Robotics
Uncertainty-Driven Self-Play for Robust Multi-Agent Driving Policies
Sajad Marvi, Julian Schmidt, Alessandro Canevaro et al. (+2 more)
Learning robust driving policies that generalize beyond their training domain remains a central challenge in motion planning. We propose an uncertainty-driven self-play scheme, in which half of the
agents are rewarded for increasing their neighbors' epistemic uncertainty, while the other half learn to drive safely as the exploring
agents continuously seek out their weaknesses. Epistemic uncertainty indicates where the policy is least confident and serves as an automatic proxy for scenario difficulty. Exploring
agents use this signal to seek out hard cases, generating a challenging curriculum without manual scenario design. The resulting policy outperforms standard self-play, achieving best-in-class zero-shot transfer to nuplan Val14 (99.12% vs. 97.97%) and Argoverse 2 (82.39% vs. 78.03%) without fine-tuning, while also improving performance over standard self-play on Waymo. Our diversity-driven approach achieves 85% higher LSTM hidden-state coverage than the baseline, indicating a much richer set of behaviors. Further analysis shows that epistemic uncertainty serves as a calibrated difficulty detector, with highest-uncertain
agents exhibiting 14.8 times the combined failure rate across collision, off-road, and DNF, of lowest-uncertain
agents, enabling automatic prioritization of challenging scenarios without ground-truth labels.
Read the full abstract ▾
All authors Sajad Marvi, Julian Schmidt, Alessandro Canevaro, Julian Jordan, Abhinav Valada
Machine Learning
New Model, Old Habits: Behavior Transfer under Model Swapping in Multi-Session LLM Agents
Youngbin Choi, Sehyun Hwang, Suhyeon Jun et al. (+4 more)
Multi-session
agents can switch between LLMs to balance performance and inference cost. Such switches require transferring a history for continuity, yet their effects on the recipient remain underexplored. Through controlled experiments with multi-session tasks, we uncover behavior transfer: recipients tend to adopt
reasoning and action patterns from the models that generated their histories. This effect is most evident with raw-history transfer but is substantially reduced by summarization. Based on these findings, we propose Direction- and Authorship-aware Summarization of History (DASH) that preserves stronger-model behavior while minimizing weak-to-strong transfer via summarization. Experiments with repeated swaps show that DASH outperforms raw-history transfer and naive summarization baselines. These results suggest that effective multi-model orchestration requires considering not only which model to use, but also which behavioral patterns to carry forward.
Read the full abstract ▾
All authors Youngbin Choi, Sehyun Hwang, Suhyeon Jun, Seoyeon Lee, Sunghyun Choi, MoonJeong Park, Dongwoo Kim
Data Structures and Algorithms
Dynamic 3-Coloring of Bipartite Graphs with Optimal Locality
Yann Bourreau, Filippo Casagrande, Tim Göttlicher et al. (+1 more)
We give a dynamic graph
algorithm which maintains a 3-coloring in bipartite graphs under edge insertions such that the coloring only changes within a radius of $O(\log n)$ around an inserted edge. In the context of locality theory in distributed graph
algorithms, this gives an upper bound on the locality under the dynamic-LOCAL model. Our bound on the locality is tight, as the problem admits a matching $\Omega(\log n)$ lower bound in the stronger online-LOCAL model, by a result of Chang et al. [PODC 2024]. Thus, our result closes the gap between dynamic and online locality of this problem.
Read the full abstract ▾
All authors Yann Bourreau, Filippo Casagrande, Tim Göttlicher, Ananth Narayanan Karunattillam
Computation and Language
Beyond State Capacity: Why Retrieval Breaks in Mamba
Nir Yarden, Amit Ben-Artzy and Roy Schwartz
Mamba models underperform
Transformers on in-context
retrieval. This gap is usually attributed to Mamba's fixed-size recurrent state, which loses information as the context grows. We challenge this assumption by focusing on query-first
retrieval, a setup in which the query precedes the context and state capacity should not be the binding constraint. We show that even in this setting Mamba lags substantially behind
Transformers, despite its selection mechanism, which was designed to distinguish relevant content from distractors. We then demonstrate that the Mamba selection gates have sufficient control over the state updates to influence the model output: intervening on specific gates alone can swing accuracy between extremes. However, as gates are input-dependent, they require the incoming
token's representation to encode its relevance to the query. We therefore probe
token representations across layers, and find that the relevance signal emerges only gradually with model depth, and that the gates begin to reflect it only several layers deeper. Crucially, we find that gates in
retrieval-critical layers are not yet aligned with relevance. The selection mechanism is thus expressive enough to solve the task, but it commonly operates on a relevance signal that has not yet arrived. Mamba's
retrieval bottleneck therefore extends beyond state capacity: even when capacity is sufficient, the delayed emergence of relevance information across depth often prevents successful
retrieval.
