CoEM: Empowering Long-Context Reasoning with Commit-on-Evidence Memory

Jingguang Li; Yebo Wu; Zuyi Guo; Kailang Ma; Xianjie Dai; Han Zheng; Benwang Chen; Li Li

cs.AISep 29, 2026

CoEM: Empowering Long-Context Reasoning with Commit-on-Evidence Memory

Authors: Jingguang Li, Yebo Wu, Zuyi Guo, Kailang Ma, Xianjie Dai, Han Zheng, Benwang Chen, Li Li, +2 more

Organizations: Korea Advanced Institute of Science & Technology · University of Macau · Massachusetts Institute of Technology

Abstract

Long-context reasoning is essential for complex and long-horizon tasks, yet the performance of large language models (LLMs) degrades as context length increases. Recent approaches address this by processing input chunk by chunk while maintaining a bounded textual memory in model context. However, premature information compression can discard critical details essential for subsequent reasoning. In this paper, we introduce Commit-on-Evidence Memory (CoEM), which learns when to convert source evidence into compact memory facts. Specifically, under a fixed context-memory budget, CoEM preserves potentially useful source excerpts verbatim in a pending set, allowing subsequent context to clarify their relevance before irreversible compression. As new context arrives, a learned policy revisits each pending excerpt and decides whether to promote it to the committed memory, retain it for further consideration, or discard it. A frozen verifier ensures proposed facts are accepted only if supported by retained excerpts and current context. To further guide effective memory management, we train this policy using reinforcement learning by combining fine-grained, step-level evidence rewards with final answer rewards. Extensive experiments demonstrate that CoEM consistently improves long-context reasoning. When evaluated on 6,400 documents long-context input, CoEM outperforms the strongest memory baseline by 10.4-11.4 F1 points on Qwen3.5-9B. Code repository: https://github.com/benmagnifico/CoEM.

Figures & tables

Figure 1: Methodology comparison of CoEM and two baselines on a HotpotQA question ( Yang et al., 2018 ) . CoEM does not make a decision about the unclear source evidence until its value is clarified by the later evidence.

Figure 2: Memory occupancy of different methods throughout reading procedure on HotpotQA.

Figure 3: Overview of CoEM . At intermediate steps $t<T$ , the policy promotes, keeps, or drops evidence. A frozen verifier checks proposed facts before commitment. At the final step $T$ , remaining pending evidence is resolved before the model answers from committed memory.

Figure 4: RL Training with step-level evidence rewards. Grouped rollouts combine final answer rewards with evidence return-to-go, carrying later source-verification feedback to earlier memory decisions. Group-centered advantages drive the clipped policy update.

Figure 5: Analysis of evidence retention, source verification, and inference efficiency with Qwen3.5-4B. In (a), Capacity events occur when admitting new evidence would exceed the pending-set budget. In (b), Forced drops discard the oldest pending evidence to free space. In (e), Self is the 4B policy self-check, Raw/Cal. are the raw/calibrated DeBERTaV3-small verifiers, and 9B is Qwen3.5-9B; the blue line uses the right axis. In (f), MA, GM, RR † , and RN denote MemAgent, GRU-Mem, budget-matched ReMemR1, and native ReMemR1.

Variant	HotpotQA		2Wiki.
	F1 $\uparrow$	Faith. $\uparrow$	F1 $\uparrow$	Faith. $\uparrow$
No RL	67.5	93.2	55.1	92.7
Eager, no verifier	73.4	85.2	61.8	84.7
Eager + verifier	77.2	95.7	66.0	95.2
Pending, no verifier	81.5	86.7	71.3	86.2
Outcome-only RL	80.4	94.4	69.9	93.9

Table 2: Ablation analysis of CoEM . Faith. is the percentage of accepted facts supported by their cited sources.

Appendix figures & tables18 assets

Supplementary material from the paper’s appendix.

Appendix

Setting	Value
Policy / verifier precision	bfloat16 / float32 logits for calibration
Chunk / total context memory	$C=5{,}000$ / $B=1{,}024$ tokens
Pending / committed allocations	$B_{P}=256$ / $B_{M}=768$ tokens
Question / instruction and feedback reserve	$L_{q}=256$ / 1,912 tokens
Input / controller output / final output	8,192 / $W_{\pi}=1{,}024$ / $W_{\rm ans}=256$ tokens
Total serving window	9,216 tokens (input plus output)

Appendix

Table 3: Policy, controller, training, and evaluation settings.

Model	Dataset	ReMemR1 †	ReMemR1 (native)	CoEM
Qwen3.5-4B	HotpotQA	81.2	83.4	85.7
Qwen3.5-4B	2Wiki	70.9	73.0	76.4
Qwen3.5-4B	MuSiQue	61.4	63.3	67.0
Qwen3.5-9B	HotpotQA	84.2	86.4	89.6
Qwen3.5-9B	2Wiki	75.6	78.0	81.9
Qwen3.5-9B	MuSiQue	67.2	69.3	73.6

Appendix

Table 4: Length-averaged F1 (%). Native ReMemR1 retains historical snapshots outside the 1,024-token budget and is reported separately from the matched-storage comparison.

