paperlist.ai

AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

arXiv

Deconstructing Off-Policy Ratios: Entropy-Scaled Trust Regions for Asynchronous Reinforcement Learning

guanqun zhao, Zijun Xie, Binbin Zheng, Enlei Gong, Jiafeng Lu, Yehan Yang, Aoqi Hu, Zeyu Chen

Asynchronous reinforcement learning (RL) accelerates large language model (LLM) post-training by overlapping rollout generation with policy optimization, but the resulting stale, off-policy data can destabilize optimization and ultimately cause policy collapse. Existing methods typically retain or discard tokens based solely on the magnitude of their importance ratios, applying the same threshold uniformly across token positions. In this work, we reveal that the natural scale of the importance ratio varies systematically with token entropy. Under asynchronous dynamics, this entropy-ratio scaling dictates two distinct phenomena: at low entropy, the inherent train-inference discrepancy is drastically amplified into substantial sampling noise; at high entropy, in-flight weight updates naturally induce pronounced, legitimate exploratory deviations. Consequently, magnitude-only correction inadvertently admits the amplified noise while strictly masking out the essential exploration triggered by in-flight updates. To address this, we propose the Entropy-Scaled Trust Region (ESTR), which scales each token's off-policy deviation by its local entropy, requiring no auxiliary forward passes or explicit version-switch detection. Across long-horizon agentic tasks and mathematical reasoning benchmarks, ESTR consistently outperforms existing asynchronous methods and achieves the best train-inference consistency. It reaches $37.34$ avg@1 on BrowseComp-Plus and $95.69$ on multi-turn GSM8K, matching synchronous GRPO while achieving a $2.6\times$ speedup.

arXiv

Interaction Dynamics Modeling and Predictive Control for Safe Steerable Catheter--Tissue Interaction

Yongyan Cao

Safe steerable catheter control is fundamentally a problem of interaction dynamics: the tip must follow a planned motion, remain compliant against moving tissue, reject friction and hysteresis, and respect a clinically meaningful never-exceed contact-force bound. We formulate catheter--tissue interaction dynamics in the scalar tip-normal coordinate of a single-segment single-tendon catheter. A partial-physics feedforward cancels only the reliable nominal bending dynamics, exposing a configuration-invariant linear interaction-dynamics model whose input gain varies through the scalar catheter inertia. A predictive optimizer then regulates this interaction state subject to hard contact-force, tendon-force, and curvature constraints. An augmented Kalman filter compresses contact, friction, and modeling error into one sensor-free disturbance state, giving nominal offset-free regulation in free space while leaving force safety to the explicit constraint. The unconstrained and disturbance-free limit recovers classical catheter impedance as a special realization of the same interaction dynamics, rather than as the main design object. In a MuJoCo distributed-compliance simulation of an eight-link tendon-driven catheter, disturbance augmentation cuts free-space approach error by 90\%, and only the force-constrained predictive interaction-dynamics controller reconciles tracking with the 0.5\,N bound: the unconstrained controller drives contact force to 0.60\,N against a penetrating target, while the constrained one holds 0.47\,N at identical tracking. These results show that offset-free motion regulation and contact-force safety are coupled interaction-dynamics objectives, and that the explicit predictive constraint resolves their tension under stiff tissue contact. The bound also holds under $0.5$\,mm, $1.2$\,Hz cardiac motion. Hardware validation is future work.

