Reinforcement_Learning
-
DeciCAD: Harness-Grounded Learning of Action Policies for CAD Agents
2026-10-15 12:11:43Yufeng Peng, Yixin Zhang, Ziyi Liu, Zhikun Xu, Jiarong Yang, Sijie Wang, Wenjie Feng, Qiyu KangAbstract
Large Language Model agents operate through closed-loop action policies whose decision space is defined by an agent harness. We investigate how this operating space shapes agent behavior and policy learning in computer-aided design (CAD), a professional domain characterized by persistent state, geometric constraints, and long-horizon procedures. We instantiate this perspective in DeciCAD, a domain-native harness that exposes semantic CAD actions, decision-oriented observations, environment feedback, and persistent state transitions. Building on this harness, we develop a learning pipeline that extracts causal decision supervision from interaction trajectories and improves the policy through supervised fine-tuning (SFT) and geometry-grounded online reinforcement learning (RL). Across four CAD benchmarks, DeciCAD achieves the best F1 and intersection over union (IoU) while reducing model-output tokens by 45--88% relative to a general-purpose coding harness. Under matched supervision, its SFT policy improves F1 from 0.6883 to 0.7437 and outperforms the coding policy; subsequent online RL further raises geometry availability from 66.5% to 73.5% and F1 to 0.7880. These results demonstrate that the decision space induced by a harness materially affects both agent execution and policy learning in CAD.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21755
PDF
-
Uni-PNP: Unified Prehensile and Non-prehensile Policy Learning for Generalizable Object Pose Reaching
2026-10-15 11:53:10Wenxuan Zhu, Yuze Wang, Jiangran Lyu, Jiayi Chen, Yixin Zheng, Mi Yan, Li Yi, Zhizheng Zhang, He WangAbstract
Object manipulation often requires combining non-prehensile actions with grasping. However, existing approaches typically develop these capabilities separately and integrate them by sequencing distinct primitives through prescribed intermediate objectives, limiting the coordination of contact motions and grasping. Their integration also remains sensitive to object and gripper geometry and depends on particular environmental supports, complicating real-world deployment. We present Uni-PNP, a unified policy that jointly learns prehensile and non-prehensile manipulation for object pose reaching across diverse objects and grippers. To achieve this, we first pretrain a geometry encoder to predict contact-induced object motion using a contact-dynamics dataset constructed from simulated interactions between diverse objects and grippers. We then train the policy in a two-stage reinforcement learning curriculum from graspable objects to ungraspable peers, encouraging the discovery of non-prehensile interactions and their integration with grasping. Experiments show 76.39% success on hundreds of seen objects with grippers, and 57.91% on unseen peers, outperforming the strongest pose-reaching baseline by 20.52 and 17.79 percentage points, respectively. We also analyze emergent behaviors, including nonprehensile and prehensile repositioning, grasp acquisition that requires grasping after tipping, and table-assisted reorientation while grasping, and transfer to the real-world scenario. Project page available at this http URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21735
PDF
-
Router Drift Control: Mitigating Off-Policy Degradation in Mixture-of-Experts Reinforcement Learning
2026-10-15 11:09:10Liangyao Jin, Zhixin Wang, Liming Liu, Mingjun Zhang, Zhengzhou Zhu, Fangcheng Fu, Jinlong Hou, Yuan Cheng, Xiaohe Hu, Ping Zhang, Siyuan FengAbstract
Reinforcement learning (RL) can become off-policy due to training-inference mismatch, mini-batch updates, and asynchronous this http URL resulting mismatch is especially harmful in Mixture-of-Experts (MoE) models, where rollout--training discrepancies can change routing decisions and lead to router drift. Rollout Routing Replay (R3) mitigates this mismatch by reusing expert selections from the rollout stage during training. Our analysis shows that routing replay introduces gradient bias by losing contributions from experts selected by the training router but not the rollout router. To address this, we propose Router Drift Control (RDC), which uses routing disagreement between rollout and training as a signal of off-policy staleness and selectively rejects high-drift responses. The sequence-level filtering avoids gradient bias introduced by replay while preserving native expert selection and the associated learning signals for retained responses. Experiments show that RDC achieves larger gains as policy staleness increases and remains effective in asynchronous RL. In asynchronous training, RDC combined with Truncated Importance Sampling (TIS) improves the average peak validation accuracy across AIME 2024 and AIME 2025 by 5.5 points over TIS and 4.5 points over R3.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21682