Read the full abstract ▾
Computer Vision
SceneAE: Scene Generation and Reconstruction in Queryable 3D-Anchored Latent Space
Shuofeng Sun, Wenzhao Zheng, Yunpeng Zhang et al. (+3 more)
Recent
video world models have increasingly adopted 3D
memory mechanisms to integrate historical observations into a lightweight and persistent scene representation. This naturally raises a complementary question: if 3D representations can serve as an effective mechanism for memorizing observed scenes, can they also be directly used as the latent space for reconstructing and generating scenes? Motivated by this idea, we represent a scene as a compact and unstructured 3D-anchored latent space (SceneAE). Each latent combines an explicit 3D position with an implicit content feature and is spatially grounded to describe its local scene region, forming a sparse latent point cloud. Unlike conventional
video-VAE latents that describe how a scene appears from particular viewpoints, our representation directly describes the scene itself, making it naturally applicable to both reconstruction and generation. For reconstruction, once the scene has been generated, our persistent 3D representation can be projected and decoded into RGB-D observations by different target cameras, without the need to regenerate a
video for each new camera trajectory. For generation, we leverage the geometry-content separation to first generate camera-controlled 3D geometry and then synthesize content conditioned on it, reducing camera-appearance
entanglement and improving camera controllability. Experiments show that this 3D latent achieves superior generation quality, computational cost, and camera controllability.
Read the full abstract ▾
All authors Shuofeng Sun, Wenzhao Zheng, Yunpeng Zhang, Yi Wu, Linqing Zhao, Haibin Yan
Data Structures and Algorithms
Revisiting Non-Adaptive Set Membership Schemes: Removing the Logarithmic Factor
Mirza Galib Anwarul Husain Baig, Aman Kumar, Pawan Kumar Saw et al. (+1 more)
We study non-adaptive bit-probe schemes for static set membership. Each query reads a fixed number of bits and answers by strict majority. We revisit the random bipartite-graph construction of Garg and Radhakrishnan [STACS, 2017]. The main observation is that a slightly stronger expansion property already bounds the number of exceptional elements. This makes a separate probabilistic estimate for exceptional elements unnecessary. A detailed union-bound calculation then gives, for every fixed $t\ge5$, a logarithm-free existence bound of $O_t(m^{1/c}n^{1-1/c})$, where $c=\lfloor(t-1)/2\rfloor$. For odd $t$, this removes the logarithmic factor from the general upper bound of Garg and Radhakrishnan [STACS, 2017].
Read the full abstract ▾
All authors Mirza Galib Anwarul Husain Baig, Aman Kumar, Pawan Kumar Saw, Vikash Tripathi
Computation and Language
RouteWeaver: Weaving Mode Selection and Execution into Unified LLM Routing
Xiaohan Wang, Haozhen Zhang, Qingyuan Liu et al. (+2 more)
LLM routing dynamically selects and coordinates heterogeneous
language models across diverse tasks. However, existing approaches are largely built around a predefined execution paradigm, such as single-round, multi-round, or agentic routing, which fixes how model calls are organized and limits adaptation to different query needs. We propose RouteWeaver, a unified routing framework that integrates these routing modes within a single LLM policy, jointly learning which mode to use and how to select models within that mode. To jointly optimize mode selection and within-mode execution, we develop COMET-GRPO (COordinated Mode-Execution Training), which decouples the trajectory-level advantage into separate signals for mode selection and within-mode execution, enabling more targeted credit assignment to each decision level. We further introduce progressive exploration, which gradually shifts training from externally assigned modes to autonomous selection, so that the router first learns how to execute each mode before deciding when to use it. We evaluate RouteWeaver across mathematics, coding, knowledge, logical
reasoning, and factual recall. RouteWeaver achieves an average accuracy of 61.4%, an 11.03% relative improvement over the strongest baseline, and outperforms all compared baselines in each of the five domains. Ablations show that both COMET-GRPO and progressive exploration are important for adaptive routing; without progressive exploration, the routing policy collapses entirely to single-round execution.
Read the full abstract ▾
All authors Xiaohan Wang, Haozhen Zhang, Qingyuan Liu, Tao Feng, Wenya Wang
Computation and Language
BANGLAPLAN: A Benchmark for Constraint-Based Planning and Decision-Making in Bangla
Md Rayhanul Masud, S M Maksudul Alam and Mohammad Jaminur Islam
Large
language models (LLMs) increasingly help users arrange appointments, plan journeys, and allocate limited resources. These tasks require models to satisfy constraints on time, cost, capacity, and order, or determine that no feasible solution exists. Bangla is the world's seventh most widely spoken
language, and existing
benchmarks cover many
language and
reasoning tasks. However,
benchmarks for evaluating planning and decision-making in Bangla under explicit constraints remain lacking. We introduce BANGLAPLAN, a
benchmark of 1,000 problems across ten task families grounded in everyday life and institutions in Bangladesh. It includes feasible and infeasible problems in four
language registers: everyday, formal, colloquial, and Bangla–English mixed. Answers cover eight structured types, including schedules, routes, allocations, and ordered steps, in a common JSON format. We construct the
benchmark through
language-model-assisted drafting and independent human validation. We evaluate 11 open-weight and proprietary model configurations using exact match, separately reporting feasible-case accuracy, infeasibility detection, and format errors. We find a large performance gap: GPT-6.1 Sol achieves 98.7% accuracy and Qwen3.5-27B with thinking reaches 80.3%, while direct-answer configurations score at most 30.9%. Seven of eleven configurations perform below the always-“infeasible” baseline. Our findings also suggest that harder problems primarily reduce plan-construction accuracy, while infeasibility detection remains more robust. BANGLAPLAN provides a reproducible basis for evaluating planning and decision-making in Bangla. BANGLAPLAN is available at: https://github.com/mrayhanulmasud/banglaplan.
