Agenci i orkiestracja

Agents and orchestration · id agentsnode

Pętle działania, delegowanie i sterowanie wykonaniem.

Action loops, delegation and control over execution.

In one sentence

To programy, które wykonują zadania etapami, oraz sposoby koordynowania ich pracy.

These programs take steps toward a goal, with controls that organise their work.

Problem it solves

Jedna odpowiedź nie wystarcza, gdy trzeba sprawdzić informacje, podjąć decyzje i wykonać kilka zależnych od siebie czynności.

A single answer cannot finish a task that requires checking information, making decisions and carrying out several connected actions.

What it does

Po każdym kroku sprawdzają wynik i decydują, czy kontynuować, użyć narzędzia, czy przekazać pracę dalej.

After each step, they inspect the result and decide whether to continue, use a tool or hand work to another assistant.

Everyday example

Przygotowując wyjazd, asystent porównuje połączenia, sprawdza noclegi i przedstawia plan do twojej oceny.

An assistant planning your trip compares travel options, checks accommodation and brings you a plan to review.

This concerns you if you…

zlecasz asystentowi zadania wymagające kilku kroków
chcesz wiedzieć, kto koordynuje pracę kilku asystentów
give an assistant tasks that need several steps
want to know how several assistants coordinate their work

Examples

Harness · hand-offs · subagenci
Harness · hand-offs · subagents

Subtopics

Agenci przy komputerze (Computer and browser use): An agent clicking in a browser and on a desktop.
- Granica zaufania SA-CUA dla agentów komputerowych (SA-CUA trust boundary for computer-use agents): A dual-model architecture that masks the screen by default, reveals trusted regions using accessibility-tree rules, and separately endorses values from untrusted content.
- Syntetyczne środowiska komputerowe do treningu (Synthetic computer-use environments for agent training): Pipelines that automate synthesis, resetting and verification of executable training environments for computer-use agents.
Agenci w tle (Ambient and scheduled agents): Agents that wake up on their own: on a schedule or when something changes.
Autor i recenzent (Maker–checker review): No agent grades its own work; a second one assumes the output is broken and looks for where.
Dyfuzyjne modele językowe w agentach badań głębokich (Diffusion language models in deep research agents): Deep-research systems in which a diffusion language model powers model-bound stages such as planning, decomposition and report synthesis.
- Wczesna ekstrakcja podzapytań ze stanów odszumiania (Early subquery extraction from diffusion denoising states): A decomposition mode that reads intermediate denoising states of a diffusion model and extracts usable subqueries before generation finishes.
Hybrydowe agenty rozumujące (Hybrid reasoning agents): An agent dynamically switches between latent-space reasoning and text for tool calls and answers.
Orkiestracja subagentów (Subagent orchestration): Deciding when to launch subagents and how to hand work to them.
- Rynkowa samoorkiestracja rojów agentów (Market-based post-training for decentralized agent swarms): A post-training framework in which decentralized agent swarms jointly learn action policies and self-orchestration through bids.
- Samonadzór wieloagentowy (MASS) (Multi-agent self-supervision (MASS)): A recursive self-improvement method in which one model alternates between improving multi-agent workflows and fine-tuning its own weights on selected trajectories.
Planowanie przez wyobrażone przyszłe stany (Planning with imagined future observations): A technique combining policy and world model that generates visual consequences of hypothetical actions and selects a plan by comparing future states.
Protokoły agent–agent (Agent-to-agent protocols): An agreed way for agents from different systems to talk.
Role i tożsamość agentów (Agent roles and identity): A named agent with a scope and standing instructions instead of an anonymous session.
Routing między modelami (Model and harness routing): Matching the model and runtime to the kind of task and its cost.
Samodzielna nawigacja drzewa stanów agenta (Agent self-navigation in checkpointed search trees): A technique in which an agent saves intermediate states as a tree and chooses which node to resume, separating tree-level reflection from tool execution.
Trwałe naprawy agentów przez adaptery lekcji (Persistent agent repair with lesson adapters): A mechanism in which an agent, after failure, distils a lesson from its trajectory into a lightweight LoRA adapter while keeping base weights frozen.
Umiejętności agentów (Agent skills): A catalog of folders with metadata, instructions and resources, loaded in layers according to the task match.
- Format pliku umiejętności (Skill file format): A folder with an instruction file whose header has at least a name and description, matching the folder name.
- Skrypty w paczce umiejętności (Bundled skill scripts): Executable code bundled with a skill and run as a tool instead of being generated into context.
- Stopniowe wczytywanie umiejętności (Progressive disclosure of skills): Three-level skill loading: metadata at startup, body after selection, resources on demand.
Uprząż agenta (Agent harness): The loop, tools, context and constraints that turn a model call into an agent that carries out work.
- Budżety czasu dla agentów (Time-budgeted agent control): Harness and learning mechanisms that help an agent adhere to a wall-clock time budget.
- Kompozycyjne przeszukiwanie uprzęży (Compositional harness search): Modular harness with pools of implementations; a contextual bandit selects combinations for evaluation.
- Mapa dokumentów dla agenta (Repository map for agents): The agent's entry point is a short map to versioned documents, not a full manual in one file.
- Mechaniczne reguły środowiska agenta (Mechanical invariants for agent environments): Architectural and style invariants enforced by tests and linters, with a repair hint in the error.
- Przekazanie pracy między sesjami (Cross-session handoff for agents): Passing state between context windows through a log, a feature list and change history, not through compaction alone.
- Uczenie uprzęży agentów (Harness learning): Meta-learning over harness code: a proposer generates edits, reinforcement learning on execution outcomes.
  - Adaptacja uprzęży podczas RL (Harness adaptation during agentic reinforcement learning): RL in which the policy and harness adapt together based on training trajectories.
  - Koewolucja modelu i uprzęży agenta (Weight-harness co-evolution): A single policy acts as proposer and reflector; harness edit logs train its weights.
  - Rekurencyjna uprżąż z rewizją wsteczną (Recurrent harness with backward revision): A harness that adapts textual state by reading and writing reflections, then revising them from the outcomes of their downstream use.
  - Skalowanie uprzęży w agenticznym RL (Harness-diversity scaling for agentic reinforcement learning): Scaling agentic RL by training on diverse harness configurations instead of one fixed one.
- Zgodność intencji z wykonaniem narzędzia (Tool-call intent–execution correspondence): The property that the action actually executed by a tool matches the action denoted by the call under the tool contract.
Wspólna przestrzeń agentów (Shared agent workspace): A place where agents see each other’s work. Classic name: blackboard architecture.
Wyuczone wczesne zatrzymywanie nieudanych uruchomień agentów (Learned early stopping of failing agent runs): External small monitor model trained on completed trajectories and verifier outcomes that predicts failure and aborts the run.

Courses

Agentic AI

Sources

Hugging Face · Agents Course · reference: Agenci, narzędzia, frameworki, agentic RAG i ewaluacja.
FSDL · LLM Bootcamp (2023, archiwum) · reference: Aplikacje LLM, prompting, retrieval, UX i LLMOps.
DeepLearning.AI — course catalogue · course catalogue: 42 topic labels with counts, about 130 courses.
How to build your first team of agents · X article · sponsored (Raft) · Machina (X): Original link not found; file saved by the user. Structure only — no statistics, no product claims.