Tool Use

MCP Apps let servers return sandboxed, interactive UI instead of text alone while the host retains control of prompts and tool calls—a useful pattern for agent workflows needing charts or controls.

MCP Tasks aim to make long-running tool calls durable across disconnects and crashes. The proposed V2 removes session-heavy state, but polling scale and implementation complexity remain unresolved.

Training on a production harness could adapt an agent to real workflows, but non-replayable interactions break common RL assumptions and make feedback harder to turn into updates.

Chat SDK’s Teams adapter adds reactions, user-only ephemeral messages, custom token supply, and routing fixes useful for building safer agent approval and progress flows.

mcp-handler 2.0 adds the stateless 2026 MCP protocol and SDK v2 while keeping 2025 Streamable HTTP clients working, but drops HTTP+SSE and raises upgrade requirements.

Inkling Small is pitched as a lower-compute model for coding, tool use, and visual reasoning, with adjustable thinking effort and zero-data-retention routing through Vercel AI Gateway.

Vercel tokens can now be restricted to one project, giving agent jobs and automation read/write access without exposing unrelated project, team, or user resources.

Kepler’s pattern keeps LLMs away from numeric mutation: agents choose sources and steps, while deterministic systems persist, calculate, and reject unverifiable values.

Intuit argues that domain context alone does not create experience. Its approach learns from verified state-action-outcome histories, using frontier models only to propose candidates.

Grok Voice Think Fast 2.0 brings speech-to-speech reasoning and earlier tool calls to Vercel’s realtime API, with server-minted tokens keeping gateway keys off clients.

Gemini Managed Agents now add model selection, sandbox hooks, token caps, schedules, and free-tier access, covering several controls needed for unattended coding work.

Edge-agent design is often memory-bound: use small prompted models when devices can spare gigabytes, or fine-tune tiny models for narrow functions when reach and latency matter more.

Skill-SP turns agent skills into units for verifiable self-play: generate tasks, solve them, then update the skill library from execution feedback. The abstract provides no per-benchmark effect sizes.

Perception agents share the rendered interface with users, turning visual annotations and design rules into agent input and checks. The open-source harness is an early attempt to close computer-use feedback loops.

Vercel’s MCP server can deploy agent-built code to new or existing projects and return a shareable URL, extending chat-based coding workflows through delivery.

AI Gateway can now stream audio into transcription models and emit partial text, letting text-based agents accept lower-latency voice input without changing the agent itself.

Vercel MCP can now buy plans, credits, add-ons, and domains from an AI assistant, but it must disclose pricing and obtain confirmation before completing a charge.

PalmClaw runs the agent loop, memory, skills, and tools directly on a phone, exposing device capabilities as structured calls instead of GUI gestures. The paper reports faster, more reliable task execution.

Chat SDK now targets X alongside six other channels from one bot codebase, handling webhook verification and OAuth refresh while accepting no streaming and likes-only reactions.

Alibaba’s open-source review CLI combines deterministic diff handling with an LLM agent to improve line-level precision and reduce token use, while explicitly trading away recall.

Grok2API fronts Grok Build, Web, and Console account pools with OpenAI- and Anthropic-compatible APIs, but its unofficial SSO routing creates terms, credential, and renewal risk.

Muse Spark 1.1 gives agent builders a 1M-token multimodal model with parallel tool calls, MCP support, and the option to run as a main agent or subagent.

SearchGen-Bench shows open image generators score 21–28/100 on long-tail entities, and naive search retrieval only adds noise; a teach-then-search co-training recipe learns when to retrieve versus rely on weights.

DramaSR-532K benchmarks speaker attribution over 532K dialogue lines and 900+ TV-drama characters; a reasoning LLM with multimodal tool use beats acoustic baselines, especially on short utterances.

Gemini Managed Agents can now run asynchronously, connect to remote MCP servers, call client-side functions, and rotate credentials without losing sandbox state.

Baileys exposes WhatsApp Web through a WebSocket-based TypeScript API, but v7 introduces breaking changes and remains unofficial, making migration and platform risk the main concerns.

Chrome DevTools MCP gives coding agents direct access to browser automation, network data, console errors, screenshots, and performance traces, with privacy controls worth setting explicitly.

A security skill router gives coding agents scoped, repeatable playbooks for reverse engineering and pentesting instead of ad hoc tool selection. Its case workflow also preserves evidence and findings.

GitHub now exposes the Copilot CLI agent runtime as SDKs for six languages, including planning, tools, and file edits. Builders can embed it with configurable permissions, auth, models, and BYOK.

eve’s Chat SDK channel lets one agent span messaging adapters while retaining threads, approval cards, proactive sends, webhook handling, and overridable defaults.

A proposed agent harness separates planning from execution, represents tool calls as inspectable programs, and requires machine-checkable safety proofs before side effects run.

Use LLMs to turn ambiguous requests into search plans, then resolve entities with deterministic indexes and set operations. This avoids context bloat and silent misses at production scale.

Five code-level controls reduce agent errors: narrow tool context, query structured data, validate responses, enforce rules before calls, and steer runtime correction.

Agent Reach installs, checks, and routes web-access tools for coding agents, reducing the setup work behind research across social platforms, video sites, GitHub, RSS, and the open web.