Read the full abstract ▾
Artificial Intelligence
Runtime Monitoring of Supermartingale Certificates
Mirco Giacobbe, Thomas A. Henzinger, Konstantin Kueffner et al. (+2 more)
Supermartingale certificates formally guarantee temporal properties of discrete and continuous-time
stochastic dynamical systems. However, these guarantees rely on a mathematical model of the world, leaving a sim-to-real gap that can invalidate them for the deployed system. We formulate the runtime monitoring problem for supermartingale certificates, in which a monitor observes a single system trajectory and raises an alarm when there is sufficient statistical evidence that the supermartingale certificate has been violated during execution. We present an
algorithm to automatically construct a monitor using betting-based sequential tests that bound the probability of ever raising a false alarm at a user-specified level. Within this betting framework, we formulate strategies that allow the monitor to exploit spatial regularity to improve detection power while preserving this statistical guarantee. We demonstrate the efficacy of our approach on supermartingale certificate
benchmarks from the literature.
Read the full abstract ▾
All authors Mirco Giacobbe, Thomas A. Henzinger, Konstantin Kueffner, Emily Yu, \DJ{}or\dj{}e Žikelić
Machine Learning
ReGRA: Residual-Gradient Adaptation for Complementary Low-Rank Fine-Tuning
Fanyao Li, Yuxi Liu, Xiaohao Liu et al. (+3 more)
Low-rank adaptation (LoRA) enables parameter-efficient fine-tuning by learning low-rank weight updates. Increasing rank expands adaptation capacity, but does not guarantee that all learned directions improve downstream performance. In a diagnostic experiment with rank-16 LoRA, we show that retaining only the top singular components achieves the best performance, whereas adding further components degrades it. Motivated by this, we propose Residual-Gradient Adaptation (ReGRA), a two-stage method for making more effective use of a fixed rank budget. After the first stage, ReGRA estimates task gradients on a calibration set and removes their projections onto the two-sided subspace induced by the first-stage update. It then aggregates the residual-gradient directions to initialize a second-stage adapter without changing the first-stage update. An orthogonality regularizer encourages the two updates to capture complementary directions. Both updates can be merged into the pretrained weights, incurring no additional inference overhead. Across diverse
benchmark sets, ReGRA achieves stronger performance than alternatives with the same total rank and even matches LoRA adapters with twice the rank. Ablation studies and further analysis support the contribution of its core design choices. Code is available at https://github.com/Fanyao-Li/ReGRA.
Read the full abstract ▾
All authors Fanyao Li, Yuxi Liu, Xiaohao Liu, He Chang, Zhaoxin Wang, Zhulin Tao
Game Theory
Effective-Balance Design in Ethereum Proof-of-Stake
Bolin Zhang and Xuechao Wang
Proof-of-Stake (PoS) systems offer a scalable and energy-efficient alternative to Proof-of-Work (PoW). The economic security of PoS relies critically on incentivizing broad and meaningful participation through well-cali\-brated staking reward mechanisms. We study Ethe\-reum's effective-balance rules as a mechanism-design problem in which the protocol chooses a reward coefficient, an activation threshold, and a maximum effective balance, and validators respond in the induced propor\-tional-allocation game. For fixed participating validators and identity counts, we establish a unique Nash
equilibrium in validator-level total stakes. When validators can split or merge their visible identities, each candidate identity structure must be evaluated after the
market re-clears. Restructuring incentives therefore depend on post-reset payoff comparisons that account for all validators' stake responses. For an illustrative simulation, we construct address-level budget proxies from Beacon Chain deposits and withdrawals, Lido staking flows, Etherscan balances, and calibrated synthetic
agents. With illustrative cost coefficients, lowering the reserve price from 32 ETH to 30 ETH increases active identities by 5.922% and total effective stake by 0.098%.
Read the full abstract ▾
Artificial Intelligence
RuleTrek: Benchmarking Agentic Rule Reasoning in Complex Scenarios
Chenhao Yuan, Bohan Yu, Yinhao Xu et al. (+10 more)
Large
language models (LLMs) increasingly tackle complex real-world tasks in specialized domains. However, identifying and correctly applying domain-specific rules remains challenging when scenario information is distributed across multiple files. Existing rule-
reasoning benchmarks typically represent scenarios using only a few factual statements, simplifying the identification and application of relevant rules. To address this gap, this paper introduces RuleTrek, a multi-domain
benchmark for agentic rule
reasoning in complex scenarios. Its rule-grounded construction pipeline extracts structured rule graphs, generates and incrementally composes rule-specific sub-scenarios while ensuring consistency and solvability. To systematically evaluate agentic rule
reasoning in complex scenarios, RuleTrek assesses three capabilities in interactive workspaces: Rule Identification (RI), Rule Deduction (RD), and End-to-End Rule
Reasoning (E2E). Experiments on 11 frontier LLMs show that the highest RI and RD scores are only 62.47% and 60.43%, respectively, while E2E scores range from 26.97% to 55.29%. These results demonstrate that current LLM
agents face substantial challenges in rule
reasoning over complex scenarios. We make our code and
dataset publicly available at \href{https://github.com/yuan247/RuleTrek}{RuleTrek}.