arXiv

Agentic Synthesis against Counterexample-Supplemented Sketches

Muness Castle, Eric Rubeck

Coding agents can fix a failing example without preserving the domain rule that made it fail. We present agentic synthesis against counterexample-supplemented sketches, a repository-native method for systems whose policy is discovered during implementation. A human starts with a partial sketch, and a coding agent compiles a replaceable projection. When simulation exposes missing or mistaken policy, an operator approves the corrected behavior and the minimum general rule the case authorizes. Every Developer call names its change authority and the rules, holes, anchors, and approved behavior that must survive. Conflict or ambiguous permission leaves the files unchanged and produces a clarification question. A complete archive preserves provenance; a curated regression set gates distinct boundaries. Before another candidate is revealed, the active case and curated regressions must pass both deterministic approved-output comparison and a separate review against the current sketch. Periodic clean regeneration tests whether the sketch carries the learned policy. We demonstrate the method with CatSynth, a captured synthetic application. In one open-world run with GPT-5.4-mini, 8 of 14 frozen candidates became counterexamples. Under the corrected protocol, replay-all, evolved-sketch rebuild, and retained Sketch-CE each passed all 8 accepted cases. They passed 14, 17, and 16 of 21 withheld cases, respectively. Sketch review rejected premature empty-input and tag policies and restored dropped anchors; adjudicated reviewer errors did not become policy. One model and one reveal order cannot establish general correctness or superiority. On this suite, the second check exposed drift hidden by deterministic replay, and the reviewed sketch passed three more withheld cases than raw example replay.

arXiv

A cubical formalisation of topos causal models: intervention, forcing, and a contextuality obstruction

Karen Sargsyan

Topos causal models recast causal inference inside a topos: a causal world is a presheaf, an intervention is a sub-model named by a characteristic map into the subobject classifier $\Om$, and reasoning is Kripke-Joyal forcing in an intuitionistic internal language. We give the first axiom-free machine-checked account of this 1-topos core, in Cubical Agda over a previously verified probability monad and do-calculus; the framework is otherwise developed on paper, with central claims stated rather than proved. Three of our results go beyond faithful transcription. We exhibit a contextuality obstruction the programme does not treat: pairwise-consistent local causal data with no global model, detected by a degree-one holonomy class. We delimit the claim that interventions are modelled by the subobject classifier: an intervention and an observation name the same subobject, so $\Om$ fixes the target of a do-operation but not the operation itself, which is surgery on the kernels --- where, on a confounder, the interventional and observational laws differ. And we settle the modal unit --- inflationarity is derivable from $j\top = \top$ and naturality, not a fourth axiom. We also machine-check the classifier of sieves with its classification theorem, the pullback collating local mechanisms, and the Kripke-Joyal forcing clauses. The development assumes no axioms and typechecks under Agda's \texttt{--safe} flag, with the ordered field discharged at $\mathbb{Q}$; type-level sheafification and a directed do-calculus are future work.

arXiv

StructureClaw: Traceable LLM Agents and an Executable Benchmark for Structural Engineering Workflows

Sizhong Qin, Yi Gu, Yao Jiang, Ao Cai, Changjian Zhou, Shaoxuan Shuai, Jiachang Wang, Tianhao Shen, Yueqiang Li, Xinhao Li, Li Zeng, Yueshi Chen, Dachen Gao, Genrong Xu, Wenjie Liao, Xinzheng Lu

Addressing a structural-engineering request requires more than a single answer; it requires a chain of interdependent artifacts: interpreted requirements, a computable model, validation records, solver outputs, applicable engineering checks, and a final report. Evaluations centered on question answering or script generation may therefore reward fluent outputs even when the underlying workflow is incomplete, inconsistent, or non-executable. We present StructureClaw, an artifact-centered workbench in which LLM agents operate through governed engineering skills, typed tools, shared artifact state, and local analysis backends, together with StructureClaw-Bench, an executable benchmark of 150 controlled scenarios spanning standard workflows, interactive robustness, and multimodal structural-model reconstruction. Its analyzable standard and multimodal cases require both strict one-to-one structural-model matching and numerical-response agreement with frozen reference responses from the selected analysis engine; interactive cases instead require positive clarification or recovery evidence together with safe non-execution when appropriate. A trial succeeds only when every fixture-required assertion passes. Across nine text-agent configurations, generic-only execution passed the model-artifact check in 87.0% of retained outcomes but achieved only 22.0% E2E Success, whereas automatic StructureClaw reached 82.9%. Interactive and multimodal evaluations further identify semantic state consistency and executable model reconstruction as the dominant remaining bottlenecks. The code and benchmark are available at https://github.com/structureclaw/structureclaw.

arXiv

Jetson-PI: Towards Onboard Real-Time Robot Control via Foresight-Aligned Asynchronous Inference

