On the Opportunities and Challenges of Prefill-to-Autoregressive Cross-Model Transfer

Zhenyi Shen; Junru Lu; Wei Liu; Jiangnan Ye; Jiazheng Li; Di Yin; Xing Sun; Tameem Adel

cs.CLNov 4, 2026

On the Opportunities and Challenges of Prefill-to-Autoregressive Cross-Model Transfer

Authors: Zhenyi Shen, Junru Lu, Wei Liu, Jiangnan Ye, Jiazheng Li, Di Yin, Xing Sun, Tameem Adel,

Organizations: King’s College London, UK · Tencent Youtu Lab, China · National Physical Laboratory, UK

Abstract

Prefill-to-Autoregressive Cross-model Transfer (PACT), a form of latent communication between language models, combines a larger model's prompt representations with a smaller model's efficient generation, offering a promising way to balance capability and inference cost. However, existing systems provide limited support for independently evaluating large-small model collaboration, and improved task performance alone does not establish whether the receiver benefits from the sender's information. We introduce PLatour, an open-source PACT framework that connects frozen models through lightweight, zero-initialized linear bridges trained directly with task rewards and supports hybrid-attention architectures. PLatour significantly outperforms open-source baselines on generation tasks and surpasses Mostik's reported results on shared mathematics and coding benchmarks using a substantially smaller sender. However, controlled experiments show that the gains on some tasks can be reproduced by uninformative sender signals, self-communication, or receiver-only training. We find that trainable bridges can act as parameter-efficient adaptation mechanisms without exploiting useful sender information. We therefore propose PACT-Check to quantify how much of a trained PACT system's gain genuinely comes from communication. Finally, we discuss the opportunities and challenges of PACT systems. Code is available at https://github.com/zhenyi4/platour.

Figures & tables

Figure 1: Opportunities and challenges of Prefill–to-Autoregressive Cross-model Transfer (PACT). (a) PLatour consistently outperforms the open-source C2C ( Fu et al., 2026 ) across all generation tasks and surpasses the closed-source Mostik on math and coding, despite using a much smaller sender. (b) Superior benchmark performance does not necessarily imply effective information transfer from the sender. PACT-Check examines whether these gains depend on sender information through inference-time interventions and separately trained controls. On Chemistry, PLatour substantially outperforms all four sanity checks, providing evidence of meaningful information transfer. In contrast, on GSM8K, all four checks achieve comparable performance, suggesting that PLatour’s large gain there cannot be attributed to task-specific information from the sender.

Figure 2: Overview of PLatour . During prefilling, independently parameterized, zero-initialized linear projectors

W_{i}

map hidden states from matched sender layers into the receiver’s residual stream via additive fusion. The receiver subsequently generates the response without further sender involvement. Both model backbones remain frozen; only the projectors are optimized using GRPO. Orange dashed arrows schematically illustrate backpropagation through the frozen receiver to the trainable projectors.

Qwen3-235B $\rightarrow$ Qwen3-1.7B
	Answer-Only / Without CoT				Generation / With CoT
Method	ARC-C	MMLU-Redux	Chemistry	Avg.	Chemistry	GSM8K	MATH500	Avg.
Receiver-Alone	74.23	53.96	39.05	55.75	41.43	80.86	73.40	65.23
C2C	92.75	83.68	60.95	79.13	41.01	75.09	64.60	60.23
KV-Lingo	91.21	77.88	40.95	70.01	40.95	17.06	11.95	23.32
PLatour-SFT	95.56	82.90	78.57	85.68	57.80	85.63	70.65	71.36

Table 1: Cross-model communication results (accuracy, %) using Qwen3 senders and a Qwen3-1.7B receiver . Arrows denote sender

\rightarrow

receiver. Avg. denotes the arithmetic mean of the three scores in each group. Bold scores indicate the best PACT result for each sender. TextComm and Sender-Alone are references outside PACT.