Read the full abstract ▾
All authors Chenhao Yuan, Bohan Yu, Yinhao Xu, Chao Yin, Chenxi Zhou, Zhaoxuan Wang, Shuwen Xu, Shaoping Huang, Haolin Ren, Jiaxiang Liu, Yao Xu, Jun Zhao, Kang Liu
Hardware Architecture
CAFE: Conducting-Cell-Aware Adaptive Differential Encoding for Robust DNN Inference in FeFET-Based Compute-in-Memory
Wenshuai Yao, Wenyong Zhou, Hanyong Shao et al. (+3 more)
Ferroelectric field-effect transistor (FeFET)-based compute-in-
memory (CIM) promises energy-efficient deep neural network (DNN) inference, but device variation can severely degrade bit-sliced CIM accuracy. Prior works either rely on hardware modifications or treat such variation as generic noise, overlooking a key FeFET asymmetry: negligible off-state leakage makes errors dominated by conducting on-state
cells. This asymmetry is amplified by two's-complement sign extension, which maps small negative values to high-significance bit slices and magnifies their errors during shift-and-add reconstruction. In this paper, we propose CAFE, a conducting-
cell-aware adaptive differential encoding framework built upon this FeFET-specific asymmetry. CAFE introduces C$^2$AM, a bit-significance-weighted conducting-
cell activity metric that predicts output deviation and inference accuracy degradation under FeFET device variation. Guided by C$^2$AM, CAFE applies differential weight and activation encoding to eliminate sign-extension-induced conducting-
cell amplification. To balance robustness and cost, CAFE performs type-wise encoding enumeration, layer-wise NSGA-II search, and post-GA
pruning to allocate robust encodings where the robustness-cost trade-off is favorable. Across representative
vision and
language workloads, CAFE reduces C$^2$AM by up to $28.6\times$; in the main deployment study, it improves accuracy over two's-complement CIM by more than 87 percentage points and approaches full-differential robustness at $1.86$-$2.78\times$ normalized cost, compared with $3.06\times$ for uniform full-differential encoding.
Read the full abstract ▾
All authors Wenshuai Yao, Wenyong Zhou, Hanyong Shao, Zhiyuan Ning, Ru Huang, Kechao Tang
Computation and Language
Share the Symbol, Not the Vector: Training-Free Fact Communication Across Language Models
Xin Li, Mengbing Liu, Hao Jiang et al. (+5 more)
Multi-
agent systems allow
language models to solve tasks collaboratively by sharing complementary information. These systems typically communicate through text, while recent approaches also explore exchanging internal model states. However, sharing these states across architectures often requires learned translators or assumptions about model compatibility. We introduce SYNC (Symbol-Indexed Neural Communication), a word-indexed interface that connects heterogeneous models without fine-tuning or a learned translator. From descriptions only it can see, the sender selects words from a shared list and sends their indices for each object, without seeing the questions. The receiver writes the described facts into its hidden states using its own word directions, vectors fitted once from its activations. We test selective use by swapping one attribute between two objects and requiring correct answers about both changed and unchanged attributes before and after the swap, four answers in total. We choose an early write layer on four development receivers and then fix it. With three different senders and nine newer receivers from five families, four-answer success on new scenes reaches 72.0-98.3%, up to 96 percentage points above middle-layer writing, and the two largest receivers match plain text. A task-free probe predicted in advance which depths each new receiver can use (45 of 45 cases). Without retuning, messages listing every fact keep 89.6-100% success under new layouts, and sender messages reach 23.9-64.0% on a landmark task with multi-
token symbols, below text but from 0% without a message. These results show that shared word indices and receiver-local directions can support selective fact use across model families without additional training.
Read the full abstract ▾
All authors Xin Li, Mengbing Liu, Hao Jiang, Xin Gao, Annan Wang, Xingwei Qu, Yichi Zhang, Chau Yuen
Artificial Intelligence
C3: Rethinking Process Supervision via Confidence-Guided Credit Correction in Multi-Turn Reinforcement Learning
Ai Jian, Haoran Pan, Eryu Guo et al. (+5 more)
Large
language models are increasingly trained as multi-turn
agents that interact with external tools. However, outcome-only reinforcement learning can produce a form of misguided reinforcement: even on successful trajectories, undesirable local behaviors may receive positive
token-level advantages and be favored by the policy update. To address this issue, we propose Confidence-Guided Credit Correction (C$^3$), a plug-in method for local credit correction. C$^3$ identifies spans corresponding to undesirable behaviors and selectively corrects positive credit after advantage estimation, with the correction strength adaptively controlled by the behavior policy's confidence in the corresponding behavior, while leaving the task reward and original credit estimation unchanged. Across multiple multi-turn
benchmarks, C$^3$ improves performance under both {critic-based and critic-free reinforcement learning methods}. Injecting the same behavioral signals as turn-level or outcome rewards does not consistently improve performance. Our results show that local credit correction provides an effective form of process supervision for outcome-driven RL.
