- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes HACE, a heterogeneous coevolution framework that jointly improves a specialized foundation model, an LLM agent, and their interaction harness. The agent is trained from verified improvements over the current specialist, while its exploration guides which examples are used to further train the specialist. An evolutionary search procedure additionally adapts the harness. Experiments on recommendation, protein function prediction, and crystal stability prediction show consistent improvements over several self-improving baselines.
Critical strengths
-
The reciprocal-learning formulation is interesting and timely. Unlike fixed teacher-student approaches, both the specialist and agent adapt to each other, while the interaction harness also evolves.
-
The empirical evaluation is broad, covering three domains, multiple specialist architectures, ablations, and scaling experiments. The gains on protein function prediction are particularly strong.
Critical weaknesses
-
The main results evaluate the fused specialist+agent system rather than clearly showing that the specialist itself improves. Since the paper’s central claim concerns improving specialized foundation models beyond convergence, specialist-only results after coevolution are important.
-
The fairness of the baseline comparison is unclear. HACE uses LLM sampling, specialist training, agent training, and repeated harness search, but the paper does not clearly describe whether ReST-EM, Meta-Harness, OpenEvolve, DGM, and TTT-Discover receive comparable generation, training, validation, and compute budgets.
Questions for authors
-
Can the authors report the final performance of the HACE-trained specialist alone, without agent fusion, on all three domains?
-
How are the computational and search budgets matched across HACE and all baselines, including LLM generations, gradient updates, validation evaluations, and total compute?
-
Since the same validation set is repeatedly used for selection over many rounds, have the authors evaluated possible adaptive overfitting to the validation set?
4 comments
Response to Reviewer 2RVp (Part 2/2)
W2/Q2. Computational and Search Budgets
On CAFA, HACE keeps its advantage when all methods are compared at the same wall-clock time, and we report each method's budget per run. In the CAFA runs of Table 2, all methods run the same number of rounds on the same rollout, validation and test blocks, and every run uses one NVIDIA B200 GPU, so its wall-clock time is also its GPU time. For gradient updates, HACE, ReST-EM and TTT-Discover train the agent on a comparable number of examples, while Meta-Harness, OpenEvolve and DGM search over harnesses without agent updates. HACE also trains the specialist and tests each specialist update against the incumbent, so it runs more validation scorings in each round than the baselines. The wall-clock time counts these scorings together with every LLM generation and gradient update of each method. The tables below give the NDCG each method reaches within a fixed wall-clock time, together with its budget per run, for both protein backbones and averaged over three seeds.
| CAFA / ESM-2 650M, 50 rounds | HACE | ReST-EM | TTT-Discover | Meta-Harness | OpenEvolve | DGM |
|---|---|---|---|---|---|---|
| NDCG within 4 h | 0.6745 | 0.6286 | 0.6287 | 0.6309 | 0.6313 | 0.6324 |
| NDCG, full run | 0.6745 | 0.6286 | 0.6287 | 0.6309 | 0.6320 | 0.6325 |
| Agent training examples w/ replay | 12,196 | 10,506 | 11,841 | - | - | - |
| Wall-clock per run (h) | 10.7 | 4.3 | 4.3 | 5.0 | 4.4 | 4.4 |
| CAFA / ProtT5-XL, 30 rounds | HACE | ReST-EM | TTT-Discover | Meta-Harness | OpenEvolve | DGM |
|---|---|---|---|---|---|---|
| NDCG within 2.5 h | 0.6733 | 0.6242 | 0.6241 | 0.6261 | 0.6254 | 0.6252 |
| NDCG, full run | 0.6739 | 0.6242 | 0.6241 | 0.6261 | 0.6254 | 0.6273 |
| Agent training examples w/ replay | 6,868 | 5,263 | 6,729 | - | - | - |
| Wall-clock per run (h) | 6.4 | 2.6 | 2.6 | 2.8 | 2.8 | 2.9 |
With both backbones, HACE exceeds the highest full-run score of any baseline within a time that is shorter than every baseline's full run. Between four hours and the end of their runs, the ESM-2 baselines gain at most 0.0007 NDCG, while HACE leads the strongest of them by 0.0420. The revised PDF adds these tables as App. C.6.
