{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/decision-making/papers/5","list_of":"/task/decision-making","task":"Decision Making","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":5,"pages_in_order":124,"rows_per_page":100,"rows":[401,500],"of":12311,"counts":{"archive_papers_tagged":12311,"with_a_code_link":2946,"where_syntology_ran_a_sample":678,"not_listed_spam_title":0,"listed":12311,"listed_where_code_ran":678,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":560,"every_run_a_failure_of_syntologys_instrument":118,"listed_with_a_run_with_no_instrument_failure":560,"listed_every_run_a_failure_of_syntologys_instrument":118,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/decision-making","prev":"/task/decision-making/papers/4","next":"/task/decision-making/papers/6","papers":[{"url":"/paper/decision-centric-fairness-evaluation-and","slug":"decision-centric-fairness-evaluation-and","title":"Decision-centric fairness: Evaluation and optimization for resource allocation problems","date":"2025-04-29","arxiv_id":"2504.20642","repositories_listed":1,"syntology":null},{"url":"/paper/generalised-label-free-artefact-cleaning-for","slug":"generalised-label-free-artefact-cleaning-for","title":"Generalised Label-free Artefact Cleaning for Real-time Medical Pulsatile Time Series","date":"2025-04-29","arxiv_id":"2504.21209","repositories_listed":1,"syntology":null},{"url":"/paper/modeling-ai-human-collaboration-as-a-multi","slug":"modeling-ai-human-collaboration-as-a-multi","title":"Modeling AI-Human Collaboration as a Multi-Agent Adaptation","date":"2025-04-29","arxiv_id":"2504.20903","repositories_listed":1,"syntology":null},{"url":"/paper/multi-agent-reinforcement-learning-for-27","slug":"multi-agent-reinforcement-learning-for-27","title":"Multi-Agent Reinforcement Learning for Resources Allocation Optimization: A Survey","date":"2025-04-29","arxiv_id":"2504.21048","repositories_listed":1,"syntology":null},{"url":"/paper/rosa-a-knowledge-based-solution-for-robot","slug":"rosa-a-knowledge-based-solution-for-robot","title":"ROSA: A Knowledge-based Solution for Robot Self-Adaptation","date":"2025-04-29","arxiv_id":"2505.00733","repositories_listed":1,"syntology":null},{"url":"/paper/automated-decision-making-for-dynamic-task","slug":"automated-decision-making-for-dynamic-task","title":"Automated decision-making for dynamic task assignment at scale","date":"2025-04-28","arxiv_id":"2504.19933","repositories_listed":1,"syntology":null},{"url":"/paper/a-rag-based-multi-agent-llm-system-for","slug":"a-rag-based-multi-agent-llm-system-for","title":"A RAG-Based Multi-Agent LLM System for Natural Hazard Resilience and Adaptation","date":"2025-04-24","arxiv_id":"2504.17200","repositories_listed":1,"syntology":null},{"url":"/paper/contextual-improving-clinical-text","slug":"contextual-improving-clinical-text","title":"ConTextual: Improving Clinical Text Summarization in LLMs with Context-preserving Token Filtering and Knowledge Graphs","date":"2025-04-23","arxiv_id":"2504.16394","repositories_listed":1,"syntology":null},{"url":"/paper/causality-enhanced-decision-making-for","slug":"causality-enhanced-decision-making-for","title":"Causality-enhanced Decision-Making for Autonomous Mobile Robots in Dynamic Environments","date":"2025-04-16","arxiv_id":"2504.11901","repositories_listed":1,"syntology":null},{"url":"/paper/novel-view-x-ray-projection-synthesis-through","slug":"novel-view-x-ray-projection-synthesis-through","title":"Novel-view X-ray Projection Synthesis through Geometry-Integrated Deep Learning","date":"2025-04-16","arxiv_id":"2504.11953","repositories_listed":1,"syntology":null},{"url":"/paper/a-winner-takes-all-mechanism-for-event","slug":"a-winner-takes-all-mechanism-for-event","title":"A Winner-Takes-All Mechanism for Event Generation","date":"2025-04-15","arxiv_id":"2504.11374","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-autonomous-driving-systems-with-on","slug":"enhancing-autonomous-driving-systems-with-on","title":"Enhancing