PDF
-
Enhancing Multimodal RLVR with Pairwise Token Contrast and Adaptive Trajectory Confidence
2026-10-15 10:55:47Yiran Zhang, Hanbo Huang, Jielan Li, Zhen Zhao, Shiyu Liang, Hongxia HaoAbstract
Reinforcement learning with verifiable rewards (RLVR) improves multimodal reasoning, but group-relative policy optimization broadcasts a single sequence-level advantage to every token of a response, although errors usually localize to a few decisive steps. Recent self-distilled variants refine credit with a teacher--student likelihood gap. However, this signal cannot tell whether it relies on the image or on a language shortcut, and is applied uniformly even when the teacher is uninformative. To address this, we propose Pairwise token contrast and Adaptive trajectory ConfidencE (PACE). Pairwise token contrast scores each response under four teacher views, crossing a correct or incorrect answer hint with the image present or removed, and compares the two hints for every token, which cancels shifts shared by both hints and reveals whether the token's support relies on the image. Adaptive trajectory confidence measures how well the teacher predicts each response given the correct hint and the image, normalizes this score within the batch, and uses it to set how far the token contrast redistributes credit within that response. PACE achieves the best average accuracy on three backbones and ranks first on all evaluated multimodal reasoning benchmarks with Qwen3-VL-8B-Instruct. Experiments show that both components matter: replacing pairwise token contrast with a single-view signal underperforms our method, while adaptive trajectory confidence adds further improvement.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21671
PDF
-
Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation
2026-10-15 09:47:19Bingxi Hou, Guochao Jiang, Guofeng Quan, Weiqing Li, Wenfeng Feng, Guohua Liu, Yuewei ZhangAbstract
Policy-shift distillation reuses the difference between a teacher's log probabilities before and after reinforcement learning (RL) as supervision on student-generated trajectories. However, this endpoint policy shift cannot reveal whether local action preferences evolved consistently during teacher training. The same endpoint shift can result from early and late shifts that reinforce or partially cancel each other. We investigate whether agreement between early and late teacher policy shifts can guide selective transfer. We introduce Waypoint-guided On-Policy Distillation (Waypoint-OPD), which uses an intermediate teacher checkpoint from the same RL run to compare early and late shifts in relative action preferences at student-visited prefixes. We gate the endpoint shift according to the directional agreement between the early and late shifts, suppressing it when they point in opposing directions. Compared with endpoint-only transfer, our method requires only one additional frozen-teacher scoring pass. Using RL-trained Qwen3-4B teachers, we evaluate our method with Qwen3-8B, Qwen3-14B, and Qwen3-30B-A3B as student models in mathematical and code reasoning. In all six domain--student settings, Waypoint-OPD achieves the highest domain-average score among the compared distillation methods. Ablations with the Qwen3-8B student show that removing or shuffling gates reduces mathematical reasoning performance. These results support the use of directional agreement between early and late teacher policy shifts to weight the endpoint shift during student training.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21601
PDF
-
Reinforcement Learning-driven Diffusion Models: Language, Vision, and Beyond
2026-10-15 09:05:38Zhiyuan Ma, Jiabao Wei, Tianyu Wang, Hanqing Wang, Jiadong Pan, Haowen Xu, Liangliang Zhao, Ruixun Liu, Yuhan Wang, Yuwei Zhang, Liang Feng, Junhao Xiao, Kaiyan Zhang, Xuekai Zhu, Daizong Liu, Biqing Qi, Yihao Liu, Ganqu Cui, Ning Ding, Linfeng Zhang, Jianjun Li, Kun He, Xiang Bai, Bowen ZhouAbstract
