View-oriented Conversation Compiler for Agent Trace Analysis

View PDF HTML (experimental)

Abstract:Agent traces carry increasing analytical value in the era of context learning and harness-driven agentic cognition, yet most prior work treats conversation format as a trivial engineering detail. Modern agent conversations contain deeply structured content, including nested tool calls and results, chain-of-thought reasoning blocks, sub-agent invocations, context-window compaction boundaries, and harness-injected system directives, whose complexity far exceeds that of simple user-assistant exchanges. Feeding such traces to a reflector or other analytical mechanism in plain text, JSON, YAML, or via grep can materially degrade analysis quality. This paper presents VCC (View-oriented Conversation Compiler), a compiler (lex, parse, IR, lower, emit) that transforms raw agent JSONL logs into a family of structured views: a full view (lossless transcript serving as the canonical line-number coordinate system), a user-interface view (reconstructing the interaction as the user actually perceived it), and an adaptive view (a structure-preserving projection governed by a relevance predicate). In a context-learning experiment on AppWorld, replacing only the reflector's input format, from raw JSONL to VCC-compiled views, leads to higher pass rates across all three model configurations tested, while cutting reflector token consumption by half to two-thirds and producing more concise learned memory. These results suggest that message format functions as infrastructure for context learning, not as an incidental implementation choice.

Comments: Code: this https URL

Subjects:

Artificial Intelligence (cs.AI)

Cite as: arXiv:2603.29678 [cs.AI]

(or arXiv:2603.29678v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2603.29678

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Lvmin Zhang [view email] [v1] Tue, 31 Mar 2026 12:33:49 UTC (97 KB)