Zebin Yang, Qi Wang, Yunhe Wang, Xiurui Guo, Bo Yu, Shaoshan Liu, Jiafeng Xu, Hao Dong, Meng Li

Vision-Language-Action (VLA) models have achieved impressive performance on diverse embodied tasks. However, deploying VLA models on low-power onboard devices, such as the Jetson Orin, remains challenging due to their high computational complexity, which leads to substantial inference latency and low control frequency. Asynchronous inference can partially mask this latency by parallelizing action execution and subsequent inference, but it introduces two critical issues: perception-execution misalignment and long reaction time. In this paper, we propose Jetson-PI, a method for efficient VLA deployment on onboard devices via Foresight-Aligned Asynchronous Correction. To address misalignment, we train a lightweight future correction module that predicts future environment representation conditioned on committed actions, enabling the action expert to directly predict actions from the future time step. To reduce reaction time, we introduce confidence-based scheduling optimization that adaptively balances VLM and action expert invocations, complemented by system-level accelerations including CUDA graph reuse, GPU-resident intermediate buffering, and flow unrolling. Extensive experiments demonstrate that Jetson-PI achieves 8.66x and 5.41x improvements in control frequency compared with naive PyTorch and vla.cpp on NVIDIA Jetson Orin, while outperforming VLASH by 14.8\% in average success rate on the LIBERO benchmark. The code of our asynchronous algorithm is available on https://github.com/PKU-SEC-Lab/Jetson-PI, and our efficient llama.cpp-based inference engine is available on https://github.com/PKU-SEC-Lab/Jetson-PI-Edge.

arXiv

PCBWorld: A Benchmark Environment for Engine-Grounded PCB Design Automation

Hyungseok Song, Junseok Park, Won-Seok Choi, Seohui Bae, Han-Seul Jeong, Youngjoon Park, Soonyoung Lee

PCB routing is the task of connecting the nets of a board with copper traces under strict design rules, yet learning-based methods still lag behind rule-based routers. We introduce PCBWorld, an open-source engine-grounded PCB routing environment built on KiCad, an electronic design automation (EDA) engine. As a human engineer does, agents in PCBWorld interactively route a board through the engine's native operations, guided by its Design Rule Check (DRC) feedback. The environment supports both RL and tool-using LLM agents. Alongside the environment, PCBWorld-Bench provides three board datasets in the native .kicad_pcb format, two controllable synthetic generators and 679 real open-source boards. It scores any completed board with eight engine-checked evaluation metrics, regardless of the routing method. In our experiments, agents in PCBWorld consistently outperformed grid-action RL policies and open-loop LLM baselines, and an RL policy trained only on synthetic boards transferred zero-shot to real boards, approaching rule-based routers.

arXiv

Branch-JEPA: Finite-Support Predictive Distributions for JEPA World Models

Zhi Song, XiMing Xing, Zhenchao Tang, Hanbo Huang, Jiehui Huang, Weilong Yan, Tianxu Lv, Minghao Yang, Zhongzheng Niu, Bing He, Lusheng Wang, Jianhua Yao

Joint-embedding predictive architectures (JEPAs) learn dynamics by predicting future observations in representation space. Yet most JEPA world models return one latent successor, even when hidden intent, partial observation, or stochastic dynamics make several futures plausible. We introduce Branch-JEPA, which replaces this point-valued transition with a context-weighted finite set of latent successors. Every branch is decoded independently, and the complete set is retained at inference. The architecture supports two complementary training regimes: specialization for recovering separated successors and full-set Energy-Score training for distributional fidelity. In a locked five-seed evaluation on the Argoverse~2 official validation split, full-set training improves trajectory Energy Score by $5.8$--$6.5\%$ and probability-weighted trajectory distance by $9.3$--$10.4\%$ over matched-$K{=}6$ assignment and transport objectives, while retaining $5.36$ endpoint-deduplicated effective branches. In a parameter-exact official-validation comparison, latent branching retains $10.3\%$ more effective modes and improves Energy Score, expected ADE, and Brier in all five paired seeds over branching only at the output decoder; every paired 95\% interval excludes zero. In an OGBench graph audit, Branch-JEPA increases teleport verified-route existence to $19.2\%$ versus $3.9\%$ for the MDN. Its raw-support advantage also persists with 29-D state and RGB observations. Together, latent branching preserves more distinct futures, while full-set scoring improves the quality of the resulting predictive distribution.

