- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper introduces Interaction Aware Compression for Long Horizon Reasoning (ICLR), a training-free technique designed to trim past reasoning tokens in long-horizon LLM agents. Using a frozen secondary model to evaluate the predictive entropy of reasoning blocks, the approach discards the lowest-entropy blocks following each interaction while keeping actions, tool calls, and environment observations intact. Evaluated on WorkBuddyBench with DeepSeek-V4-Flash, ICLR achieves higher task performance alongside a noticeable reduction in memory. Additionally, the authors analyze how pruning reasoning impacts future interaction and examine why historical reasoning becomes redundant once key information is captured externally.
Critical strengths
-
Entropy-driven context compression. While Step Entropy is not a new concept, and it is already used for early stopping of reasoning, this paper extends it to compressing historical reasoning in long-horizon agentic tasks. To my knowledge, this is the first entropy-driven methods for context compression, providing a fresh perspective. The method is simple, training-free, and achieves promising efficiency gains while maintaining competitive task performance.
-
Insightful analysis of reasoning compression in agent interactions. Beyond end-to-end evaluations, the paper provides extensive analyses through trajectory-level ablations, representation probing, activation patching, and controlled state interventions. These experiments offer valuable insights into how reasoning deletion affects future agent behavior and why historical reasoning becomes less necessary once task-relevant information is externalized.
Critical weaknesses
-
Limited evaluation across benchmarks and models. The experiments are restricted to a single benchmark (WorkBuddyBench) and a single acting model (DeepSeek-V4-Flash). Although the benchmark covers four domains, evaluations on additional long-horizon agent benchmarks and different model families would provide stronger evidence of generalizability.
-
Limited analysis of entropy scorer robustness. The method relies on a single frozen Qwen3.5-9B model to estimate reasoning-block entropy. Since entropy estimates can vary across models, evaluating different scorer sizes and model families would help establish whether the proposed compression strategy is robust to the choice of scorer.
Questions for authors
I am more than happy to increase my score weak accept/clear accept if the following questions could be addressed.
-
Generalization: How effectively does ICLR perform when applied to alternative agent models and different long-horizon benchmarks?
-
Scorer Robustness: How sensitive is the framework to the model chosen as the entropy scorer? Could you try other scorers?
4 comments
Scorer Sensitivity and Responses to the Two Questions
W2: Analysis of entropy Scorer robustness is limited.
The method relies on a single frozen Qwen3.5-9B model to estimate reasoning-block entropy. Since entropy estimates can vary across models, evaluating different scorer sizes and model families would help establish whether the proposed compression strategy is robust to the choice of scorer.
Thank you very much for this important suggestion. We compare four entropy Scorers across the Qwen and Llama model families, covering different sizes and checkpoints.
We fix DeepSeek-V4-Flash as the acting model and retain the same Full260 task list, 80% Block deletion rule, and evaluation protocol. This sensitivity analysis uses the same Full260 Base reference; each Scorer configuration's ICLR result is calculated from its corresponding run records, separately from the main three-seed experiment.
| Scorer backbone | N | Base Overall | ICLR Overall | Base Actor Tokens/task | ICLR Actor Tokens/task | Scorer Tokens/task |
|---|---|---|---|---|---|---|
| Qwen3.5-4B | 260 | 0.7451 | 0.7219 | 2,558.2k | 1,918.5k | 185.3k |
| Qwen3.5-9B | 260 | 0.7451 | 0.7372 | 2,558.2k | 2,082.2k | 191.3k |
| Llama-3.2-3B | 260 | 0.7451 | 0.7123 | 2,558.2k | 2,152.1k | 171.9k |
| Llama-3.1-8B | 260 | 0.7451 | 0.7333 | 2,558.2k | 2,173.8k | 221.4k |
All four configurations reduce Actor token usage, but their Rewards in this sensitivity batch are below the Base reference. Within each family's comparison, the larger Scorer achieves higher Reward alongside increased Actor and Scorer token processing.
These results show that Scorer size and checkpoint affect downstream performance and resource usage. We will explicitly report this sensitivity rather than treat different Scorers as interchangeable without performance loss. We sincerely appreciate your suggestion, which helped us characterize the quality-cost trade-off in Scorer selection more accurately.