Diffusion models (DMs) have steadily demonstrated outstanding performance in high-fidelity, controllable generation across diverse scenarios, following the "pretraining-finetuning" paradigm established in LLMs. Despite these advances, conventional DMs still face critical limitations in sophisticated reasoning, autonomous exploration of generation pathways, and adaptability to complex, human-aligned objectives. Inspired by RLHF's success in LLMs, RL has recently emerged as a pivotal post-training mechanism to iteratively refine DMs through reward-driven trajectory optimization. This paper presents the first comprehensive review of RL-driven DMs and an empirical analysis of how RL reshapes the diffusion process towards experience-centric, goal-directed generation. We propose a novel technical panorama elucidating RL's multifaceted roles in diffusion-based language, multimodal, robotic, and scientific models, with a granular focus on diffusion trajectory optimization and reward engineering. Through extensive experiments on multiple task-specific benchmarks, we systematically evaluate representative methods to intuitively highlight the advantages of different RL post-training strategies. Furthermore, we reveal and dissect three crucial bottlenecks that currently hinder the real-world deployment of RL-driven DMs: reward design fragility, exploration-exploitation trade-off in high-dimensional generation spaces, and training instability under sparse rewards. Based on these perspectives, we provide a principled roadmap for the integration of RL into DMs and outline promising future research directions for robust, interpretable RL-diffusion systems. We also construct a public repository to continuously track the latest developments in this rapidly evolving field: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21539
PDF
-
QREF: Improving DeepSearch Agents by Aligning Search with Reasoning via Query Refinement and Evidence Filtering
2026-10-15 08:47:44Yujia Chen, Yuhui Wang, Junzhe Wang, Shihan Dou, Di Liang, Yujiong Shen, Yuhao Zhou, Zhiheng Xi, Ming Zhang, Senjie Jin, Jiayi Chen, Dingwei Zhu, Yajie Yang, Yuan Hua, Chenyao Lu, Tao Gui, Qi Zhang, Xuanjing HuangAbstract
DeepSearch agents achieve strong performance on complex information-seeking tasks through iterative search and reasoning. However, they often issue intent-misaligned, under-constrained, or redundant search queries, resulting in poor evidence coverage and accumulating retrieval noise. To mitigate these limitations, we propose QREF, a plug-and-play Query Refiner and Evidence Filter. Specifically, the Query Refiner rewrites search queries according to the current reasoning intent while ensuring complementary coverage across each search batch. The Evidence Filter retains evidence relevant to both the current search batch and the reasoning objective, reducing distracting retrieval results. We initialize the Query Refiner with supervised fine-tuning and optimize it through reinforcement learning based on interactions with a real-world web search environment, reducing ineffective queries. Comprehensive experiments demonstrate that our approach improves the performance of DeepSearch agents across four challenging benchmarks, achieving average relative Pass@1 improvements of 33.55% on WebSailor and 11.04% on TongyiDeepResearch without modifying architectures or retraining their reasoning policies. Compared with the original DeepSearch backbone without QREF, the RL-trained refiner reduces the fraction of query batches that lack discriminative retrieval anchors by 95%. Compared with the SFT-trained refiner, it also lowers the filter-based ineffective query ratio.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21512
PDF
-
Incentivizing Tool-Use Reinforcement Learning for Post-Arrival Emergency Care Prediction
2026-10-15 07:53:54Pengfei Hu, Chenwei Wu, Qiao Jin, Jun Deng, Zhiyong Lu, Liyue Shen, Yue NingAbstract
Large language models (LLMs) can reason over both structured measurements and free-text records, which makes them attractive for emergency department (ED) prediction. However, most existing LLMs still fall short of conventional ML methods like trees on EHR-based prediction tasks. Our controlled analysis traces this gap to two weaknesses: LLMs do not select informative features, and they misjudge what numerical values imply for risk even when given the right features. We propose TIR-EC, a tool-integrated reinforcement learning framework that addresses both. TIR-EC exposes EHR feature groups as tools the LLM can call. It trains the LLM with rewards from a gradient-boosted tree teacher, which provides a reference set of informative tools and a graded risk target. TIR-EC also distills task-specific clinical skills into the model weights through a reverse curriculum that gradually removes the skills from the prompt during RL process. Evaluation on three clinical prediction tasks shows that our 4B agent achieves the highest macro F1 of all compared models, outperforms conventional ML baselines, and is competitive with much larger frontier LLMs. Further analysis shows that TIR-EC selects more useful evidence with fewer tool calls and combines measurements more effectively.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21449
