- Rating
- 3
- Confidence
- 2
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes Trace, a framework that converts noisy, sparse-reward agent trajectories into executable, reusable memories for long-horizon LLM agents. Trace combines three key components: (1) progress anchoring and delayed credit assignment to identify useful actions, (2) prerequisite estimation to infer dependencies between actions and environmental states, and (3) backward dependency slicing to compile relevant actions into structured walkthroughs. A state-aware scheduler then selects and executes these walkthroughs across episodes using a frozen LLM actor. Experiments on WebShop, J-TTL, and ScienceWorld with three LLM backbones report average relative improvements of 30.9% in AUC and 41.6% in Final-3 performance over the strongest baselines. Ablation and robustness studies further examine the contributions of individual components and their resilience to noisy trajectories and execution perturbations.
Critical strengths
The overall research problem is the online learning ability of the agent, which is very important. The experiments have been done are very sufficient.
Critical weaknesses
- There is a little concern about the effect, which is written in the question.
- The baseline methods, or the cited paper, is not officially implemented on the three benchmarks used in this paper. That is to say, the author himself re-adapted the methods of other papers on the benchmark they chose. There is no evidence that they reproduce successfully, and each paper is targeted on the benchmark of their choice, which means that the results are not very credible.
- The description of the paper, including the drawing of the chart. It seems that llm participates too much, which is not a problem, but the table and chart contain too many numbers or information, which is easy to make human readers lack focus.
Questions for authors
I need the following results to consider improving my score.
- On the benchmark used in the baseline paper, the fair comparison under the same model and setting
- The result of trace when the number of episodes is k, compared with the results of best-of-k and pass@k