AIarXiv
Heuristic editor, no API keyVerdict: RoutineREMORY: Learning Residual Memory for Context Compaction
Long-horizon agents compact their history to continue within a finite context window, but a textual summary alone may not support every subsequent decision.
Key numbers
- 5.2% of the input positions
Caveats
- Preprint; not yet peer reviewed.
VerdictCompetent work. Briefs at most.
Abstract
Long-horizon agents compact their history to continue within a finite context window, but a textual summary alone may not support every subsequent decision. We introduce REMORY, a neural memory network that supplements the summary with a bounded sequence of soft memory tokens. Given the history and summary, the network learns to generate tokens that help a frozen LLM approximate the continuation it would produce with the full history. The tokens are conditioned on the summary and appended after it, forming an analogue of a residual connection along the sequence dimension. On SummHay, REMORY improves source attribution at nearly unchanged insight coverage and approaches the full-context joint score using only 5.2% of the input positions. Across long-horizon agent benchmarks, Qwen3.8-27B and GLM-5.3-Flash show consistent gains with residual memory. Both models also exhibit substantially fewer repeated tool outputs and tool errors on BrowseComp and Terminal-Bench 2.1.
The editor's rubric
| Dimension | Level | Weight | What that level means |
|---|---|---|---|
| Leverage | ███░░ 3 | 24% | A method or resource many groups across the field will adopt within a year. |
| Magnitude | ██░░░ 2 | 18% | Solid incremental gain on a meaningful problem. |
| Evidence | ██░░░ 2 | 14% | Limited: single setting, weak baselines, or an observational association presented as causal. |
| Novelty | ██░░░ 2 | 16% | A new combination of known ideas. |
| Trajectory | ██░░░ 2 | 18% | Some room to improve with obvious engineering. |
| Stakes | ██░░░ 2 | 10% | Benefits a professional community (practitioners, clinicians, engineers). |
Editor’s rationale
Heuristic triage from title and abstract text only, not a reading of the paper. Cues found: method (we propose); stakes (general AI).
How the score was computed
- Merit
- 3.7 / 10
- Adjusted merit
- 3.9 / 10
- Attention
- 72%
- Freshness
- 35%
- Citations0 (reference 15, via semantic-scholar, Oct 10, 2026, 02:05 UTC)
- Influential citations0 (reference 3, via semantic-scholar, Oct 10, 2026, 02:05 UTC)
- Hugging Face upvotes37 (reference 25, via hf-daily, Oct 11, 2026, 13:49 UTC)
- GitHub stars38 (reference 250, via hf-daily, Oct 11, 2026, 13:49 UTC)