PDF
-
V-SHARE: Provable Convergence Guarantees for Advantage-based Algorithms
2026-10-15 07:52:35Kintan Saha, Hamed Masoudi, Xinyi Sheng, Dominik Baumann, Joni Pajarinen, Arsenii MustafinAbstract
In reinforcement learning, advantage-based value-learning methods, unlike standard Q-learning, share information across actions by decomposing the action-value function into a state-dependent value component and action-specific advantages. While this mechanism has proven effective in both tabular and deep reinforcement learning, its theoretical understanding remains incomplete. We introduce V-SHARE, an advantage-based value-learning algorithm that combines cross-action value sharing with an importance-weighted Bellman-residual correction. To our knowledge, we provide the first complete theoretical characterization of an advantage-based algorithm, including both asymptotic convergence and non-asymptotic finite-sample guarantees. We identify a regime in which V-SHARE mitigates the rare-action bottleneck of asynchronous Q-learning and uncover a contraction--variance tradeoff between stronger deterministic contraction and increased importance-weighting noise. Motivated by this tradeoff, we develop decreasing residual-preconditioning schedules that combine faster early contraction with lower asymptotic noise. We further develop a two-timescale analysis that removes the single-timescale residual-weight threshold while preserving convergence guarantees. Experiments on discrete Markov decision processes (MDPs) and deep reinforcement-learning benchmarks corroborate our results.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21448
PDF
-
Learning to Reason with Selective Internal Feedback
2026-10-15 07:08:46Xun Lu, Shumeng Yang, Xinrui Wang, Songjun Tu, Linjing Li, Daniel Dajun ZengAbstract
Reinforcement learning from internal feedback can improve language models without ground-truth answers or external verifiers. However, confidence and correctness can diverge during training, and continued optimization of average self-certainty can increase confidence while degrading reasoning accuracy. We introduce SIF, a reinforcement learning method that combines comparative reward construction with selective policy updates. SIF compares ranked token-level self-certainty profiles across multiple windows and peers, assigning positive rewards only when both levels of voting provide sufficient support. Sample and group level filtering determines which responses contribute to policy optimization. Experiments on three backbones across 12 mathematical and scientific reasoning benchmarks show that SIF's final checkpoints achieve higher average accuracy than the best-validation checkpoints of Intuitor and Vigor, with a gain of 4.71 percentage points over Intuitor on Qwen2.5-Math-1.5B. Further analyses show better retention of accuracy during continued optimization, while test-time training experiments demonstrate sustained improvements with as few as four rollouts per prompt.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21392
PDF
-
Perception or Reasoning? Diagnosing and Tackling Reinforcement Learning Bottlenecks in VLMs
2026-10-15 07:00:46Zeyuan Yang, Zhuohao Chen, Jiaben Chen, Yao Zhang, Maohao Shen, Chuang GanAbstract
Reinforcement learning has brought strong gains to language model reasoning, but its improvements on visual tasks remain less consistent. One difficulty is that visual task failures can arise from different sources: the same benchmark may be limited by perception for one model and by reasoning for another. We introduce Perception and Reasoning Attribution (PARA), which measures the remaining perceptual and reasoning headroom of each model--benchmark pair by comparing how many current errors are recovered with more accurate visual information versus a stronger reasoner. Across 4 vision-language models and 17 multimodal benchmarks, PARA broadly agrees with the expected characteristics of existing benchmarks while revealing