Context compaction
Technique · Agents · 4 items since Jun 2026
Summarizing or pruning an agent's history so long tasks continue within the context limit.
Related
- Organizations
Trends
Items
- Sep 18
Empirical study of coding-agent harness design
Across 176 matched settings on SWE-Bench Verified and Terminal-Bench 2.1, staging rule-based elision before LLM summarization is the most efficient context strategy, and planning shifts from an accuracy aid for weaker models to a cost saver for stronger ones.
- Aug 3
OpenAI details GPT-Live and the WARP protocol
OpenAI described the full-duplex architecture behind GPT-Live, with asynchronous delegation to frontier models and context-compaction handoffs, plus an open WebRTC Abridged Roundtrip Protocol that cuts session startup from six network round trips to one.
- Jul 24
BAAI's AREX self-improving research agent
A deep-research agent alternates an inner evidence-gathering loop with an outer constraint-wise self-audit and an autonomous context-compression tool, released as open-weight 4B and 122B-A10B MoE models competitive on BrowseComp and Humanity's Last Exam.
- Jun 22
SelfCompact compacts agent context on demand
A model-invoked compaction tool fires only when a sub-task resolves or a trajectory converges, matching fixed-interval summarization while improving math accuracy by up to 18.1 points at 30-70% lower per-question cost, with no fine-tuning.