Autonomous Driving Systems with On-Board Deployed Large Language Models","date":"2025-04-15","arxiv_id":"2504.11514","repositories_listed":1,"syntology":null},{"url":"/paper/sequence-models-for-by-trial-decoding-of","slug":"sequence-models-for-by-trial-decoding-of","title":"Sequence models for by-trial decoding of cognitive strategies from neural data","date":"2025-04-14","arxiv_id":"2504.10028","repositories_listed":1,"syntology":null},{"url":"/paper/toward-aligning-human-and-robot-actions-via","slug":"toward-aligning-human-and-robot-actions-via","title":"Toward Aligning Human and Robot Actions via Multi-Modal Demonstration Learning","date":"2025-04-14","arxiv_id":"2504.11493","repositories_listed":1,"syntology":null},{"url":"/paper/unchecked-and-overlooked-addressing-the","slug":"unchecked-and-overlooked-addressing-the","title":"Unchecked and Overlooked: Addressing the Checkbox Blind Spot in Large Language Models with CheckboxQA","date":"2025-04-14","arxiv_id":"2504.10419","repositories_listed":1,"syntology":null},{"url":"/paper/dynamical-symmetries-in-the-fluctuation","slug":"dynamical-symmetries-in-the-fluctuation","title":"Dynamical symmetries in the fluctuation-driven regime: an application of Noether's theorem to noisy dynamical systems","date":"2025-04-13","arxiv_id":"2504.09761","repositories_listed":1,"syntology":null},{"url":"/paper/optimizing-power-grid-topologies-with","slug":"optimizing-power-grid-topologies-with","title":"Optimizing Power Grid Topologies with Reinforcement Learning: A Survey of Methods and Challenges","date":"2025-04-11","arxiv_id":"2504.08210","repositories_listed":1,"syntology":null},{"url":"/paper/probability-estimation-and-scheduling","slug":"probability-estimation-and-scheduling","title":"Probability Estimation and Scheduling Optimization for Battery Swap Stations via LRU-Enhanced Genetic Algorithm and Dual-Factor Decision System","date":"2025-04-10","arxiv_id":"2504.07453","repositories_listed":1,"syntology":null},{"url":"/paper/flashdepth-real-time-streaming-video-depth","slug":"flashdepth-real-time-streaming-video-depth","title":"FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolution","date":"2025-04-09","arxiv_id":"2504.07093","repositories_listed":1,"syntology":null},{"url":"/paper/persona-dynamics-unveiling-the-impact-of","slug":"persona-dynamics-unveiling-the-impact-of","title":"Persona Dynamics: Unveiling the Impact of Personality Traits on Agents in Text-Based Games","date":"2025-04-09","arxiv_id":"2504.06868","repositories_listed":1,"syntology":null},{"url":"/paper/agent-arena-a-general-framework-for","slug":"agent-arena-a-general-framework-for","title":"Agent-Arena: A General Framework for Evaluating Control Algorithms","date":"2025-04-08","arxiv_id":"2504.06468","repositories_listed":1,"syntology":null},{"url":"/paper/playing-non-embedded-card-based-games-with","slug":"playing-non-embedded-card-based-games-with","title":"Playing Non-Embedded Card-Based Games with Reinforcement Learning","date":"2025-04-07","arxiv_id":"2504.04783","repositories_listed":1,"syntology":null},{"url":"/paper/agentic-knowledgeable-self-awareness","slug":"agentic-knowledgeable-self-awareness","title":"Agentic Knowledgeable Self-awareness","date":"2025-04-04","arxiv_id":"2504.03553","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/agentic-knowledgeable-self-awareness#ran","syntology_url":"https://syntology.ai/paper/2504.03553","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.03553"}},"official":{"repos":["zjunlp/knowself"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/semiparametric-counterfactual-regression","slug":"semiparametric-counterfactual-regression","title":"Semiparametric Counterfactual