substantial model-specific variation. More importantly, it shows that RL gains become smaller as perceptual headroom increases, but larger when reasoning explains more of the recoverable errors, suggesting that current RL exploits reasoning headroom more effectively than perceptual headroom. Motivated by this gap, we analyze how existing RL objectives affect visual perception and find that reward- and token-level signals influence visual attention only indirectly. We therefore propose GRAD, a group-relative attention distillation objective that uses the best rollout in each group to directly guide the visual attention of weaker rollouts. GRAD consistently improves performance across two model scales and seven benchmarks, and further complements existing RL methods.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21380
PDF
-
Hindsight-Privileged RLVR: Single-Rollout Token Credit Without Group Sampling
2026-10-15 06:36:16Wei Chen, Yubing Wu, Zhou Xu, Haoyue Zhang, Delu Zeng, Jiahao Wang, Junmei Yang, Pan tiewen, Jingfeng Liu, Zhiheng Zhou, Bo Li, Min ChenAbstract
Reinforcement learning with verifiable rewards (RLVR) trains language models from checked task outcomes, but assigning a terminal reward to individual reasoning tokens or actions remains difficult. Group-relative methods such as Group Relative Policy Optimization (GRPO) sample several attempts per prompt, but lose their reward-based learning signal when all attempts receive the same outcome. We propose Hindsight-Privileged RLVR (HP-RLVR), a single-rollout method that turns a completed trajectory's own future into token-level update weights. The generating policy snapshot scores each eligible token under its causal history and under a hindsight context containing the realized future and verifier feedback. A normalized Jensen--Shannon divergence between the two views weights the reward relative to a historical baseline, yielding bounded token credit for both successful and failed attempts, with no reference solution or learned critic. In paired Qwen3-8B runs over a shared $100$-step schedule, HP-RLVR trains $1.21\times$, $1.46\times$, and $2.30\times$ faster than GRPO on mathematics, code generation, and ALFWorld, using one eighth the rollouts per prompt. Accuracy is comparable overall, with HP-RLVR ahead on mathematics at all three sizes and GRPO ahead on code and ALFWorld. In ALFWorld, $43.2\%$ (4B) and $49.0\%$ (8B) of GRPO's gradient-norm records are zero, versus none for HP-RLVR.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20497
PDF
-
Ranking and Partitioning of Attention Heads for Sparse and Continual Reinforcement Learning Fine-tuning
2026-10-15 06:21:56Ruizhe Shi, Zaiwen Yang, Qiubo Wang, Banghua Zhu, Maryam FazelAbstract
We study sparse and continual reinforcement learning fine-tuning of language models through attention-head ranking and partitioning. For sparse learning, we rank attention heads by gradient norm to identify a small subset of heads that can be trained effectively. For continual learning, we partition heads across tasks to reduce cross-task interference and preserve previously learned capabilities. Theoretically, we relate gradient norm to training effectiveness, and further characterize why sparse, separated head updates can remain stable. Empirically, across math, instruction-following, and coding tasks, tuning higher-ranked heads consistently outperforms tuning lower-ranked ones while often matching denser baselines, and head partitioning improves retention while preserving adaptation to new tasks.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21336
PDF
-
Constrained Multi-Agent Reinforcement Learning in Imagination
2026-10-15 06:09:04Raz Shmueli, Shahaf S. ShperbergAbstract
Predicting cost in a multi-agent world model moves most constrained policy updates into imagination: the stronger model-free baseline needs $10$ to $20$ times CA-MAMBA's interactions on the median SMAC configuration, and CA-MAMBA earns $2.8$ to $12$ times the baselines' MAMuJoCo reward at equal budget. In controlled tests on one task per benchmark, pricing the model's cost advantages at parity more than halves a cost-blind learner's cost and meets a tight continuous-control limit the learned multiplier misses, suggesting the model's cost estimates are not the bottleneck.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21319
PDF
-
What Should We Remove? Evaluating the Reliability and Costs of RLVR Data Decontamination
Abstract
