architecture · replace-conversation-history-rewritten-execution-state TEC-0294 · proposed

Replace conversation history with a rewritten execution stat

At each step the model sees only the immutable skill spec, the current structured state and the latest observation, emits a JSON state patch plus an action, and has its reasoning trace discarded after the runtime validates and merges the pa

Proposed. Filed by the drafting stage because a paper introduces or tests it. Nobody has vouched for it. The claim drafted from that paper is its first evidence, and what the paper used to validate it is in that claim’s source note. Say whether it held up for you, below.

At each step the model sees only the immutable skill spec, the current structured state and the latest observation, emits a JSON state patch plus an action, and has its reasoning trace discarded after the runtime validates and merges the pa Filed by the drafting stage from SKILL.state: Scalable Long-Horizon Agent Skills (2608.26263) with status proposed: the paper introduces or tests it, and the claim drafted from the paper is its first evidence. The paper validated it by: On a 500-shelf warehouse simulation with Gemini-3-Flash over 5 seeds, accuracy at T=200 was 0.94 vs 0.74 (ReAct), 0.84 (summary memory) and 0.88 (LangGraph-style structured state plus full transcript), with 122k vs 2.6-6.2M cumulative tokens; at T=100 under a matched ~1,800-token budget it scored 0.94 vs 0.18 sliding window, 0.52 summary-capped and 0.22 LLMLingua. Also highest pass rate on InterCode CTF (54.2% vs 46.4% best baseline) and both tau-Bench domains.. Nobody has vouched for it; add support or contest it on this page.

Addresses: Completing tasks that take many steps or many hours

Does it work?

nothing measured0 supporting · 0 contesting sources

Efficacy claims — what this technique actually moves, under which conditions, and whether that has been contested.

No efficacy claim filed yet. The technique is catalogued; whether it moves the capability, and when, is a separate assertion that needs its own sources.

No search recorded either, so this says nothing about the literature — only that nobody has looked here yet.

Code

No repository linked yet. Contribute one.

Sources

Either way, bring evidence: a link, or what you saw.

Whether a technique works is a claim. What you file here becomes a claim about this technique under the capability it addresses, with your evidence as its source, and moves the standing above the same way a paper would.