Regression","date":"2025-04-03","arxiv_id":"2504.02694","repositories_listed":1,"syntology":null},{"url":"/paper/gmai-vl-r1-harnessing-reinforcement-learning","slug":"gmai-vl-r1-harnessing-reinforcement-learning","title":"GMAI-VL-R1: Harnessing Reinforcement Learning for Multimodal Medical Reasoning","date":"2025-04-02","arxiv_id":"2504.01886","repositories_listed":1,"syntology":null},{"url":"/paper/urban-computing-in-the-era-of-large-language","slug":"urban-computing-in-the-era-of-large-language","title":"Urban Computing in the Era of Large Language Models","date":"2025-04-02","arxiv_id":"2504.02009","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-quacking-deep-integration-of-language","slug":"beyond-quacking-deep-integration-of-language","title":"Beyond Quacking: Deep Integration of Language Models and RAG into DuckDB","date":"2025-04-01","arxiv_id":"2504.01157","repositories_listed":1,"syntology":null},{"url":"/paper/quantum-random-lunch-generator-qrlg","slug":"quantum-random-lunch-generator-qrlg","title":"Quantum Random Lunch Generator (QRLG)","date":"2025-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-time-series-forecasting-with-fuzzy","slug":"enhancing-time-series-forecasting-with-fuzzy","title":"Enhancing Time Series Forecasting with Fuzzy Attention-Integrated Transformers","date":"2025-03-31","arxiv_id":"2504.00070","repositories_listed":1,"syntology":null},{"url":"/paper/the-more-the-merrier-logical-and-multistage","slug":"the-more-the-merrier-logical-and-multistage","title":"The more the merrier: logical and multistage processors in credit scoring","date":"2025-03-31","arxiv_id":"2503.23979","repositories_listed":1,"syntology":null},{"url":"/paper/language-guided-concept-bottleneck-models-for","slug":"language-guided-concept-bottleneck-models-for","title":"Language Guided Concept Bottleneck Models for Interpretable Continual Learning","date":"2025-03-30","arxiv_id":"2503.23283","repositories_listed":1,"syntology":null},{"url":"/paper/opendrivevla-towards-end-to-end-autonomous","slug":"opendrivevla-towards-end-to-end-autonomous","title":"OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model","date":"2025-03-30","arxiv_id":"2503.23463","repositories_listed":1,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/opendrivevla-towards-end-to-end-autonomous#ran","syntology_url":"https://syntology.ai/paper/2503.23463","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.23463"}},"official":{"repos":["DriveVLA/OpenDriveVLA"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-based-token-pruning-in","slug":"reinforcement-learning-based-token-pruning-in","title":"Reinforcement Learning-based Token Pruning in Vision Transformers: A Markov Game Approach","date":"2025-03-30","arxiv_id":"2503.23459","repositories_listed":1,"syntology":null},{"url":"/paper/towards-trustworthy-gui-agents-a-survey","slug":"towards-trustworthy-gui-agents-a-survey","title":"Towards Trustworthy GUI Agents: A Survey","date":"2025-03-30","arxiv_id":"2503.23434","repositories_listed":1,"syntology":null},{"url":"/paper/a-causal-framework-to-measure-and-mitigate","slug":"a-causal-framework-to-measure-and-mitigate","title":"A Causal Framework to Measure and Mitigate Non-binary Treatment Discrimination","date":"2025-03-28","arxiv_id":"2503.22454","repositories_listed":1,"syntology":null},{"url":"/paper/vital-more-understandable-feature","slug":"vital-more-understandable-feature","title":"VITAL: More Understandable Feature Visualization through Distribution Alignment and Relevant Information Flow","date":"2025-03-28","arxiv_id":"2503.22399","repositories_listed":1,"syntology":null},{"url":"/paper/a-friendly-introduction-to-triangular","slug":"a-friendly-introduction-to-triangular","title":"A friendly introduction to triangular transport","date":"2025-03-27","arxiv_id":"2503.21673","repositories_listed":1,"syntology":null},{"url":"/paper/dissecting-and-mitigating-diffusion-bias-via","slug":"dissecting-and-mitigating-diffusion-bias-via","title":"Dissecting and