- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
Racer proposes a recoverable KV cache management framework for multi-turn LLM agents. The paper identifies compression-induced trajectory drift, where KV cache compression causes incorrect decisions that propagate through subsequent tool interactions. To address this, Racer selectively preserves important tool definitions and historical context, detects potentially incorrect actions, and restores relevant KV cache information to regenerate decisions before execution. Experiments across six KV compression backends show a 43.7% relative improvement in mean task success on long-context tasks and 1.67× higher throughput compared to full-context execution. The key contribution is making KV cache compression recoverable, improving agent reliability while reducing memory overhead.
Critical strengths
Very interesting direction that recovers compressed KV. Could be important.
Critical weaknesses
- Not enough evaluations on the method... I can see some gain from table 2. But too little results. Table 1 has nothing about your method.
Questions for authors
Can you run your method on more datasets? Idea is interesting but the experiment is way less than desired.
Thank you for your time and feedback. We could have made RACER’s results easier to locate and the two evaluation settings easier to distinguish.
1. RACER results in Table 1
The
+ Racercolumns in Table 1 report RACER’s closed-loop results. For each KV backend,Onlyis compression without RACER,+ Raceris the same backend with RACER, andΔgives the change at the same history budget. The six-backend mean task success rises from 10.5% to 15.1% on BFCL Long Context and from 20.3% to 24.2% on BFCL Base. Table 1 evaluates history compression, while Table 2 separately evaluates tool-definition compression.Original submission — §4.2 and Table 1, pp. 6–7, and §4.4 and Table 2, p. 8.
2. Evaluation beyond BFCL
The original submission also includes a closed-loop evaluation on ToolSandbox scenarios. RACER improves official scenario similarity on four of six KV backends. The Agent-LLM-Traces experiment evaluates a different setting, namely tool-definition compression.
The follow-up experiments extend the BFCL analysis rather than add a dataset. On BFCL Long Context, the gain over compression alone remains +3.2 percentage points after excluding C²KV, with a paired 95% confidence interval of [+1.4, +5.2]. The new component ablation also shows that most of the gain in that setting came from pre-generation history protection.
Original submission — §§4.1–4.2, pp. 6–7, and §4.4, p. 8.