AI ENGVisual Encyclopedia

MODULE 8: ADVANCED CAPABILITIES & DEPLOYMENT · SCENE 22

Multimodal & Agentic Alignment

Interleaved image/audio token mix and the composite tool-call success rate of syntax plus argument fidelity.

SYNTAXARGSTOOL SUCCESS · 89.8%IMAGE TOKEN SHARE · 26%
SYNTAX 95%×ARGS 90%EXEC 89.8%+30% RETRY RECOVERY · CREDIT BLUR OVER 30 STEPS = 0.18

Agent success decomposes into syntax × argument fidelity, plus retry recovery. Long trajectories blur outcome credit to ~1/√steps — hence process rewards.

TECHNICAL BREAKDOWNModule 8: Advanced Capabilities & Deployment

Multimodal and agentic alignment

Post-training extends beyond text: interleaved image/audio tokens need their own alignment data, and agentic models must not just answer but act — emitting well-formed tool calls with faithful arguments. Both extend the SFT/RL toolkit with new reward surfaces.

Token Mix

An image costs hundreds-to-thousands of tokens via a vision encoder. Token budgeting across modalities decides context economics and which modality dominates gradients.

Tool-Call Success

Success decomposes: syntax valid × arguments faithful × execution succeeds. Training on execution traces (with retries) teaches repair behavior.

Trajectory Credit

A 30-step agent run has one outcome signal. Per-step credit blurs as 1/√steps — hence step-level verifiers, process rewards, and short-horizon curricula.

MATHEMATICAL FORMULATION · COMPOSITE TOOL SUCCESS
success = min(1, s_syntax · s_args + (1 − s_syntax · s_args) · retry_gain); blur = 1/√steps

95% syntax × 90% argument fidelity = 85.5% base; a 30% recovery from retries lifts it to ~90%. Meanwhile a 30-step trajectory's credit signal blurs to ~0.18 — outcome-only RL on long horizons is nearly signal-free.

REAL-WORLD PRODUCTION ENGINEERING
  • Agentic post-training runs on real execution sandboxes (shell, browsers, APIs) with per-step telemetry; success rate on held-out tasks is the KPI, not loss.
  • Multimodal preference data is scarce and expensive; most pipelines bootstrap it by projecting text preferences onto multimodal conversations.