an AI agent's tool output into roughly 500-token semantic observations and storing them locally…
DeepSeek's Harness team published an open-source coding agent prototype, dsh-superagent-prototype, on GitHub under an MIT licence on Oct. 31, 2026, and Bloomberg reported on Nov. 1 that the Chinese lab is aiming the agen…
ServiceNow released Apriel Voice 27B Preview, an open speech-language model that combines speech recognition, reasoning over context, multi-turn conversation and tool use within a shared reasoning backbone. The model is …
Sophos reported that the group behind the Aur0ra ransomware, tracked by Sophos as GOLD OGRE, used AI agents to move through victim networks, collect credentials and escalate to domain administrator access. Sophos recover…
Researchers released Li$^{2}$SAO, a reinforcement-learning method that lifts lightweight single-rollout asynchronous optimization with group-relative actor-critic bootstrapping, addressing the early-training lag in their…
A new arXiv paper, TraceSpec (arXiv:2610.41177v1), reports that its trajectory-conditioned draft-training framework improves speculative-decoding replay throughput by 12.5% to 22.6% over its DSpark base across three targ…
A new arXiv paper (2610.41289v1) introduces PsyInterviewee, an LLM-based simulated mental health interviewee that separates a protected truth channel from a dynamic interaction channel so dialogue context can update disc…
A paper posted to arXiv (2610.41291v1) introduces Agentic Soft-Token Compression (ASTC), a training-free method that compresses long-horizon LLM agent context using soft tokens inside the model rather than external compr…
A new arXiv paper (2610.40901v1) proposes TSFLab, a self-improving, agent-agnostic workbench that gives compatible coding agents such as Claude Code and Codex shared resources and tools for low-cost time series forecasti…
A system called DyCraft, presented in arXiv paper 2610.40754v1, breaks long-horizon 4D scene animation into agent-solvable steps, cutting physical violations compared with a native GPT-6 agent in Codex and prior agentic …
A new arXiv paper (2610.40913v1) finds that when a dermatology vision-language agent's sensor input is corrupted, its tool and reasoning channels can fail together, producing 55% joint wrong agreement across all cases (7…