Read the full abstract ▾
All authors Ai Jian, Haoran Pan, Eryu Guo, Haojin Yang, Jinghan He, Xiaoyun Zhang, Jiangbo Pei, Peiyu Liu
Artificial Intelligence
ReFormBench: Benchmarking the Stability of Response-Conditioned Format Correction in Large Language Models
Tianxiang Gao, Yahan Li, Chenlu Guo et al. (+3 more)
Reliable use of large
language models requires responses to satisfy formatting requirements across changing instructions. Standard compliance scores do not distinguish preserving a model's observed format from correcting it, or reveal whether that correction holds across variants. We introduce ReFormBench, a
benchmark that uses each model's unconstrained response to the same question as its formatting baseline. It links targets by feature and require/forbid mode, evaluating their instantiated requirements across variants. ReFormBench comprises 5,000 difficulty-screened three-constraint test instances derived from 910 source questions and covering 66 formatting features. TCPR measures complete instruction compliance, while EMCR measures individual and joint correction of targets opposed to the annotated baseline state. Across ten models, EMCR ranges from 34.04% to 64.72%, and the highest three-target correction estimate is 50.02%. Compliance and correction scores yield different model rankings and task-level profiles. A prompting experiment on Qwen3.5-9B improves both metrics, and the catalog covers over 95% of extracted instances on four additional models. ReFormBench makes response-conditioned correction across instruction variants a measurable dimension of format following. The code and data are available at https://anonymous.4open.science/r/ReFormBench/.
Read the full abstract ▾
All authors Tianxiang Gao, Yahan Li, Chenlu Guo, Diana Inkpen, Yi Chang, Yuan Wu
Machine Learning
Annealed Lévy Diffusion via Gaussian Surrogate Reverse Dynamics
Yuling Jiao, Lican Kang, Jerry Zhijian Yang et al. (+2 more)
Gaussian
diffusion models offer a practical framework for generative modeling. Denoising Lévy Probabilistic Models (DLPM) introduce heavy-tailed perturbations with a fixed tail index throughout denoising. We introduce Annealed Lévy
Diffusion (ALD). ALD varies the stability index $\alpha(t)$ to combine heavy-tailed exploration with Gaussian refinement. Our marginal-first formulation represents stable noise as a scalar Gaussian scale mixture. This formulation enables standard Gaussian noise-prediction training with one additional scale input. We study two sampling processes. ALD-renoise estimates the clean sample and injects fresh marginal noise. ALD-posterior preserves dependence between successive states through an accumulated conditional variance and a Gaussian bridge update. Both samplers reuse the same trained predictor with different scalar inputs. We evaluate ALD on four 2D
benchmarks and an imbalanced nine-mode mixture. We also examine training efficiency and the effects of prediction perturbations on clipped Holtsmark data. Additional experiments evaluate MNIST and CelebA64 generation and CIFAR-10LT augmentation. ALD preserves local geometry on the evaluated light-tailed and
manifold-structured targets.
Read the full abstract ▾
All authors Yuling Jiao, Lican Kang, Jerry Zhijian Yang, Cheng Yuan, Ruizhe Zhang
Information Theory
Efficient construction of subspace design codes over constant alphabet
Shu Liu
Subspace-design codes form a central unifying framework in coding theory, connecting probabilistic existence results and explicit algebraically structured constructions. The two core families are folded Reed-Solomon codes and univariate multiplicity codes, both possessing the subspace-design property. These codes reach list-decoding capacity with
polynomial-size lists, but their alphabet size grows with code length and hurts practical efficiency. Goyal, Guruswami, and Hsieh achieved a major breakthrough: they constructed the first explicit subspace-design codes over constant-size alphabets via the Alon-Edmonds-Luby expander framework, settling an open problem and showing subspace-design properties can hold without large alphabets. Despite recent progress, constructing subspace-design codes with low-complexity efficient encoding remains a critical open challenge. This work gives an explicit construction of r-dimensional subspace-design codes over a constant alphabet whose size grows exponentially with r. By comparison, Goyal et al. (FOCS 2026) built r-dimensional subspace-design codes with alphabet size doubly exponential in r squared. Our construction is computationally efficient: encoding scales quadratically with block length and linearly with dimension r in field operations. We use modified algebraic geometry codes, replacing rational evaluation points with higher-degree places to obtain a valid additive code. To confirm parameter bounds, we use Moore
matrices to analyze determinants with many zero entries. We also generalize univariate multiplicity codes, originally built from Reed-Solomon codes, to algebraic geometry codes, and prove these AG-multiplicity codes achieve optimal parameters.
Read the full abstract ▾
Game Theory
PPAD-Completeness of Contiguous Envy-Free Cake Cutting with Additive Valuations
Yasushi Kawase, Bodhayan Roy and Mohammad Azharuddin Sanpui
We prove that computing a complete contiguous $\varepsilon$-envy-free cake allocation is PPAD-complete for normalized rational piecewise-constant additive valuations. The hardness holds even when $\varepsilon$ is given in unary, and even when every density takes only two values, which are the same for all
agents, and is piecewise constant with at most six breakpoints. As a consequence, computing an exact contiguous envy-free allocation is also PPAD-complete, and the hardness holds under the same restrictions on the densities. Our key ingredient is to assign prices to the pieces so that, in every approximately envy-free allocation, all prices are nearly equal, regardless of how the pieces are assigned to the
agents. We further show that, for every fixed integer $c\ge1$, computing a contiguous EF$c$ allocation of indivisible goods on a path is PPAD-complete for additive valuations, and the hardness holds even for binary valuations in which each good is valued by exactly one
agent and all
agents value the same number of goods.
