- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper introduces Agent-Radar, a training-free method for helping LLM agents use relevant information in accumulated communication histories. It selects sentences based on semantic similarity to the current query, weighted by message age and the graph distance between the source and receiving agents. The selected context is then emphasized using an existing attention-steering method while retaining the full history. Experiments across five benchmarks, multiple multi-agent frameworks, and different communication topologies show consistent improvements.
Critical strengths
-
The empirical evaluation is fairly thorough. Agent-Radar improves performance across five benchmarks and three multi-agent frameworks, with additional experiments on different topologies and backbone models.
-
The method is simple and the ablations help explain its benefits. The paper compares against semantic-only retrieval, random steering, alternative retrievers, and a prompt-only retrieval variant, and separately removes spatial and temporal decay. Together, these experiments provide useful evidence that both context selection and steering contribute to performance. The method also preserves the existing workflow and does not require model training.
Critical weaknesses
-
The methodological contribution is relatively modest. The steering mechanism is inherited from SPA, while the main addition is a sentence-selection score combining semantic similarity with spatial and temporal decay. The results support the usefulness of this combination, but the paper should distinguish its contribution to automatic context selection more clearly from advances in attention steering itself.
-
The assumptions behind the decay factors are not directly tested. Recent messages and nearby agents may often be useful, but important evidence can also come from an earlier round or a distant specialist. This is particularly relevant when the communication graph is randomly constructed, since graph distance need not reflect information quality. The component ablation demonstrate average benefits, but do not establish when these preferences help or suppress useful evidence.
Questions for authors
-
How does Agent-Radar behave when decisive evidence appears in an older message or comes from a distant agent, while recent or nearby messages contain incorrect reasoning? A controlled experiment would help establish the limits of the decay assumptions.
-
In the spatial and temporal ablations, does removing a decay factor substantially change the number of selected sentences? A comparison with the selection count held fixed would help separate the benefit of the relevance ranking from changes in how much context is emphasized.
-
Can you clarify whether the prompt-token accounting in the efficiency analysis includes the masked-input computation used by SPA? A breakdown of retrieval and steering latency, together with the context lengths used, would make the reported overhead easier to interpret.
3 comments
Response to Reviewer 31M5 (2/2)
Q2 In the spatial and temporal ablations, does removing a decay factor substantially change the number of selected sentences?
Thank you for pointing this out. We would like to clarify that the "removing decay" ablations in Table 5 already hold the selection count fixed to isolate the benefit of the relevance ranking. As mentioned in Line 993, removing a decay factor will change the number of sentences receiving attention steering. To isolate each decay contribution, we match the steering budget to the full AGENT-RADAR method. Specifically, if Agent-Radar steers historical sentences, each ablation steers its top- sentences under the ablated scoring function. We have added a footnote on page 8 to make this experimental control more explicit.
Q3 Clarify the latency overhead breakdown
Thank you for this comment. We break down the end-to-end latency (seconds per task) into the table below:
| Component | Base MAS | Agent-Radar |
|---|---|---|
| Sentence retrieval | – | 1.2 |
| Masked forward pass of SPA | – | 305.1 |
| Decoding | 968.8 | 890.2 |
| Total | 968.8 | 1196.5 |
Sentence retrieval only takes 1.2 seconds. The overhead comes from the masked forward pass of SPA and decoding. We have added this breakdown in the revised paper(Appendix A.8).
Thank you for the rebuttal
Thank you for the clarifications and additional results. The fixed selection count addresses my concern, and the latency breakdown is helpful. I would like to maintain my positive rating.
Response to Reviewer 31M5 (1/2)
Dear Reviewer 31M5,
Thank you for the careful review. We address each point below.
Thank you for this comment. We would like to clarify that SPA [1] requires users to manually specify which input tokens the model should attend to. In the original SPA experiments, the steered context is selected by human and fixed in advance. Given the complexity of multi-agent systems, the communication history is long and changes at every step, so it is hard to decide manually which parts to steer attention to.
By contrast, Agent-Radar automatically identifies the relevant context in the multi-agent conversation history. More importantly, Agent-Radar is agnostic to the steering method. We have conducted an experiment in Appendix A.5 replacing SPA with PASTA and show the same trend. We have updated the manuscript to clarify this point (Lines 49–52).
[1] Tian, Yuan, and Tianyi Zhang. "Selective prompt anchoring for code generation." ICML 2025.
[2] Zhang, Qingru, et al. "Tell your model where to attend: Post-hoc attention steering for llms." ICLR 2024.
Thank you for raising this question. First, we would like to clarify that our use of randomly constructed communication topologies follows established prior work on the same topic, including AgentPrune [1] (ICLR 2025) and AgentDropout [2] (ACL 2025). Both studies investigate communication efficiency in multi-agent systems and adopt random communication topologies in their evaluations. Our experimental setup follows these established practices to ensure consistency and comparability with prior research.
To further investigate the concern about important information originating from earlier messages or more distant agents, we manually inspected 100 randomly sampled tasks. We found that only 9% of the tasks contained critical information exclusively in earlier messages or messages from more distant agents, without being restated in subsequent communication.
To understand how Agent-Radar behaves in these cases, we compare it with the original multi-agent system without steering and Agent-Radar with only semantic-based steering (no decay). We evaluated all three methods on both the 9 edge cases and the full set of 100 tasks across three runs.
As expected, semantic-based steering performs best on the 9 edge cases (6.7 correct answers on average), as it can directly steer attention toward relevant information regardless of its temporal or spatial distance. However, it does not achieve the best overall performance across all 100 tasks, since relying solely on semantic similarity without considering recency and spatial relationship may introduce indirect noise, redundant context, or outdated information. Agent-Radar achieves the highest overall performance (70.3 correct answers on average, compared with 64.0 for semantic-based steering). Although Agent-Radar does not explicitly steer attention toward the distant critical information in the 9 edge cases, that information remains in the context window. Moreover, Agent-Radar still outperforms the original multi-agent system on the 9 edge cases (6.0 versus 3.3 correct answers on average), potentially because it explicitly steers attention toward the original question (Lines 211-212), preventing the task objective from being buried in the conversation history. We have added this analysis and discussion to Appendix C.
[1] Zhang, Guibin, et al. "Cut the crap: An economical communication pipeline for llm-based multi-agent systems." ICLR 2025.
[2] Wang, Zhexuan, et al. "Agentdropout: Dynamic agent elimination for token-efficient and high-performance llm-based multi-agent collaboration." ACL 2025.