Q1: How effectively does ICLR perform on alternative agent models and different long-horizon benchmarks?
Thank you very much for your attention to generalization and your specific suggestions. In our response to W1, we report the additional cross-benchmark and cross-actor evaluations, together with Actor usage and local Scorer overhead. Please see the corresponding tables for the detailed results.
The supplementary results show that ICLR can be applied to different task environments and acting models, with quality and usage benefits varying by setting. The revision will present each result separately and clarify the method's scope. We sincerely appreciate your professional guidance, which helped us expand the evaluation and support our conclusions more fully and accurately.
Q2: How sensitive is the framework to the entropy Scorer model? Could you try other Scorers?
Yes. We compare Qwen3.5-4B, Qwen3.5-9B, Llama-3.2-3B, and Llama-3.1-8B with the acting model, task list, and deletion rule fixed.
These results show that entropy scoring can operate across two model families, but downstream quality and resource usage are sensitive to Scorer choice. In this batch, the larger Scorer within each family achieves higher Reward than the smaller version, with increased token processing. We therefore report these as a sensitivity analysis, explicitly showing quality and cost changes for each configuration and qualifying the Scorer-robustness conclusion.
We sincerely thank you again for recognizing the method design and mechanistic analysis, and for proposing these specific, professional experimental directions. Your suggestions helped us expand the evaluation and better understand the benefits and limitations across task environments, acting models, and Scorer configurations.
We are deeply grateful for the valuable time, professional judgment, and care you have devoted to understanding and improving this work, and wish you a fulfilling, enjoyable, and intellectually stimulating academic exchange at this year's ICLR.
Response to rebuttal
Many thanks to the authors for their detailed rebuttal. I am satisfied with their responses, particularly regarding the following points:
- Generalization: The authors provide additional evaluations on new benchmarks, including -Bench and Terminal-Bench v2.0, as well as experiments with other actor models.
- Scorer Robustness: The authors conduct further evaluations using diverse entropy scorers to assess the sensitivity of their method to scorer choice.
I am therefore raising my score from 2 to 3 as promised. I am not assigning a 4 because, the work is more a clever adaptation of existing concepts (step entropy + ACON). Good luck!
Thank you very much for your feedback! We greatly appreciate your encouragement and recognition. Wish you all the best!
Cross-Benchmark and Cross-Actor Evaluation
Dear Reviewer,
We sincerely thank you for the valuable time and effort devoted to this careful, professional review. We especially appreciate your recognition of entropy-driven historical reasoning compression, the training-free design, and the trajectory ablations, representation probes, activation patching, and externalization analysis. Your positive assessment is very encouraging.
Your suggestions on additional benchmarks, acting models, and Scorer robustness provided clear guidance for examining the method's scope. We report results from three external benchmarks, three acting models, and four Scorers below.
W1: Evaluation across benchmarks and acting models is limited.
Thank you for identifying this limitation. We report runs on τ-bench, Terminal-Bench 2.0, and SWE-bench Verified, together with additional acting models. Evaluation batches are reported separately.
1. Cross-benchmark evaluation
Tokens are per-task averages; k denotes 1,000 tokens.
Both Base and ICLR use the native TauICLRAgent on τ-bench.
These results extend evaluation beyond WorkBuddyBench, but benefits vary: Terminal-Bench and SWE-bench show higher Reward and lower Actor token usage; τ-bench shows lower Actor token usage alongside lower Reward. We report quality and resource usage separately rather than claim improvements on every benchmark.
Local Scorer workload
Terminal has one recovery/acceptance-layer timing record, and SWE has four recovery timing records; these are listed separately as recovery-process records. Overall Runner timings are reported using each benchmark's valid task count, separately from Scorer CUDA timing.
2. Cross-actor evaluation
We additionally evaluate Qwen3.8-Flash, HY-3, and GPT-5.6-Luna on Full260.
Qwen3.8-Flash and HY-3 show slightly higher mean Reward and lower Actor token usage. GPT-5.6-Luna has unchanged mean Reward but increased Actor token usage.
These results expand the range of acting models while showing that benefits depend on the actor. The revision will report these differences fully and restrict generalization claims to the evaluated models and environments.