Reinforcement learning with verifiable rewards (RLVR) math corpora are routinely screened for benchmark overlap, but the reliability and data-loss costs of cleaning policies remain underexamined. We audit sixteen open RLVR math corpora comprising 1,673,514 corpus-specific training items against six benchmarks containing 1,949 questions. We evaluate eight policies based on exact, lexical, and semantic matching using 594 independently and blindly dual-reviewed training-benchmark pairs. Calibration and held-out sets have disjoint benchmark questions and training-example families. A separate review of all 83 candidate matches for 80 sampled training items measures item-level false removal. At cosine threshold 0.80, 52 of 59 sampled removals (88%) were confirmed false removals; this is not a demonstrated population rate. No semantic threshold in our preregistered grid (0.80-0.98) meets the 90% conservative-precision target on calibration. The existing judge-adjudicated policy achieves 98.1% resolved precision and 98.2% candidate-frame recall on held-out corpora. It has zero confirmed false removals among six sampled removals, with one unresolved case; this does not establish zero risk. Within the evaluated candidate frame, this policy offers a more favorable precision-recall balance than the semantic-threshold alternatives tested. Recall does not measure contamination outside the candidate frame. We release reviewed labels, per-policy decisions, and coverage accounting to support evaluation of cleaning reliability and cost rather than overlap counts alone.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21229
PDF
-
Rubric Judgments Lack Uncertainty: Conformal Weighting for LLM Evaluation
2026-10-15 04:06:12Licheng Pan, Haocheng Yang, Haoxuan Li, Yuzhou Chen, Yichen Sun, Yuan Lu, Xiaoxi Li, Hao Wang, Zhixuan Chu, Kui RenAbstract
Rubric-based evaluation is widely used to assess large language model (LLM) outputs by decomposing quality into multiple criteria and assigning each a binary judgment from an LLM verifier. However, judgment certainty varies substantially across criteria. Existing methods uniformly aggregate these judgments into a final score, implicitly treating every criterion as equally certain and overlooking this heterogeneity. As a result, uncertain judgments remain incorporated into reward estimation without distinction, potentially yielding misleading training signals for downstream reinforcement learning (RL). To address this limitation, we propose Uncertainty-aware Rubric Weighting (URW), a training-free framework that quantifies criterion-level judgment uncertainty via conformal calibration. Specifically, URW elicits a soft uncertainty signal from a fixed pool of paraphrased judgment templates and converts it into a per-criterion weight using split-conformal $p$-values with provable coverage guarantees. Extensive experiments demonstrate that URW consistently improves pairwise preference accuracy and delivers stronger downstream RL alignment.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21214
PDF
-
Judging the Judges: Confidence and Disagreement in Rubrics as Rewards
2026-10-15 03:35:00Michael Tian-Yue Liu, Anne Harrington, Trevor Darrell, Yutong BaiAbstract
Rubrics as Rewards (RaR) extends reinforcement learning to non-verifiable domains by using an LLM judge to score responses against a structured rubric. Prior work has focused on improving the rubric or strengthening the single judge, with comparatively little attention to how different single or multiple judges might be used during RaR training. We first show that judge identity alone produces a substantial spread in scores when training Qwen3-4B-Base on RaR-Medicine and RaR-Science across five frontier and open-weight judges. Building on this, we propose RaRE (Rubrics as Rewards with Ensembles), a novel judge ensemble strategy for RaR with two mechanisms: a soft-Likert reward that uses judge logprobs to weight more confident judges more heavily, and a drop-on-disagreement mask that excludes high-disagreement rollouts from the GRPO update. We find that this design is critical: while a naive average of judge scores fails to outperform the best single judge, RaRE outperforms every single-judge RaR variant on both HealthBench and GPQA Diamond, with per-theme analysis showing that it inherits the complementary strengths of its constituent judges. Our findings establish judge ensembling as a compelling axis for improving RaR.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21179
PDF
-
All-in-One Memory: Process-Rewarded Reinforcement Learning for Memory Agents
