AI Coding Live News

As autonomous agents execute complex multi-step workflows across terminal consoles and web browsers, context window expansion and escalating token costs impose severe operational bottlenecks. Conventional compaction methods rely on text summarization or token pruning, both of which discard crucial state variables and induce semantic drift over extended sessions. Researchers from HKUST and Alibaba present REMORY (arXiv:2610.11287), introducing a residual memory paradigm designed for sequence-level context compaction. REMORY combines lossy natural language summaries with bounded sets of learned soft memory tokens, effectively forming a residual connection in the sequence dimension. While text summaries convey high-level narrative continuity, the soft memory tokens reconstruct lost fine-grained execution artifacts, API arguments, and intermediate environment states. On challenging benchmarks including BrowseComp and Terminal-Bench 2.1, REMORY retains 97% of full-context task performance while occupying only 5.2% of the original input token footprint, slashing redundant tool retries and loops by more than 40%.

@CompleteSkeptic (Diogo Almeida, TypeSafe; RLHF background) published public design notes on TypeSafe × coding agents (Google Doc), covering routing, context compaction, subagents, skills, and MCP tradeoffs, and invited the community to experiment. The post drew ~930 likes / ~56k views the same day.

@aiRobertDaily highlighted fast-jev-compaction, a Claude Code plugin that replaces traditional LLM summarization with Jev-driven, decision-based context compaction. It quickly filters tool calls and results, drops or truncates stale content, and keeps only the necessary parts of valuable text; a related Codex-facing Jev context server was also noted. The aim is lower token cost and faster delivery.

Sourcegraph introduced a semantic context compaction engine for Cody. Designed for deep call-stack comprehension, the algorithm prunes boilerplate while strictly retaining function signatures, type contracts, and critical execution paths. This compresses token usage by 60% and increases multi-package code synthesis accuracy by 34%.