		Mathematics (DAPO-17k)					Coding (DeepCoder-24k Clean)
Method	Sender	AIME-80	AIME-135	HMMT	IMO-Ans.	Avg.	LCB v6	HumanEval	MBPP	Avg.
Receiver-Alone	–	59.22	59.12	46.35	41.13	48.90	40.36	83.16	65.08	62.87
PLatour	397B	71.88	72.73	61.77	49.25	60.97	52.50	93.67	85.43	77.20
PLatour	35B	75.63	74.63	64.58	49.75	63.32	54.29	94.97	89.93	79.73
Mostik	753B	–	70.74 ∗	–	–	–	54.14 ∗	86.13 ∗	82.00 ∗	74.09
Sender-Alone	397B	85.86	86.39	82.29	61.06	76.40	63.79	95.43	86.78	82.00

Table 2: Mathematical reasoning and code generation accuracy (%) with a Qwen3.5-4B receiver . Senders are Qwen3.5 models except for Mostik, which uses GLM-5.2 (753B). AIME-80 excludes the 55 problems overlapping with DAPO-17k; AIME-135 is the full set. IMO-Ans. denotes IMO-AnswerBench v2. Math Avg. is the unweighted mean of AIME-80, HMMT, and IMO-Ans.; coding Avg. is the unweighted mean of the three coding benchmarks. DeepCoder-24k Clean is decontaminated against all three coding test sets. Bold scores indicate the best result in each column, excluding Receiver-Alone and Sender-Alone. ∗ Mostik scores are reported results.

Figure 3: Inference efficiency. (a) Prefill latency, measured as time to first token (TTFT), versus input length. (b) Decoding time and (c) total inference time versus output length, with input length fixed at 4K tokens.

Figure 4: PACT-Check results for PLatour and PLatour-SFT . Panels (a)–(c) show Qwen3 results, and panel (d) shows Qwen3.5 domain averages. Each benchmark is normalized independently, with Receiver Alone at 0% and the evaluated PACT system at 100%. Bars show the fraction of the system’s gain reproduced by each control (DT, IT, SC, and TR); darker bars mark the strongest control. Gain and PACT-Score report absolute accuracy differences in percentage points: Gain compares the system with Receiver Alone, while PACT-Score compares it with the strongest control. A positive PACT-Score indicates performance beyond all tested controls, providing evidence for a benefit from sender information. In panel (b), TR uses the better of full-parameter SFT and LoRA-SFT for each benchmark to provide an SFT-matched comparison. MATH500 is marked “no-gain” because PLatour-SFT underperforms Receiver Alone. Per-benchmark accuracies are reported in Tables A20 and A21 .

Gain over Receiver-Alone (pp)
	Answer-Only / Without CoT			Generation / With CoT
Method	ARC-C	MMLU-Redux	Chemistry	Chemistry	GSM8K	MATH500
Sender-Alone gain (235B)	$+22.02$	$+30.95$	$+17.14$	$+16.61$	$+13.49$	$+16.30$
C2C	$+18.52$	$+29.72$	$+21.90$	$-0.42$	$-5.01$	$-5.50$
KV-Lingo	$+16.98$	$+23.92$	$+4.28$	$-0.48$	$-2.51$	$-3.55$
PLatour-SFT	$+21.33$	$+28.94$	$+39.52$	$+16.37$	$+4.77$	$-1.30$

Table 3: Gains over Receiver-Alone and PACT-Scores, both in percentage points (pp), with a Qwen3-1.7B receiver. The first row reports the gain of the strongest standalone sender (Qwen3-235B) over Receiver Alone. For each method and benchmark, we select the sender (235B or 8B) yielding the highest original cross-model accuracy and compute both metrics for that setting. Gain is the selected accuracy minus Receiver-Alone accuracy. PACT-Score subtracts the strongest applicable control among Dummy Transfer (DT), Irrelevant Transfer (IT), Trained Receiver (TR), and Self-Communication (SC), using DT and IT from the selected sender setting and method-matched SC where available. TR uses the better of full-parameter SFT and LoRA-SFT for answer-only tasks, and the better of full-parameter GRPO and LoRA-GRPO for generation tasks, consistently across methods. Positive PACT-Scores indicate performance above all included controls. Unreported results are denoted by –.

Appendix figures & tables23 assets

Supplementary material from the paper’s appendix.