Q3. Possible Adaptive Overfitting to the Validation Set
We check for adaptive overfitting to the validation set with a held-out test block. In all three domains, this block is disjoint from the rollout and validation blocks and never enters an accept or reject decision. In the CAFA runs of Table 2, HACE stays above every baseline on this block at the final round, in every seed and with both backbones, after 30 to 50 rounds of selection on the validation pool. Within that pool, each proposal is compared with the incumbent on a fresh random draw in every round, and the incumbent is re-scored on that draw. Both states in each decision therefore see the same examples, and no decision reuses a score from an earlier draw. The revised App. C.3 describes the paired acceptance test.
We hope these results address your concerns, and we would be happy to provide any further clarification.
Dear Reviewer 2RVp,
Thank you again for your constructive comments. As the discussion phase ends in one day (November 18), we would like to ask whether our responses have addressed your concerns. If there are any remaining questions, we would be happy to respond.
If you find our responses satisfactory, we would appreciate your consideration in updating the evaluation.
Sincerely,
Authors
Thank you for the detailed rebuttal and additional experiments. The specialist-only results and computational comparisons have adequately addressed my original concerns.
I still have some reservations about the unique contribution of reciprocal coevolution. On CAFA, SFT with an acceptance test nearly matches full HACE (0.6737 vs. 0.6745), while decoupled training achieves comparable performance on Toys (0.0707 vs. 0.0692). These results suggest that the benefits of reciprocal coupling remain somewhat unclear.
Nevertheless, I appreciate the authors' thorough responses, the broad experimental evaluation, and the demonstrated improvements of the specialist models. Considering the additional evidence, I am updating my rating from 2 to 3.
Response to Reviewer 2RVp (Part 1/2)
We sincerely thank Reviewer 2RVp for recognizing the interesting and timely reciprocal-learning formulation, the broad evaluation across three domains with multiple specialist architectures, ablations and scaling experiments, and the particularly strong gains on protein function prediction.
W1/Q1. Specialist-Only Performance after Coevolution
The specialist itself improves after coevolution in all three domains, without agent fusion. As the reviewer noted, our central claim is that a specialized foundation model can improve beyond convergence, so the specialist alone is its most direct test. Base is already trained to convergence, in the sense that three more epochs of its original supervised schedule change the reported metric by less than 0.001 in every domain (App. C.3). To further address the reviewer's concern, we show the HACE-trained specialist alone (fusion weight λ=0) next to the initial specialist in each domain, averaged over three seeds.
The recommendation values come from our 20-round Toys runs, which also score the specialist alone in every round, on 2,000 held-out test users that differ from the users in Table 1. On these users, the specialist improves in every seed, and the fused system reaches 0.0692, so in recommendation the agent's ranking adds further gains on top of the improved specialist. The protein values come from new runs of the Table 2 configurations that also score the specialist alone, evaluated on the same test blocks and seeds in the same way as Table 2. With 95% confidence intervals over the paired seeds, the specialist gains +0.0456 [+0.0431, +0.0480] NDCG with ESM-2 and +0.0501 [+0.0433, +0.0570] with ProtT5-XL.
On CAFA, the specialist alone comes close to the fused HACE system with both backbones, for example 0.6726 against 0.6745 NDCG with ESM-2. It also scores above every baseline in Table 2, all of which fuse their agent's ranking with the specialist and reach at most 0.6325 with ESM-2 and 0.6273 with ProtT5-XL. The improved specialist can therefore be deployed on its own there, without the agent at inference time.
For crystal stability, Table 6 already reports the specialist alone for every method, because F1, the discovery acceleration factor (DAF), MAE and R2 are computed from the energy predictions of each method's specialist, and the agent enters only the NDCG ranking. In our WBM setup, every method refits the same residual energy head, so these metrics compare how each method trains the specialist. With the same refit, the baselines reach a DAF of at most 2.203 and an MAE of at least 0.0748, and the specialist trained inside HACE has the best value on all four metrics. Compared with Base, it raises DAF from 1.644 to 2.242. Its MAE also falls from 0.1049 to 0.0729, so the energy predictions themselves become more accurate.
The revised Sec. 4.1 also states the specialist-alone gain in the main text, and the revised PDF adds this table as App. C.4.