Read the full abstract ▾
Machine Learning
Function-Space Temporal Self-Distillation for Policy Optimization
Aryan Das, Arnab Bhattacharya and Vinay Kumar Verma
Reinforcement Learning with Verifiable Rewards (RLVR) improves
reasoning in
language models, but scalar outcomes provide coarse supervision over response trajectories. Self-
distillation offers denser
token-level guidance by comparing an unassisted policy with a feedback-informed self-teacher, yet the teacher evolves with the student, creating unstable targets and motivating additional regularization. We introduce Function-Space Policy Optimization (FSPO), a single-policy framework that combines current privileged adaptation with function-space temporal consolidation. FSPO stores sparse historical next-
token distributions as fixed temporal targets, providing temporal separation without maintaining a persistent teacher model. It further introduces privileged disagreement correction to explicitly suppress locally overvalued actions, reliability-adaptive grounding that strengthens reference supervision when self-generated evidence repeatedly fails, and quality and coverage-aware temporal
memory that retains verified behaviors and improves privileged demonstrations. Across
reasoning and tool-use
benchmarks, FSPO achieves the highest average accuracy under a 5-hour training budget, improving over the strongest baseline by approximately 4% points on average while reducing peak
memory from about 70 GB to 56 GB on Olmo3-7B-Instruct.
Read the full abstract ▾
Computation and Language
Interlock: From Local Correctness to Task Completion in Long-Horizon Agents
Linji Hao, Yanji He, Zihan Wang et al. (+6 more)
Large
language model
agents increasingly undertake long-horizon tasks in complex environments characterized by fragmented evidence, partially completed states, and dependencies across resources and artifacts. Existing
agents may satisfy individual requirements while failing to maintain these relationships, producing locally correct but incomplete outcomes. These failures arise because task completion depends on relationships among environmental evidence, consequential decisions, and required effects. To address this completion gap, we propose Interlock, a framework for task synthesis that represents each task as a typed completion graph. Grounding edges connect public evidence to decisions, coupling hyperedges impose joint constraints across components, and realization edges connect decisions to all required downstream effects. Interlock compiles this graph into a resettable workspace, a public request, and an evaluation rubric. A source-coverage review checks whether the original requirements survive generation, while a public-input review checks whether the rubric is supported by the materials available to the solver. An
agent-as-judge inspects execution artifacts and runs verification scripts, retaining trajectories judged to satisfy all mandatory requirements. To evaluate training utility, we fine-tune two Qwen3.6 backbones on their own accepted trajectories. Across the two backbones, training improves AutomationBench task pass rates by 4.00-4.50 percentage points, JobBench weighted scores by 3.20-6.64 points, and Harvey LAB criterion pass rates by 3.89-4.16 percentage points. These results demonstrate the training utility of the synthesized experience across external task environments.
Read the full abstract ▾
All authors Linji Hao, Yanji He, Zihan Wang, Hansi Yang, Jiayuan Zhang, Hongyan Hao, Qi Gu, Yan Feng, Han Wu
Machine Learning
Beyond Distribution Matching: Selective Margin Preservation for Supervised Fine-Tuning
Yuxuan Wang, Guangxiang Zhao, Xinyu Tan et al. (+6 more)
Supervised fine-tuning (SFT) changes logit margins among non-target
tokens at teacher-forced prefixes. Matching a local reference distribution keeps those probabilities and also penalizes margin expansions. We ask whether a soft auxiliary can preserve selected local non-target margin relations without freezing that distribution. We introduce Selective Rank-Preserving SFT (SRP-SFT), a soft margin target: a hinge on reference-scaled lower bounds for pairs from the reference's top-$K$ non-target
tokens, applied at fixed teacher-forced prefixes. The hinge stops once the requested bound is met. We derive the KL cost of violating a margin, characterize the feasible region and its conditional utility, and give a finite-step condition for reducing aggregate violations. In one-epoch experiments on Qwen3-4B-Base and UltraFeedback, this target raises MATH-500 and code-generation scores over CE and LP-SFT at all three training seeds. At seed 1234, MATH-500 pass@1 rises from 49.56% to 54.56% and the four-metric code mean rises from 65.91% to 69.50% relative to LP-SFT. Ranking controls, held-out cache diagnostics, sensitivity sweeps, and six additional backbones show where these score changes appear.
Read the full abstract ▾
All authors Yuxuan Wang, Guangxiang Zhao, Xinyu Tan, Yahui Han, Xinxiang Yin, Zhonghai Wu, Xiangzheng Zhang, Lin Sun, Tong Yang
Machine Learning
Enhancing Latent World Models with Associative Memory
Yuwei Sun and Siyu Zhu
World models trained via latent dynamics offer a scalable path for embodied planning, yet existing methods suffer from representational collapse, computational overhead, and limited long-horizon capability. We introduce a
memory-enhanced latent world model that augments JEPA-style prediction with a content-addressable
memory bank. Our approach learns high-level representations directly from observations, operating at multiple temporal scales within a shared latent space, and conditions predictions via adaptive layer normalization. To prevent collapse and ensure effective
memory usage, we design two complementary losses that encourage slot diversity and balanced temporal utilization. Experiments on PushT, Tworoom, Reacher, and OGBCube demonstrate that our method achieves state-of-the-art performance with a lightweight architecture, outperforming conventional latent world models on long-horizon planning tasks.