arXiv

Distributionally Robust Listwise Preference Optimization

Xudong Wu, Jian Qian, Pangpang Liu, Vaneet Aggarwal, Jiayu Chen

Existing robust preference optimization for language-model alignment mainly studies pairwise supervision and places robustness at the dataset, prompt, or preference-pair level. We instead study listwise preference optimization under ranking-label uncertainty: given a prompt and a candidate list, the observed ranking over that list may be ambiguous due to annotator inconsistency, near-ties, lossy rankwise feedback, or reward-model noise. We propose a pointwise total-variation robust Plackett--Luce objective that directly robustifies the ranking label conditional on the candidate list. The robust loss admits an exact decomposition into the nominal PL loss plus a worst-case PL correction, and the worst-case ranking is obtained by sorting current implicit scores in ascending order, reducing the inner maximization from $K!$ enumeration to $O(K\log K)$. This tractable structure yields strong offline and online optimization guarantees. In the offline fixed-list setting, the robust objective is convex and projected stochastic subgradient reaches global $ε$-suboptimality with $O(ε^{-2})$ sample complexity. In the online policy-induced setting, where candidate lists are generated by the current policy, we establish weak convexity and $\widetilde O(ε^{-2})$ Moreau-envelope stationarity. Experiments in offline LLM alignment show that the proposed robust correction largely preserves performance under clean labels and improves robustness under noise. In online alignment, it makes reward-model-ranked candidate expansion more reliable and improves both reward-model and external GPT-4 judge metrics.

arXiv

VFEAgent: A Multimodal Agent Framework for End-to-End Automated Finite Element Analysis

Jiachen Zhang, Junyi Lao, Chenghao Liu, Siyuan Liu, Shixin Wu, Linsen Zhang, Boyu Wang, Songfang Huang

Finite Element Analysis (FEA) serves as the cornerstone of modern engineering design. However, its workflow is inherently complex and relies heavily on domain expertise. Although recent efforts have integrated Large Language Models (LLMs) into FEA, existing approaches face limitations in handling multimodal inputs and executing complex tasks. To address these limitations, we propose VFEAgent, an end-to-end multi-agent system designed to automate FEA modeling and simulation directly from input images and problem descriptions. Our methodology integrates two core components: (1) a multimodal vision-language multi-agent pipeline that employs ReAct-driven reasoning to extract structured FEA specifications from heterogeneous inputs and (2) a verification-first code synthesis framework, incorporating robust self-debugging and fallback mechanisms to ensure executability and physical validity. We systematically evaluated the system across various engineering mechanics scenarios. The results demonstrate that VFEAgent achieves a high success rate in generating complete and physically valid simulations, outperforming LLM-based baseline methods in reliability and correctness. These findings validate the feasibility of automating the complete FEA workflow, highlighting the framework's potential to liberate engineers from tedious manual analysis.

arXiv

C-MIG: Multi-view Information Gain-based Retrieval-Augmented Generation for Clinical Diagnosis Reasoning

Yuwei Miao, Gen Li, Yunsheng Zeng, Xiandong Li, Yujin Wang, Siyu Chen, Luning Wang, Yunhao Qiao, Junfeng Wang, Jianwei Lv, Bo Yuan

Retrieval-augmented generation combined with reinforcement learning has shown promise for grounding large language models in trustworthy medical evidence. However, existing methods rely on exact-match binary rewards, which in clinical diagnosis cause two issues: (i) semantically relevant but non-verbatim steps receive zero signal, discarding valuable learning signals; and (ii) uni-dimensional rewards cannot effectively supervise heterogeneous reasoning capabilities. To address these issues, we propose C-MIG, a Multi-view Information Gain-based retrieval-augmented generation framework for Clinical diagnosis. C-MIG estimates information gain under a frozen reference model from two complementary views, retrieved-document and document-refinement, to jointly guide what to retrieve and how to refine, alleviating the issues of valuable reward signal loss and credit assignment. We further design a multi-subquery retrieval augmentation strategy that improves knowledge recall coverage in clinical diagnostic scenarios. Comprehensive experiments on four medical benchmarks demonstrate that C-MIG achieves the best performance among all RAG-RL methods on both in-domain and out-of-domain sets, and outperforms state-of-the-art general-purpose LLMs for clinical diagnosis.