Configuration	ECE (%) $\downarrow$	NLL $\downarrow$	Brier ( $\times 100$ ) $\downarrow$
Raw	7.10	0.52	8.00
Temperature scaling	3.20	0.49	7.40

Appendix

Table 5: Held-out calibration metrics. ECE uses ten equal-width bins; lower values are better.

Verifier	Faith. $\uparrow$	FAR $\downarrow$	FRR $\downarrow$	ms/pair $\downarrow$
No verification	64.0	100.0	0.0	0.0
Policy self-check (Qwen3.5-4B)	89.8	18.5	8.3	165.0
DeBERTaV3-small, raw	94.9	9.2	3.9	4.2
DeBERTaV3-small, calibrated	97.2	4.9	6.4	4.3
Qwen3.5-9B verifier	97.5	4.3	5.8	295.0

Appendix

Table 6: Independent audit of source-support verifiers on the same blinded set of 2,000 pre-verification promotion attempts. Faithfulness measures source support among accepted claims; FAR and FRR measure unsupported claims accepted and supported claims rejected, respectively. Latency is measured per source–claim pair on one H800 with batch size one.

Figure 6: Context-memory occupancy during the Qwen3.5-4B HotpotQA experiment with 6,400 documents and 128 chunks. The shaded band shows pending source text above committed memory; both components contribute to CoEM ’s total retained context memory. This enlarged view uses the same experimental trace as Figure 2 .

2Wiki condition	Mean / P95 tokens	Capacity events	Forced drops	Overflow
Ordinary ordering	142 / 223	2.8%	0.5%	0.0%
Gap 128	183 / 246	6.2%	1.8%	0.0%
Source-dense stress	224 / 254	19.7%	7.6%	0.0%

Appendix

Table 7: Pending-set stress diagnostics for Qwen3.5-4B on 2WikiMultiHopQA with 6,400 documents and

B_{P}=256

. Mean / P95 tokens report the mean and 95th-percentile occupancy of

P

. The capacity-event rate is the fraction of eligible admissions that require freeing space; the forced-drop rate counts evicted resident pending records per admitted record; overflow denotes token-budget violations.

Method	800 docs	1,600 docs	3,200 docs	6,400 docs
MemAgent	84	171	351	720
GRU-Mem	55	112	231	474
ReMemR1 †	102	207	425	870
ReMemR1 (native)	108	221	459	951
CoEM	63	130	267	548

Appendix

Table 8: End-to-end latency (s/question) for the Qwen3.5-4B policies on one H800. Full-scan timing includes all controller operations, verification, memory callback, and final-answer generation.

Figure 7: Training diagnostics for Qwen3.5-4B. (a) Training answer F1. (b) Development answer F1, evaluated every 25 updates; stars mark the maxima of the mean curves, rather than the checkpoints selected separately for each run. (c) Verifier-rejection rate among proposals passing all non-entailment checks. (d) Invalid-operation rate among all proposal attempts. Lines show three-seed means and shaded bands show one sample standard deviation across policy seeds.

Figure 8: Memory decisions during training. (a) Step-level evidence reward. (b) Fact proposals checked by the verifier. (c) Proposals passing verification. (d) Voluntary Drop actions. Panels (b)–(d) report counts per reading chunk. Lines show three-seed means and shaded bands show one sample standard deviation across policy seeds. Passing verification does not imply that the corresponding atomic transaction is committed. Evidence rewards for Outcome-only RL are logged but do not affect its updates.

Setting	Comparator	CoEM	Comparator	$\Delta$ [95% CI]
4B / HotpotQA / 800	Outcome-only RL	$85.5\pm 0.46$	$80.4\pm 0.85$	5.1 [3.3, 7.0]
4B / 2Wiki / 800	Outcome-only RL	$76.1\pm 0.56$	$69.9\pm 0.85$	6.2 [4.3, 8.2]
9B / HotpotQA / 6,400	ReMemR1 †	$89.1\pm 0.40$	$78.7\pm 0.75$	10.4 [7.6, 13.4]
9B / 2Wiki / 6,400	ReMemR1 †	$81.0\pm 0.56$	$69.6\pm 0.75$	11.4 [8.7, 14.3]
9B / MuSiQue / 6,400	ReMemR1 †	$72.3\pm 0.66$	$61.6\pm 0.85$	10.7 [8.2, 13.4]

Appendix

Table 9: Uncertainty summaries for key comparisons. Settings list backbone / dataset / number of documents. F1 entries are mean

\pm

SD over policy seeds 17, 29, and 43;

\Delta

is CoEM minus comparator F1. Each setting contains 128 paired questions, and the 95% interval for

\Delta

uses 10,000 question-level bootstrap resamples that preserve method and seed pairing.

\dagger

denotes budget-matched ReMemR1.

