Agent 深入

Agent advanced: design multi-tool, multi-step agents with planning, safety, and stability.

1) Agent Styles

• ReAct: interleave reasoning + tool use, good for search/code tasks.
• Plan-and-execute: plan first, then execute steps; stable for longer tasks.
• Tree of Thoughts / Reflexion: explore multiple options, self-critique, pick best.
• Router agents: choose specialized sub-agents by intent/domain.

2) Tooling Strategy

• Tool schema: explicit params, types, constraints; prevent free-text tool calls.
• Tool selection: require rationale; limit tool list per task to reduce mistakes.
• Sandboxing: code exec/search in isolated env; resource/time limits.
• Idempotent tools where possible; otherwise guard with locks.

3) Planning & Memory

• Short-term: keep recent steps concise; prune verbose logs.
• Long-term: store key facts/decisions; retrieve by intent or doc ID.
• Checkpoints: allow resume after failure; persist plan + progress.

4) Safety & Policy

• Guardrails before/after tool calls (PII, dangerous actions).
• Allowlist external domains/APIs; blockwrites unless explicitly permitted.
• Human approval steps for risky actions (emails, transactions, prod changes).

5) Quality Controls

• Stop conditions: max steps/tool calls/time; detect loops.
• Self-critique: ask agent to verify outputs vs. instructions and citations.
• Dual-model verification: cheap model executes, stronger model reviews.

6) Observability

• Trace per run: steps, chosen tools, inputs/outputs, duration, errors.
• Metrics: success rate, avg steps, tool error rate, cancel rate.
• Replay: store deterministic inputs; enable re-run with same seed/config.

7) Minimal Skeleton (pseudo)

while not done:
  plan = agent.decide(observation, tools)
  if plan.type == "tool":
    result = run_tool(plan.tool, plan.args, sandbox=true)
  else:
    result = agent.respond()
  observation.append(result)
  if stop_condition(): break

8) Practice

1. Build a ReAct agent with 2 tools (search + calculator); add max-steps + timeout.
2. Add a self-critique step: verify answer cites the tool outputs.
3. Log each step to a trace store (time, tool, args, tokens) and surface a run report.