arXiv

Asymmetric Generative Recommendation via Kronecker Residual Bridge and Multi-Faceted Hierarchical Quantization

Bin Huang, Xin Wang, Junwei Pan, Yongqi Zhou, Yifeng Zhou, Zhixiang Feng, Shudong Huang, Haijie Gu, Wenwu Zhu

Generative Recommendation (GenRec) models reformulate recommendation as a sequence generation task, representing items as discrete Semantic IDs used symmetrically as both inputs and prediction targets. We identify a critical dual-stage information bottleneck in this design: (1) the Input Bottleneck, where lossy quantization degrades fine-grained semantics, while popularity bias skews learned representations toward frequent items, and (2) the Output Bottleneck, where imprecise discrete targets limit supervision quality. To address these issues, we propose AsymRec, an asymmetric continuous-discrete framework that decouples input and output representations. Specifically, Kronecker Residual Bridge (KRB) maps continuous embeddings into the Transformer's hidden space via a Kronecker projection with a residual pathway, preserving semantic richness and improving generalization to infrequent items. Multi-faceted Hierarchical Quantization (MHQ) constructs high-capacity, structured discrete targets through multi-view and multi-level quantization with semantic regularization, preventing dimensional collapse while retaining fine-grained distinctions. Extensive experiments demonstrate that AsymRec consistently outperforms state-of-the-art generative recommenders by an average of 18.7%. Our project page is available at https://github.com/huangb23/AsymRec.

arXiv

Characterizing Readability Issue Patterns and the Role of Prompt Design in LLM-Generated Code

Hengzhi Ye, Fengyuan Ran, Weiwei Xu, Minghui Zhou

Large Language Models (LLMs) are increasingly changing how code is produced, but generated code still requires human review and validation before it can be adapted or integrated into real-world projects. This makes the readability of LLM-generated code a critical concern. Existing studies have mainly focused on functional correctness and task completion of LLM generated code, leaving open questions about whether it is readable, how its readability fails, and to what extent prompt design can improve it. We therefore investigate the readability of LLM-generated code. We first construct a readability assessment model that integrates textual, structural, program, and visual features. Using this model, we compare human-written code with code generated by representative frontier LLMs across 2,735 scenarios derived from World of Code (WoC) and LeetCode. We further characterize readability issue patterns using thematic analysis and examine prompt design associations through controlled prompt-variant experiments. Our results show that current LLMs produce code that is comparable to human-written code in overall readability. However, this aggregate similarity masks distinct issue patterns, including excessive complexity, redundant comments, and unknown API usage. Prompt analysis further shows that function signature, constraints, and style description are most strongly associated with code readability, although the overall role of prompt design remains bounded. These findings reveal latent readability debt in AI-assisted programming, identify prompt design as a lightweight starting point for improving generated-code readability, and motivate automated support for detecting and mitigating readability issues in future development workflows.

arXiv

Counterfactual Reasoning for Causal Responsibility Attribution in Probabilistic Multi-Agent Systems

Chunyan Mu, Muhammad Najib

Responsibility allocation -- determining the extent to which agents are accountable for outcomes -- is a fundamental challenge in the design and analysis of multi-agent systems. In this work, we model such systems as concurrent stochastic multi-player games and introduce a notion of retrospective (backward) counterfactual responsibility, which quantifies an agent's accountability for outcomes resulting from a given strategy profile. To allocate responsibility among agents, we utilise the Shapley value and formally show that this method satisfies key desirable properties, including fairness and consistency. Building on this foundation, we propose a formal framework that supports both verification and strategic reasoning in responsibility-aware multi-agent systems. Furthermore, by adopting Nash equilibrium as the solution concept, we demonstrate how to compute stable strategy profiles in which agents trade off responsibility against expected reward.