2026-10-15 03:02:24Bingbing Wang, Jingjie Lin, Weiming Qiao, Jing Li, Ruifeng XuAbstract
Large language models increasingly rely on external memory to answer queries grounded in long-horizon histories such as multi-session dialogues and lengthy documents. However, existing memory methods often optimize retrieval and memory construction separately, without a shared reward space for evaluating search, writing, and stopping decisions. To address this, we propose All-in-One Memory (AiO-Mem), which organizes these operations as transitions over a shared evidence state and directly evaluates the semantic quality of each action in a unified reward space. AiO-Mem compiles heterogeneous histories into source-traceable multi-view events, providing a shared substrate for retrieval and memory writing. A unified memory policy actor then rolls out complete interaction trajectories over this shared evidence state. A separate trajectory-conditioned process reward model is trained through evidence-grounded supervised fine-tuning and trajectory-level DPO to assign process scores to the collected trajectories. These scores are aggregated into an action-balanced trajectory reward and used by Process-Aligned DAPO (PA-DAPO) to optimize the memory policy. Across long-context memory benchmarks, AiO-Mem consistently improves answer accuracy over both static memory systems and RL-trained memory agents.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21147
PDF
-
Manifold Generative Annealing for Contact Constraint-aware Impedance Control with Reinforcement Learning Prior
2026-10-15 02:51:51Zhilin He, Guoquan Qi, Changliu LiuAbstract
Contact-rich robotic tasks require coordinated motion and impedance under uncertain interaction dynamics and physical constraints. While recent methods on learned policies provide useful interaction strategies, they may fail when contact conditions differ from those encountered during training. Model-based generative methods show promising receding-horizon trajectories optimization results, but often lack structured behavioral guidance and refinement that jointly accounts for constraint geometry and actual contact responses. To this end, we propose Manifold Generative Annealing (MGA), a joint model-free and model-based generative framework for motion--impedance optimization. MGA first organizes pretrained reinforcement learning policies into structured sequence proposals, retaining task-specific interaction strategies without committing to their execution. It then evaluates these proposals alongside exploratory samples through model-based rollouts for refinement or separate execution selection. Crucially, realization-aware manifold refinement aligns updates from the refinement bank with both task constraints and locally achievable physical responses, allowing learned experience to guide online adaptation under changing contact conditions. Experiments cover surface scanning, peg insertion, and humanoid pushing, with improved safety success rate of impedance control under nominal and sensing-shift conditions.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21140
PDF
-
MemComposer: Learning to Assemble Memories for LLM Agents via Reinforcement Learning
2026-10-15 01:47:06Yixuan Xie, Xueqiang Xu, Xinyi Fan, Xinxi Lyu, Tao Feng, Xing Fan, Chenlei Guo, Jie Hao, Shaowen Wang, Jiashuo Sun, Jiawei HanAbstract
Agent memory enables large language model (LLM) agents to reuse past experiences without updating their parameters. However, semantic similarity alone does not guarantee memory usefulness: downstream performance depends on how memories are selected and presented to the agent. We propose MemComposer, a memory composer that jointly examines the current query and retrieved candidates to decide which experiences to include, how many to select, and how to order them. We train the composer using Experience Policy Optimization (ExPO), a GRPO-based framework that evaluates assembled memory contexts through complete agent interactions and uses task-success feedback to optimize the assembly policy. Across three $\tau^2$-bench domains with two frozen executors, MemComposer outperforms the strongest baseline for each executor while reducing average memory-token usage by 16.9% and 4.9%, respectively. The learned policy also transfers to unseen domains, executors, and memory banks, and benefits from memories generated by stronger models without further training. These results demonstrate the value of learning query-specific memory assembly using downstream task feedback.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21091
PDF