Appendix

Runtime adapter	GSM8K avg@2	Truncation rate
Sample-wise, unpadded	77.29	0.38
Batched, intermediate padding	76.42	0.30
Batched, tail-only padding	77.33	0.23

Appendix

Table A1: Comparison of our C2C runtime adapters with Qwen3-4B

\rightarrow

1.7B on GSM8K. All values are percentages. Runs share the same data, split, layer mapping, three-epoch schedule, batch size of 64, learning rate of

10^{-4}

, and response limit of 2,048 tokens.

Dataset	Train	Holdout	Test
Qwen3
ARC-C	1,107	12	1,172
MMLU	9,900	100	5,632
Chemistry (no-CoT)	1,871	19	210
Chemistry (CoT)	1,871	19	210
GSM8K	7,398	75	1,319

Appendix

Table A2: Data partitions. Qwen3 rows show supervised training splits; Qwen3 GRPO uses the complete source training pools. Qwen3.5 rows show GRPO training splits. DAPO and DeepCoder use the external test benchmarks described in the text.

Method	Sender information	Trainable components	Training objective
Standalone models
Receiver Alone	None	None	—
Sender Alone	—	None	—
Existing communication methods
C2C ( Fu et al., 2026 )	KV caches	Communication modules	SFT
KV-Lingo ( Castin et al., 2026 )	KV caches	Bridge	Linear alignment + KL-based training

Appendix

Table A3: Comparison of baseline methods and PLatour. The table distinguishes the source of information, trainable components, and optimization objectives.

Setting	SFT	KV-Lingo	GRPO
Epochs	3	3	3
Global batch size	64	64	64 / 32
Learning rate	$10^{-4}$	$10^{-4}$	$10^{-5}$
LR schedule	Linear	Cosine	Constant
Warmup ratio	10%	5%	0

Appendix

Table A4: Training hyperparameters. GRPO batch sizes count questions, each with eight sampled responses; Chemistry uses 32 questions per batch.

Task	Decoding	$k$	Token limit
Qwen3
ARC-C (val/test)	Greedy	1	2,048
MMLU (val/test)	Greedy	1	64
Chemistry (no-CoT) (val/test)	Greedy	1	64
Chemistry (CoT) (val/test)	Sampled	8	2,048
GSM8K (val/test)	Sampled	2	2,048

Appendix

Table A5: Evaluation settings.

k

denotes responses per question; token limits apply to individual responses. Rows marked “val” denote evaluations on the validation partitions; reported GRPO checkpoints are selected by mean validation accuracy. AIME includes both the full 135-problem set and the 80-problem subset excluding DAPO overlaps.

Method	2022	2023	2024	2025	2026 I	AIME-135
Receiver-Alone	60.00	57.29	67.92	52.50	56.67	59.12
PLatour (397B)	73.54	73.33	77.92	65.63	73.75	72.73
PLatour (35B)	73.13	72.08	81.25	70.21	78.33	74.63
Full-GRPO	75.83	76.88	82.08	72.08	79.58	77.04
LoRA-GRPO	74.38	73.75	78.96	65.21	77.50	73.56
Self-Communication	73.13	70.21	75.83	68.33	76.67	72.41

Appendix

Table A6: AIME-135 accuracy (%) by year, measured as

\operatorname{avg}@16

. Each of 2022–2025 contains 30 questions (480 responses), while 2026 contains 15 AIME I questions (240 responses). The full-set column pools all 135 questions (2,160 responses) and is not the unweighted mean of the five displayed yearly percentages. All rows use the 32K response limit and the original Qwen3.5 mathematical answer scorer.

Method	2022	2023	2024	2025	2026 I	AIME-80
Receiver-Alone	68.75	59.38	67.92	52.50	53.57	59.22
PLatour (397B)	78.13	70.31	77.92	65.63	71.88	71.88
PLatour (35B)	71.88	71.88	81.25	70.21	76.79	75.63
Full-GRPO	68.75	75.00	82.08	72.08	78.13	76.95
LoRA-GRPO	62.50	76.56	78.96	65.21	75.89	72.73
Self-Communication	62.50	73.44	75.83	68.33	75.00	72.42

Appendix

Table A7: AIME-80 accuracy (%) by year on the fixed, decontaminated subset of AIME-135. The retained question counts for 2022–2026 are 2, 4, 30, 30, and 14 (32, 64, 480, 480, and 224 responses at

k=16

). The last column pools 80 questions (1,280 responses); it is not an equal-weight average of years. In particular, the 2022 and 2023 entries describe only two and four questions, not their complete annual AIME competitions. Scores retain the original 32K generation and answer-equivalence protocol.