arXiv

ICU-Bench:Benchmarking Continual Unlearning in Multimodal Large Language Models

Yuhang Wang, Wenjie Mei, Junkai Zhang, Guangyu He, Zhenxing Niu, Haichang Gao

Privacy deletion requests often arrive sequentially, creating a continual unlearning challenge for deployed multimodal large language models (MLLMs). However, existing benchmarks mainly focus on static or short-sequence settings, offering limited support for evaluating continual privacy deletion on privacy-critical documents. To bridge this gap, we introduce ICU-Bench, an Identity-centric Continual Unlearning benchmark (pronounced ``I see you'') for privacy-critical multimodal documents. ICU-Bench contains 1,000 synthetic privacy-sensitive profiles from medical reports and labor contracts, comprising 9,500 document images, 16,000 question-answer pairs, and 100 sequential forget tasks. We further introduce history-aware evaluation protocols and sequence-aware metrics to assess current forgetting, historical forgetting preservation, retained utility, and stability throughout the unlearning sequence. Experiments with representative unlearning methods on two MLLMs reveal that methods effective on current targets often fail to preserve earlier forgetting or retained capabilities over long sequences. Some methods further obtain low forget accuracy through severe model degradation. These results expose long-horizon failure modes overlooked by conventional evaluations and highlight the need for multimodal unlearning methods explicitly designed for continual privacy deletion. Our code and benchmark are publicly available at: https://github.com/AstorYH/ICU-Bench.

arXiv

When to Vote, When to Rewrite: Disagreement-Guided Strategy Routing for Test-Time Scaling

Zhimin Lin, Yixin Ji, Jinpeng Li, Yu Luo, Dong Li, Junhua Fang, Juntao Li, Min Zhang

Large Reasoning Models (LRMs) achieve strong performance on mathematical reasoning tasks but remain unreliable on challenging instances. Existing test-time scaling methods, such as repeated sampling, self-correction, and tree search, improve performance at the cost of increased computation, yet often exhibit diminishing returns on hard problems. We observe that output disagreement is strongly correlated with instance difficulty and prediction correctness, providing a useful signal for guiding instance-level strategy selection at test time. Based on this insight, we propose a training-free framework that formulates test-time scaling as an instance-level routing problem, rather than allocating more computation within a single strategy, dynamically selecting among different scaling strategies based on output disagreement. The framework applies lightweight resolution for consistent cases, majority voting for moderate disagreement, and rewriting-based reformulation for highly ambiguous instances. Experiments on seven mathematical benchmarks and three models show that our method improves accuracy by 3% - 7% while reducing sampling cost compared to existing approaches.

arXiv

SymphonyGen: 3D Hierarchical Orchestral Generation with Controllable Harmony Skeleton

Xuzheng He, Nan Nan, Zhilin Wang, Ziyue Kang, Zhuoru Mo, Ao Li, Yu Pan, Xiaobing Li, Feng Yu, Xiaohong Guan

Generating symphonic music requires simultaneously managing high-level structural form and dense, multi-track orchestration, yet existing symbolic models often struggle with a "complexity-control imbalance" between scalability and steerability. We present SymphonyGen, a 3D hierarchical framework for contemporary orchestral generation, whose cascading decoders decompose the bar, track, and event axes, keeping decoding memory far below flat token streams and enabling conditioning at every structural level. A beat-quantized multi-pitch harmony skeleton, which may be user-written, analyzed, or model-generated, provides "short-score" conditioning, enabling outline control while producing orchestral textures. The model is refined with reinforcement learning against a cross-modal acoustic reward from CLaMP 3 audio embeddings, and a dissonance-averse sampling algorithm suppresses unintended tonal clashes during inference. Objective evaluations show that both post-training mechanisms reduce dissonance while maintaining independent melodic metrics, and in subjective tests SymphonyGen is rated above baseline systems in quality and preference, significantly so among general listeners.

arXiv

GeoMind: An Agentic Workflow for Lithology Classification with Reasoned Tool Invocation