Figure 9: Supporting-evidence diagnostics for Qwen3.5-4B on HotpotQA. (a) Recoverable supporting relations at 32 normalized reading positions, before final resolution. (b) Pending-source survival immediately before bridge arrival under the existing gap intervention; labeled gap settings are equally spaced. (c) Commitment timing or removal for initially admitted records containing supporting evidence at gap 32. Within 1 step denotes commitment at the bridge step or the following step. Shaded bands in (a) and (b) show one sample standard deviation across policy seeds; panel (c) reports pooled record proportions.

Training objective	$\alpha$	Evidence reward	HotpotQA F1	2Wiki F1
Outcome-only RL	1.0	None	$80.4\pm 0.85$	$69.9\pm 0.85$
Matched $\alpha$ , no evidence	0.8	None	$81.0\pm 0.70$	$70.5\pm 0.80$
Immediate evidence reward	0.8	Current chunk	$83.1\pm 0.60$	$73.2\pm 0.70$
Full CoEM	0.8	Return-to-go	$85.5\pm 0.46$	$76.1\pm 0.56$

Appendix

Table 10: Reward controls with Qwen3.5-4B at 800 documents (mean

\pm

SD over three seeds).

\alpha

is the answer-advantage weight; matched controls fix

\alpha=0.8

and the KL coefficient at

10^{-3}

, and both evidence variants share the same

1/T

scaling and penalty weights.

Policy	GPUs/run	Hours/run	GPU-h/run	GPU-h/3 seeds
Qwen3.5-4B	8	18.0	144	432
Qwen3.5-9B	8	42.0	336	1,008
Total for the six runs	—	—	—	1,440

Appendix

Table 11: Training resources for CoEM on nodes with eight H800 GPUs.

Resource or operation	Value
Regular / additional / answer policy calls	128 / 12 / 1
Total policy calls	141
Policy input / generated tokens	1,020,672 / 21,432
Final-answer tokens (included above)	52
Verifier pairs / processed pair tokens	360 / 64,800
Policy / verifier / controller time (s)	540.300 / 1.548 / 6.152

Appendix

Table 12: Inference resources. Additional calls cover capacity handling and final resolution; verifier memory is included in peak memory.

Figure 10: Source admission and retention before an alias relation makes the biography relevant to the question.

Figure 11: Verified commitment after the alias arrives. Each claim is checked against an available source, and the three entries are inserted as one atomic transaction.

Figure 12: Capacity pressure develops before the cast relation arrives. The new source passes its individual size check, but admitting it requires resolution of an existing pending record.

Figure 13: A promotion can fail the committed-memory budget check even when its source states the proposed fact. Forced removal then makes the date unavailable when the later cast relation identifies the relevant person.

Explore similar work

ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning
Jul 2, 2026Yanjun Zhao, Ruizhong Qiu, Tianxin Wei +6Long-Context Reasoning LLM Reasoning Strategies
University of Illinois Urbana-Champaign
PI-Mem: Pushing Long-Context Reasoning to 3.6M Tokens with Parallel-Iterative Memory
Aug 4, 2026Dawei Liu, Haixu Song, Shuang Cheng +9Long-Context Reasoning Large Language Model Memory
Shanghai Jiao Tong University · Shanghai Artificial Intelligence Laboratory · Tsinghua University +3
Evidence-State Rewards for Long-Context Reasoning
Jul 2, 2026Ya Gao, Pekka MarttinenLong-Context Reasoning LLM Reasoning Strategies
1Aalto University

Jul 2, 2026, cs.AIJ/K move · Enter open · S save

ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning

Yanjun Zhao, Ruizhong Qiu, Tianxin Wei, Yuanchen Bei+5

University of Illinois Urbana-Champaign

Long-Context Reasoning LLM Reasoning Strategies

Open paper AskPDF arXiv

Understanding and reasoning over long contexts has become a key requirement for deploying large language models (LLMs) in realistic applications. Although recent LLMs support increasingly long context windows, they often fail to use relevant evidence that is already present in the input, revealing a gap between context access and effective context utilization. In this work, we propose Recursive Evidence Replay as LLM Harness for Long-Context Reasoning (RECONTEXT), a training-free inference method for improving long-context reasoning. RECONTEXT uses model-internal relevance signals to construct a query-conditioned evidence pool and replays it before final generation while preserving the full original context. This recursive selection process separates evidence organization from answer generation without training, external memory, or context pruning. We also provide a theoretical analysis based on associative memory, which characterizes the context as a memory store, the question as a retrieval cue, attention as cue-trace association, and replay as trace reactivation. Experiments on eight long-context datasets with 128K context length show that RECONTEXT consistently improves evidence utilization across Qwen3-4B, Qwen3-8B, and Llama3-8B, achieving the best average rank on all three backbones. Code is available at https://github.com/Yanjun-Zhao/ReContext.

Abstract

Explore similar work

ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning

PI-Mem: Pushing Long-Context Reasoning to 3.6M Tokens with Parallel-Iterative Memory

Evidence-State Rewards for Long-Context Reasoning