	$\operatorname{avg}@16$ (%)			$\operatorname{pass}@16$ (%)
Method	Feb.	Nov.	All 60	Feb.	Nov.	All 60
Receiver-Alone	39.79	52.92	46.35	80.00	83.33	81.67
PLatour (397B)	54.38	69.17	61.77	86.67	90.00	88.33
PLatour (35B)	58.75	70.42	64.58	90.00	90.00	90.00
Full-GRPO	60.63	69.79	65.21	90.00	86.67	88.33
LoRA-GRPO	56.46	62.50	59.48	90.00	86.67	88.33

Appendix

Table A8: HMMT 2025 results by competition, using the same 30 February and 30 November problems for every method. Each competition has 480 responses, so

\operatorname{avg}@16

is the fraction of correct responses and

\operatorname{pass}@16

is the fraction of questions answered correctly at least once; “All 60” pools both competitions rather than treating them as separate benchmarks in the three-test math average. Sender-Alone 397B reaches 82.29%

\operatorname{avg}@16

and 93.33%

\operatorname{pass}@16

locally; the two metrics must not be conflated. For Receiver-Alone and Sender-Alone 35B, only responses previously truncated at 16K were independently regenerated at 32K; their other saved responses were reused. All other rows use the original full 32K test runs.

Sender	Prompt	MATH500	AIME	Tok.
–	Receiver-Alone	85.65	58.61	–
Qwen3.5-35B-A3B	T2T	86.10 (+0.45 [ $-$ 0.85, 1.75])	58.98 (+0.37 [ $-$ 1.81, 2.55])	47–58
	Step-Back	85.75 (+0.10 [ $-$ 1.50, 1.65])	–	138
	Plan	86.15 (+0.50 [ $-$ 1.20, 2.20])	–	134
	Hint	86.05 (+0.40 [ $-$ 1.25, 2.05])	61.48 (+2.87 [ $-$ 0.09, 5.79])	102–265
	Understand	87.30 (+1.65 [0.25, 3.05])	61.76 (+3.15 [0.60, 5.74])	274–299

Appendix

Table A9: TextComm prompt selection via Qwen3.5-4B receiver. Each cell gives avg@

k

, followed by the gain over Receiver-Alone and its 95% confidence interval. Tok. is the average number of message tokens seen by the receiver (MATH500–AIME). Step-Back and Plan are evaluated only on MATH500 with the Qwen3.5-35B-A3B sender.

Sender	Prompt	AIME	HMMT	IMO-Ans.
–	Receiver-Alone	61.25	44.27	38.63
397B	T2T	60.46 ( $-$ 0.79)	46.56 (+2.29)	41.69 (+3.06)
397B	Understand	63.15 (+1.90)	49.06 (+4.79)	42.06 (+3.44)
35B	T2T	61.30 (+0.05)	45.63 (+1.35)	39.88 (+1.25)
35B	Understand	62.92 (+1.67)	46.77 (+2.50)	41.94 (+3.31)
4B	Understand	57.36 ( $-$ 3.89)	43.96 ( $-$ 0.31)	39.63 (+1.00)

Appendix

Table A10: TextComm on the Qwen3.5 math benchmarks via Qwen3.5-4B receiver ( Answer: format, 32K tokens). Gains over Receiver-Alone on the same hardware are in parentheses. IMO-Ans. denotes IMO-AnswerBench v2.

Standalone baselines	Qwen3-4B: 84.60 Qwen3-30B: 88.65 Qwen3.5-4B: 83.30 Qwen3.5-122B: 93.15
Ablation	Variant	Sender $\rightarrow$ Receiver	MATH500
Hidden states or KV caches	Hidden-state transfer	Qwen3-30B $\rightarrow$ Qwen3-4B	88.05
	Hidden-state transfer (no propagate)	Qwen3-30B $\rightarrow$ Qwen3-4B	86.80
	KV-cache transfer	Qwen3-30B $\rightarrow$ Qwen3-4B	86.00
	KV-cache transfer (propagate)	Qwen3-30B $\rightarrow$ Qwen3-4B	85.05
	Original C2C recipe + on-policy	Qwen3-30B $\rightarrow$ Qwen3-4B	86.85

Appendix

Table A11: Ablation studies with training on the MATH dataset and evaluation on MATH500, reporting avg@4. Within each ablation group, all other experimental settings are held fixed. PLatour’s final configurations are bolded.