Mingyue Cheng, Yitong Zhou, Jiahao Wang, Qingyang Mao, Qi Liu

Lithology classification in well logs is a fundamental geoscience data mining task that aims to infer rock types from multi dimensional geophysical sequences. Despite recent progress, existing approaches typically formulate the problem as a static, single-step discriminative mapping. This static paradigm limits evidence-based diagnostic reasoning against geological standards, often yielding predictions that are detached from geological reality due to a lack of domain priors. In this work, we propose GeoMind, a tool-augmented agentic framework that models lithology classification as a sequential reasoning process. GeoMind organizes its toolkit into perception, reasoning, and analysis modules, which respectively translate raw logs into semantic trends, infer lithology hypotheses from multi-source evidence, and verify predictions against stratigraphic constraints. A global planner adaptively coordinates these modules based on input characteristics, enabling geologically plausible and evidence-grounded decisions. To guarantee the logical consistency of GeoMind, we introduce a fine-grained process supervision strategy. Unlike standard methods that focus solely on final outcomes, our approach optimizes intermediate reasoning steps, ensuring the validity of decision trajectories and alignment to geological constraints. Experiments on four benchmark well-log datasets demonstrate that GeoMind consistently outperforms strong baselines in classification performance while providing transparent and traceable decision-making processes.

arXiv

Bounded Normative Equivalence in Human-AI Cooperation: Group Behaviour, Not Partner Labels, Predicts Cooperation under Anonymous Aggregate Feedback

Nico Mutzner, Taha Yasseri, Heiko Rauhut

The introduction of artificial intelligence (AI) agents into human groups raises questions about how they influence cooperative social norms. Prior work has examined human-AI and human-robot teaming in small groups, but less is known about whether an AI label alters cooperation and norm-related outcomes in repeated group interactions. We report an online experiment using a repeated four-player Public Goods Game. Each group comprised three human participants and one bot, framed either as human or AI, following one of three predefined strategies: unconditional cooperation, conditional cooperation, or free-riding. Among 236 participants, cooperation was primarily associated with the group's contribution in the previous round and with participants' own previous contributions. These patterns were similar across human- and AI-labelled conditions, and cooperation levels did not differ significantly by agent label; a formal equivalence test (TOST) indicated that any label effect was smaller than +/-5 tokens (5% of the endowment). We also found no evidence of label-based differences in norm persistence in a follow-up Prisoner's Dilemma or in participants' normative perceptions. We describe this pattern as bounded normative equivalence: under anonymous aggregate group feedback, an AI label produced no detectable differences in observed cooperation or norm-related outcomes. We argue that this equivalence is bounded by the informational structure of the setting: aggregate feedback makes individual actions difficult to attribute, diluting the identity cues that might otherwise trigger differentiation. These findings suggest that, in collective settings where individual contributions are not identifiable, cooperative norms can extend to groups that include artificial agents.

arXiv

Group-Reflective Self-Distillation for Agentic Reinforcement Learning

Binbin Zheng, Zijun Xie, guanqun zhao, Enlei Gong, Xing Ma, Xiaoliang Fu, Zeyu Chen

Reinforcement learning with verifiable rewards (RLVR) is effective for training large language model agents. However, terminal rewards provide only coarse trajectory-level supervision, leaving successful behaviors, recurring mistakes, and incidental choices entangled in the same outcome signal. Existing agentic self-distillation methods enrich sparse supervision with natural-language skills, but skills retrieved externally or extracted from a single trajectory by stronger models may mismatch current experience, exceed the policy's capability, or remain path-specific. We propose Group-Reflective Self-Distillation (GRSD), which derives capability-aligned and outcome-discriminative guidance from the policy's own verified rollouts. For each prompt, the policy reflects on each verified trajectory in an on-policy group, and a stop-gradient snapshot contrasts the resulting reflections from successful and failed rollouts to construct group-level privileged guidance. Conditioned on this guidance, a self-teacher refines turn-level credit assignment by modulating outcome-based advantages while preserving the verifier-determined learning direction. Experiments across multiple agentic environments and model scales demonstrate that GRSD consistently outperforms competitive baselines and generalizes more effectively to unseen tasks.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.