Read the full abstract ▾
Computer Vision
MicroSDF: Microfacet-Driven Hybrid Neural SDFs for Mixed-Reflectance Surface Reconstruction
Lejia Ye, Yuhua Xu, Yulan Guo et al. (+2 more)
Accurate 3D reconstruction in real-world environments remains a significant challenge due to the coexistence of reflective and non-reflective surfaces, which pose distinct modeling demands. Existing methods often treat these surface types separately, limiting their generalizability and physical plausibility. To bridge this gap, we propose MicroSDF, a novel neural implicit framework that facilitates geometry and reflectance modeling through microfacet theory. Our approach incorporates three core innovations: (i) a microfacet-guided geometry model that extracts multi-scale surface normals (macroscopic and microfacet) from a signed distance field (SDF), regularized by a proposed microfacet normal consistency loss to enforce physically plausible surface orientations; (ii) an enhanced dual-branch color model, where the specular branch leverages the microfacet normals to model high-frequency reflectance, and the vanilla branch, unlike prior works, uses reflection direction (instead of viewing direction) to better model diffuse and low-frequency specular components; and (iii) a detection-guided color blending strategy that adaptively fuses the color outputs based on reflection priors, providing more physically intuitive blending than implicitly learned blending weights. Combined with a tailored multi-stage optimization scheme, the proposed MicroSDF achieves robust and high-fidelity reconstruction across reflective and non-reflective surfaces. Extensive experiments on DTU, Shiny Blender, Ref-NeRF, and DeepVoxels
datasets demonstrate state-of-the-art performance, establishing a new direction for physically grounded neural reconstruction.
Read the full abstract ▾
All authors Lejia Ye, Yuhua Xu, Yulan Guo, Lian Xu, Xiaohu Zhang
Artificial Intelligence
MCAIR: Monitoring and Correcting Agent Unfaithfulness via Internal Representations
Yan Xu, Dandan Song, Luan Zhang et al. (+8 more)
Large
Language Model (LLM)-based
agents have demonstrated remarkable capabilities in completing complex tasks through multi-step
reasoning and tool interactions. However, recent studies have revealed that LLM-based
agents can exhibit unfaithful behaviors, where their final reports fail to faithfully reflect their actual execution trajectories. Specifically, when
agents fail to accomplish tasks through the intended sources or procedures, they may resort to alternative sources or strategies while failing to disclose such deviations, leading users to incorrectly believe that the tasks have been completed according to the original requirements. We refer to this specific form of
agent unfaithfulness as
Agent Completion Unfaithfulness. Detecting and mitigating
agent completion unfaithfulness is critical yet remains largely unexplored. In this work, we propose MCAIR, a runtime monitoring and correction framework that leverages internal representations of LLM-based
agents. MCAIR uses multi-step internal representations as inputs to train a risk-aware probe, enabling online detection of potential completion unfaithfulness during execution. Furthermore, MCAIR introduces a risk-guided correction loop that
prompts agents to review their execution history and mitigate potential inconsistencies between their execution trajectories and final reports. Additionally, we construct ACUD, a
dataset for
Agent Completion Unfaithfulness detection that provides step-level execution traces, step-level internal representations, and consistency annotations for training and evaluating runtime detection probes. Experiments demonstrate that MCAIR outperforms LLM-as-a-judge baselines, generalizes across
prompts and tasks, and effectively reduces
agent completion unfaithfulness.
Read the full abstract ▾
All authors Yan Xu, Dandan Song, Luan Zhang, Jun Yang, Ke Duan, Yuhang Tian, Yading Li, Xudong Li, Xing Pei, Guangyuan Feng, Chenhao Li
Sound
TVPara: Paralinguistic Captioning of Expressive TV-Series Speech in Complex Acoustic Environments
Ziyang Zhang, Wenyi Yu, Wen Wu et al. (+2 more)
Large audio-
language models (LALMs) struggle to parse paralinguistics (e.g., emotion, pace, pitch) in
speech that combines intense emotion with complex acoustic environments. Strengthening this ability calls for training data that reflects such conditions. However, existing corpora rely heavily on studio-recorded
speech, offering limited emotional and acoustic diversity. To address this gap, we introduce TVPara, a paralinguistic captioning
dataset built from TV series.
Speech in TV series often carries diverse emotional expression and co-occurs with scene-specific background sound, providing expressive emotion and complex acoustic environments at scale. Constructed via LALM pre-annotation and human correction, TVPara includes two tasks: Single-Utterance (~492h) and Multi-Utterance (~213h) Paralinguistic Captioning. Fine-tuning open-source LALMs on TVPara yields an average relative improvement of 31.26% in paralinguistic understanding under complex acoustic environments. The gains further generalize to an unseen TV series and to cleaner, cross-domain
speech.