Qwen3-235B $\rightarrow$ Qwen3-1.7B
		Answer-only			CoT Generation
Method	Layer Matching	ARC-C	MMLU-Redux	Chemistry	Chemistry	GSM8K
PLatour-SFT	Equal-width	89.25	77.22	79.05	50.18	82.52
PLatour-SFT	Last- $n^{\dagger}$	95.56	82.90	78.57	57.80	85.63
PLatour-GRPO	Equal-width †	–	–	–	–	89.35
PLatour-GRPO	Last- $n$	–	–	–	–	86.50

Appendix

Table A12: Layer-matching ablation for PLatour-SFT and PLatour-GRPO with a Qwen3-1.7B receiver. All scores are percentages, with evaluation settings specified in Section B.4 . Unreported results are denoted by –. † marks the configurations used in Table 1 .

	avg@4 (%)
Step	Last- $n$	Relative-depth (full-to-full)
0	83.65	83.25
30	88.60	91.25
59	82.95	89.15
89	89.20	90.00
118	90.75	91.10

Appendix

Table A13: Comparison of last-

n

and relative-depth (full-to-full) layer matching across training steps. All scores are avg@4, reported as percentages.

Method	Projection	Init.	Propagation	Accuracy (%)	Bridge Weight Norm
Receiver alone	–	–	–	80.86	–
C2C	Original	Random	No	75.85	16.61
Linear C2C	Separate K/V	Random	No	75.63	18.48
Linear C2C	Separate K/V	Zero	No	79.87	1.17
Linear C2C	Separate K/V	Zero	Yes	82.22	1.10
Linear C2C	Shared K/V	Random	No	74.68	18.48

Appendix

Table A14: GSM8K avg@2 accuracy with a Qwen3-8B sender and a Qwen3-1.7B receiver, using a 2,048-token response limit. Shared K/V uses the same linear map for keys and values; separate K/V uses independently parameterized maps. Propagation indicates whether lower-layer fused KV caches influence higher-layer ones.

	GRPO step
Initialization	0	30	60	90	120
Zero	84.7	85.6	87.9	87.5	88.1
Random	79.3	82.4	83.7	84.4	85.1

Appendix

Table A15: MATH500 avg@4 accuracy (%) during direct GRPO training with zero and random projector initialization. Step 0 denotes evaluation before training.

Qwen3-235B $\rightarrow$ Qwen3-1.7B
Method / Recipe	ARC-C	MMLU-Redux	Chemistry	Chemistry (Gen)	GSM8K	MATH500
Receiver-Alone	74.23	53.96	39.05	41.43	80.86	73.40
C2C	92.75	83.68	60.95	41.01	75.09	64.60
PLatour-SFT	95.56	82.90	78.57	57.80	85.63	70.65
Original	91.21	77.88	40.95	40.95	17.06	11.95
PLatour Recipe	90.19	77.70	39.05	–	–	–

Appendix

Table A16: KV-Lingo training-recipe ablation on answer-only and generation tasks (accuracy, %). Original denotes KV-Lingo with cosine decay and 5% warmup; PLatour Recipe uses linear decay with 10% warmup. All other KV-Lingo settings remain unchanged. Italicized methods are included as reference baselines. Unreported results are denoted by –.

Method	Supervision Source	Chemistry (CoT)	GSM8K	MATH500
LoRA-SFT	Qwen3-235B	48.10	81.16	70.00
	Qwen3-8B	38.99	81.69	72.55
	Qwen3-1.7B	40.83	81.08	72.05
Full-SFT	Qwen3-235B	51.13	83.59	70.55
	Qwen3-8B	40.65	82.56	73.40
	Qwen3-1.7B	42.62	81.61	71.85

Appendix

Table A17: Fine-tuning results (%) with training responses generated by different Qwen3 models. All variants adapt the Qwen3-1.7B receiver. Bold values indicate the best supervision source within each method and benchmark, corresponding to the variants reported in Table A20 .

Sender $\to$ Receiver	SFT	GRPO	SFT / GRPO
GSM8K
235B $\to$ 1.7B	21.128	2.634	$8.02\times$
8B $\to$ 1.7B	19.132	2.299	$8.32\times$
Chemistry (CoT)
235B $\to$ 1.7B	11.568	1.855	$6.24\times$
8B $\to$ 1.7B	9.400	2.178	$4.32\times$

Appendix

Table A18: Aggregate Frobenius norms of the projection matrices across 28 receiver layers at the final training checkpoints. Each configuration contains 234,881,024 projection parameters.

Step	PLatour-GRPO			LoRA-GRPO
Step	Accuracy	Avg. Length	Clipping	Accuracy	Avg. Length	Clipping
0	73.10%	878	2.30%	73.35%	872	2.45%
59	78.20%	1,275	9.65%	78.20%	1,269	10.50%
118	76.45%	992	5.55%	79.60%	1,433	13.20%
177	0.00%	2,438	59.40%	80.10%	1,486	14.45%
236	0.00%	2,246	54.75%	80.60%	1,505	14.40%

Appendix

Table A19: MATH500 avg@4 accuracy, average response length (tokens), and clipping rate during GRPO training. Clipping denotes responses reaching the 4,096-token generation limit. Both methods use a Qwen3-1.7B receiver; PLatour additionally uses a Qwen3-235B sender.

Figure A1: Training dynamics of PLatour on DAPO. We compare Qwen3.5-397B and Qwen3.5-35B senders paired with a Qwen3.5-4B receiver. Panels show (a) validation accuracy (avg@4), (b) mean response length, (c) the percentage of clipped responses, and (d) mean critic score. For training metrics, faint curves show raw values and solid curves show trailing 10-step means; validation accuracy is shown at evaluated checkpoints. The 397B-sender run exhibits a transient clipping spike around step 180, together with increased response length and a sharp drop in critic score. These training metrics subsequently recover, but validation accuracy remains below its earlier peak.

		Answer-Only / Without CoT				Generation / With CoT
Setting	Method	ARC-C	MMLU-Redux	Chemistry	Avg.	Chemistry	GSM8K	MATH500	Avg.
Receiver-Alone		74.23	53.96	39.05	55.75	41.43	80.86	73.40	65.23
Cross-Model Transfer	PLatour-SFT	95.56	82.90	78.57	85.68	57.80	85.63	70.65	71.36
	PLatour	–	–	–	–	69.29	89.35	78.20	78.95
Dummy Transfer (DT)	PLatour-SFT	75.68	57.90	39.05	57.54	38.04	80.71	70.90	63.22
	PLatour	–	–	–	–	52.44	87.76	78.20	72.80

Appendix

Table A20: Comparison of cross-model communication with control settings (accuracy, %). All settings use a Qwen3-1.7B receiver. Cross-model rows use a Qwen3-235B sender; Self-Communication uses Qwen3-1.7B as both sender and receiver; Virtual Sender uses trainable virtual sender representations. LoRA-SFT reports the best result for each benchmark across the configurations in Table A17 . Avg. denotes the arithmetic mean of the three scores in each group and is reported only when all three scores are available. Underlined scores mark the strongest of Dummy Transfer, Irrelevant Transfer, Trained Receiver, and Self-Communication for PLatour-SFT or PLatour in each column, from which PACT-Score is computed in Table 3 .

Cross-model transfer
	Mathematics (DAPO-17k)					Coding (DeepCoder-24k Clean)
Method	AIME-80	AIME-135	HMMT	IMO-Ans.	Avg.	LCB v6	HumanEval	MBPP	Avg.
Receiver-Alone	59.22	59.12	46.35	41.13	48.90	40.36	83.16	65.08	62.87
PLatour (35B)	75.63	74.63	64.58	49.75	63.32	54.29	94.97	89.93	79.73
Mostik (753B)	–	70.74 ∗	–	–	–	54.14 ∗	86.13 ∗	82.00 ∗	74.09
Controls for PLatour

Appendix

Table A21: Comparison of cross-model communication with control settings (accuracy, %). All settings use a Qwen3.5-4B receiver. Cross-model PLatour uses a Qwen3.5-35B sender; Mostik uses GLM-5.2 (753B) and is shown for comparison. Trained Receiver fine-tunes the receiver with GRPO, either with full parameters or with LoRA. AIME, IMO-Ans., and Avg. are as in Table 2 ; the controls and underlines are as in Table A20 . Our coding experiments use DeepCoder-24k Clean, decontaminated against all three coding test sets. ∗ Mostik scores are reported results.