Read the full abstract ▾
All authors Ziyang Zhang, Wenyi Yu, Wen Wu, Xuenan Xu, Chao Zhang
Robotics
ACRO: Actor-Critic Rollout Orchestration
Junhoo Lee, Seungyeon Kim, Baekseung Kim et al. (+4 more)
Executing a
vision-
language-action (VLA) policy involves deciding when to continue an attempt and when to intervene to improve its chances of success. We introduce ACRO, an Actor–Critic rollout orchestration layer that makes these decisions for a fixed VLA. ACRO seeks interventions that offer a more promising continuation, are physically feasible, and leave sufficient time to complete the task. A Critic learned from policy rollouts estimates success prospects to decide when to intervene and select a re-entry target along the executed trajectory. Trajectory Retraction shortcuts the visited path to return the
robot to that target, where the same VLA resumes execution from a fresh observation. We evaluate ACRO with GR00T N1.7 and $\pi_{0.5}$ across SimplerEnv, RoboCasa, and real-
robot manipulation. Under the same physical execution budget, including all return motion, ACRO improves success by 10.4, 7.3, and 21.7 percentage points, respectively. It also completes additional tasks as the execution budget grows. These results show that controlling when and where a policy resumes can turn its existing capabilities into more successful task executions. Project page: https://junhoo.me/acro
Read the full abstract ▾
All authors Junhoo Lee, Seungyeon Kim, Baekseung Kim, Minkyu Kim, Suhyun Jeon, Jimyeong Kim, Nojun Kwak
Computer Vision
Remember, Revisit, Revise: Scaffold Memory for Long-Horizon 3D Geometry
Soumick Sarker and Mengmi Zhang
Geometry foundation models estimate camera poses and 3D scene structure from
video sequences, but maintaining consistent reconstructions over long horizons remains challenging. Feed-forward models process long sequences as independent, fixed-length frame windows and align their predictions, causing pose and reconstruction errors to accumulate across windows. Streaming models retain information from past frames to inform future predictions, but cannot revise earlier estimates when later observations reveal errors. To address this, we introduce Scaffold
MemOry for Revision (SMORE), a framework equipping frozen geometry foundation models with a revisable external
memory for long-horizon inference. Inspired by hippocampal associative
memory in biological
brains, which links spatial context with sensory experience, SMORE associates where an observer is with what it observes, enabling past observations to be stored, retrieved, verified against new evidence, and revised when inconsistencies are detected. We evaluate SMORE with eight competitive geometry models on five
datasets spanning camera pose estimation, multi-view depth estimation, 3D point-cloud reconstruction, simultaneous localization and mapping (SLAM), and novel view synthesis. Across all evaluated models, SMORE consistently improves long-sequence pose estimation, reduces multi-view depth error by up to 58%, reduces Chamfer distance for 3D point-cloud reconstruction by up to 43%, and achieves average trajectory error as low as 2.9 cm in long-horizon SLAM. By retaining corrected poses and observations, SMORE further improves the fidelity and spatial consistency of large-scale 3D scene reconstruction. These results establish revisable external
memory as a flexible interface for extending pretrained geometry models beyond fixed-context prediction toward iterative, error-correcting inference over long visual sequences.
Read the full abstract ▾
Hardware Architecture
ESL-former: Event Sparse Linear Transformer for FPGA-Accelerated Malware Detection
Jun Yang, Yumeng Cao, Yingxuan Xiao et al. (+2 more)
Transformer based intrusion detection has shown strong potential for identifying unknown malware variants, but its deployment on resource constrained edge devices remains difficult due to the high computational and
memory cost of self
attention. This paper presents an event sparse Linear
Transformer framework for malware detection on FPGA edge platforms. Instead of relying on an explicit
attention matrix, the proposed method derives
token and channel importance directly from the accumulated key value state of Linear
Transformer. A contribution aware scoring function is introduced to measure the perturbation of each
token or kernel channel to the linear
attention state, allowing redundant
tokens and low contribution channels to be removed without constructing quadratic
attention maps. To translate sparsity into practical hardware acceleration, the proposed design further replaces conventional binary mask based execution with a Top K active
token buffer and a hardware compaction unit. The selected active
tokens and channels are reorganized into dense fixed length data streams, enabling downstream processing elements to execute regular multiply accumulate operations with reduced redundant
memory access and control overhead. This design is suitable for low power FPGA based malware detection, where both latency and on chip resource usage are critical. Experimental evaluation demonstrates that the proposed sparse Linear
Transformer can reduce hardware cost while preserving malware classification accuracy.
Read the full abstract ▾
All authors Jun Yang, Yumeng Cao, Yingxuan Xiao, Changhong Li, Shangru Zhou
Artificial Intelligence
Learning When to Trust Medical Knowledge: Regression-Safe Routing for Clinical Reasoning
Hui Zhang, Yujia Zeng and Yuhao Xin
Clinical
reasoning LLMs need external medical knowledge, but retrieved evidence and
reasoning chains can be outdated, poisoned, or hallucinated. Harmful knowledge can cause regression: changing a correct answer into an incorrect one. We construct a medical knowledge-poisoning
benchmark covering retrieved evidence and
reasoning chains, with seven attack families filtered by a three-judge "subtle-but-wrong" vote and paired clean exams that separate poisoning effects from question difficulty. No fixed knowledge-use strategy is robust across these settings: strong RAG methods trade robustness to poisoned evidence against accuracy when evidence is useful. We formulate knowledge use as per-instance routing and introduce Med-TrustRouter, a lightweight controller that keeps the solver frozen. From leakage-free runtime signals, it estimates each action's expected correctness gain and uncertainty, preserving the base answer unless another action is confidently better. Across seven medical
reasoning settings, Med-TrustRouter achieves 78.9 macro and 69.2 worst-case accuracy, matching the strongest competitor on macro accuracy while substantially improving the worst-case floor. Its gains transfer across solvers and evidence judges, unlike a hand-coded router using the same signals. Similar performance across linear, tree, and neural action-value heads suggests that the benefit comes from routing rather than
estimator complexity. These results support learning when to trust external knowledge for robust clinical
reasoning.
Read the full abstract ▾