Qwen3-235B $\rightarrow$ Qwen3-1.7B
		Answer-only			CoT Generation
Method	Inference Setting	ARC-C	MMLU-Redux	Chemistry	Chemistry	GSM8K	MATH500
Receiver alone (1.7B)	Receiver-only	74.23	53.96	39.05	41.43	80.86	73.40
Best trained receiver	Per-task best	81.06	61.54	77.62	65.95	88.53	82.25
PLatour-SFT	Original	95.56	82.90	78.57	57.80	85.63	70.65
	Dummy Transfer	75.68	57.90	39.05	38.04	80.71	70.90

Appendix

Table A22: Original, dummy-transfer, and irrelevant-transfer results (%) with a Qwen3-1.7B receiver. Original denotes standard inference with the trained communication modules. Controls follow Section B.7 . PLatour-GRPO results use the checkpoints selected by mean validation accuracy. DT and IT retain the corresponding original checkpoint without additional training. Unreported values are denoted by –.

Multi-LLM Collaboration

Multi-LLM collaboration studies how large language models share work, exchange information, and combine outputs to improve capability, reliability, or cost.

See all 88 papers

RL Post-Training Diffusion Language Models Along Their Own Generation Paths
Oct 12, 2026Vaibhav Singh, Eugene BelilovskyLanguage Model Post-Training RL for Diffusion Models
Mila, Concordia University
Think Before You Speak: Enabling Training-Free Latent Communication Between Language Models
Oct 12, 2026Rishi KhareMulti-LLM Collaboration LLM Inference Acceleration
Georgia Institute of Technology
Cross-Family Speculative Prefill: Training-Free Long-Context Compression with Small Draft Models
Mar 3, 2026Shubhangi Upasani, Ravi Shanker Raju, Bo Li +5Prompt Compression Long-Context Language Model Inference
SambaNova AI

Oct 12, 2026J/K move · Enter open · S save

RL Post-Training Diffusion Language Models Along Their Own Generation Paths

Vaibhav Singh, Eugene Belilovsky

Mila, Concordia University

Language Model Post-Training RL for Diffusion Models Diffusion Language Models LLM Reasoning

Open paper AskPDF arXiv

Diffusion language models are a promising and more efficient alternative to autoregressive models. However, most RL post-training techniques are not easily adapted to these models. One issue is that diffusion language models generate answers through many intermediate states, deciding at each step which masked positions to reveal and which tokens to place in them. Many existing RL methods used in this setting approximate intractable sequence likelihoods or weight every denoising step by the same advantage, without explicitly distinguishing how these intermediate states of the denoising trajectory affect the expected reward. To address this issue of trajectory blindness, we introduce PACT (Potential-Anchored Consistency of Transitions). Motivated by a reward-tilted reference distribution, PACT jointly learns the policy and a scalar potential that scores each intermediate state, anchored by terminal reward. For each sampled denoising transition, a consistency loss matches the policy-to-reference log-probability ratio of revealed tokens to the change in this potential. This formulation requires neither sequence-likelihood estimation nor importance-ratio clipping. On four tasks, PACT improves LLaDA-8B-Instruct by +9.9 points on GSM8K, +12.0 on MATH500, +55.7 on Countdown, and +72.6 on Sudoku, and reaches the best average accuracy across the four tasks reported for this model, +3.7 points over the next best method. Further compared to AGRPO, it reaches that baseline's best accuracy in about half the training compute on GSM8K.

Abstract

Multi-LLM Collaboration

Explore similar work

RL Post-Training Diffusion Language Models Along Their Own Generation Paths

Think Before You Speak: Enabling Training-Free Latent Communication Between Language Models

Cross-Family Speculative Prefill: Training-Free Long-Context Compression with Small Draft Models