Mitigating Diffusion Bias via Mechanistic Interpretability","date":"2025-03-26","arxiv_id":"2503.20483","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/dissecting-and-mitigating-diffusion-bias-via#ran","syntology_url":"https://syntology.ai/paper/2503.20483","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.20483"}},"official":null}},{"url":"/paper/mcts-rag-enhancing-retrieval-augmented","slug":"mcts-rag-enhancing-retrieval-augmented","title":"MCTS-RAG: Enhancing Retrieval-Augmented Generation with Monte Carlo Tree Search","date":"2025-03-26","arxiv_id":"2503.20757","repositories_listed":1,"syntology":null},{"url":"/paper/perspective-shifted-neuro-symbolic-world","slug":"perspective-shifted-neuro-symbolic-world","title":"Perspective-Shifted Neuro-Symbolic World Models: A Framework for Socially-Aware Robot Navigation","date":"2025-03-26","arxiv_id":"2503.20425","repositories_listed":1,"syntology":null},{"url":"/paper/wasserstein-distributionally-robust-bayesian","slug":"wasserstein-distributionally-robust-bayesian","title":"Wasserstein Distributionally Robust Bayesian Optimization with Continuous Context","date":"2025-03-26","arxiv_id":"2503.20341","repositories_listed":1,"syntology":null},{"url":"/paper/llm-based-agent-simulation-for-maternal","slug":"llm-based-agent-simulation-for-maternal","title":"LLM-based Agent Simulation for Maternal Health Interventions: Uncertainty Estimation and Decision-focused Evaluation","date":"2025-03-25","arxiv_id":"2503.22719","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/llm-based-agent-simulation-for-maternal#ran","syntology_url":"https://syntology.ai/paper/2503.22719","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.22719"}},"official":{"repos":["sarahmart/llm-abs-armman-prediction"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/deepfund-will-llm-be-professional-at-fund","slug":"deepfund-will-llm-be-professional-at-fund","title":"Will LLMs be Professional at Fund Investment? DeepFund: A Live Arena Perspective","date":"2025-03-24","arxiv_id":"2503.18313","repositories_listed":1,"syntology":null},{"url":"/paper/depth-matters-multimodal-rgb-d-perception-for","slug":"depth-matters-multimodal-rgb-d-perception-for","title":"Depth Matters: Multimodal RGB-D Perception for Robust Autonomous Agents","date":"2025-03-20","arxiv_id":"2503.16711","repositories_listed":1,"syntology":null},{"url":"/paper/fin-r1-a-large-language-model-for-financial","slug":"fin-r1-a-large-language-model-for-financial","title":"Fin-R1: A Large Language Model for Financial Reasoning through Reinforcement Learning","date":"2025-03-20","arxiv_id":"2503.16252","repositories_listed":1,"syntology":null},{"url":"/paper/neurosep-cp-lcb-a-deep-learning-based","slug":"neurosep-cp-lcb-a-deep-learning-based","title":"NeuroSep-CP-LCB: A Deep Learning-based Contextual Multi-armed Bandit Algorithm with Uncertainty Quantification for Early Sepsis Prediction","date":"2025-03-20","arxiv_id":"2503.16708","repositories_listed":1,"syntology":null},{"url":"/paper/learning-with-expert-abstractions-for","slug":"learning-with-expert-abstractions-for","title":"Learning with Expert Abstractions for Efficient Multi-Task Continuous Control","date":"2025-03-19","arxiv_id":"2503.14809","repositories_listed":1,"syntology":null},{"url":"/paper/a-parallel-hybrid-action-space-reinforcement","slug":"a-parallel-hybrid-action-space-reinforcement","title":"A Parallel Hybrid Action Space Reinforcement Learning Model for Real-world Adaptive Traffic Signal Control","date":"2025-03-18","arxiv_id":"2503.14250","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-accumulated-attention-map-for","slug":"dynamic-accumulated-attention-map-for","title":"Dynamic Accumulated Attention Map for Interpreting Evolution of Decision-Making in Vision Transformer","date":"2025-03-18","arxiv_id":"2503.14640","repositories_listed":1,"syntology":null},{"url":"/paper/visescape-a-benchmark-for-evaluating","slug":"visescape-a-benchmark-for-evaluating","title":"VisEscape: A Benchmark for Evaluating Exploration-driven Decision-making in Virtual Escape Rooms","date":"2025-03-18","arxiv_id":"2503.14427","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-on-the-optimization-of-large","slug":"a-survey-on-the-optimization-of-large","title":"A Survey on the Optimization of Large Language Model-based Agents","date":"2025-03-16","arxiv_id":"2503.12434","repositories_listed":1,"syntology":null},{"url":"/paper/sagallm-context-management-validation-and","slug":"sagallm-context-management-validation-and","title":"SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planning","date":"2025-03-15","arxiv_id":"2503.11951","repositories_listed":1,"syntology":null},{"url":"/paper/combatvla-an-efficient-vision-language-action","slug":"combatvla-an-efficient-vision-language-action","title":"CombatVLA: An Efficient Vision-Language-Action Model for Combat Tasks in 3D Action Role-Playing Games","date":"2025-03-12","arxiv_id":"2503.09527","repositories_listed":1,"syntology":null},{"url":"/paper/towards-robust-multimodal-representation-a","slug":"towards-robust-multimodal-representation-a","title":"Towards Robust Multimodal Representation: A Unified Approach with Adaptive Experts and Alignment","date":"2025-03-12","arxiv_id":"2503.09498","repositories_listed":1,"syntology":null},{"url":"/paper/unmask-it-ai-generated-product-review","slug":"unmask-it-ai-generated-product-review","title":"Unmask It! AI-Generated Product Review Detection in Dravidian Languages","date":"2025-03-12","arxiv_id":"2503.09289","repositories_listed":1,"syntology":null},{"url":"/paper/locally-private-nonparametric-contextual","slug":"locally-private-nonparametric-contextual","title":"Locally Private Nonparametric Contextual Multi-armed Bandits","date":"2025-03-11","arxiv_id":"2503.08098","repositories_listed":1,"syntology":null},{"url":"/paper/segagent-exploring-pixel-understanding","slug":"segagent-exploring-pixel-understanding","title":"SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories","date":"2025-03-11","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/segagent-exploring-pixel-understanding-1","slug":"segagent-exploring-pixel-understanding-1","title":"SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories","date":"2025-03-11","arxiv_id":"2503.08625","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/segagent-exploring-pixel-understanding-1#ran","syntology_url":"https://syntology.ai/paper/2503.08625","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.08625"}},"official":{"repos":["aim-uofa/SegAgent"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/v-max-making-rl-practical-for-autonomous","slug":"v-max-making-rl-practical-for-autonomous","title":"V-Max: A Reinforcement Learning Framework for Autonomous Driving","date":"2025-03-11","arxiv_id":"2503.08388","repositories_listed":1,"syntology":null},{"url":"/paper/dyncim-dynamic-curriculum-for-imbalanced","slug":"dyncim-dynamic-curriculum-for-imbalanced","title":"DynCIM: Dynamic Curriculum for Imbalanced Multimodal Learning","date":"2025-03-09","arxiv_id":"2503.06456","repositories_listed":1,"syntology":null},{"url":"/paper/dsgbench-a-diverse-strategic-game-benchmark","slug":"dsgbench-a-diverse-strategic-game-benchmark","title":"DSGBench: A Diverse Strategic Game Benchmark for Evaluating LLM-based Agents in Complex Decision-Making Environments","date":"2025-03-08","arxiv_id":"2503.06047","repositories_listed":1,"syntology":null},{"url":"/paper/reward-centered-rest-mcts-a-robust-decision","slug":"reward-centered-rest-mcts-a-robust-decision","title":"Reward-Centered ReST-MCTS: A Robust Decision-Making Framework for Robotic Manipulation in High Uncertainty Environments","date":"2025-03-07","arxiv_id":"2503.05226","repositories_listed":1,"syntology":null},{"url":"/paper/framing-the-game-how-context-shapes-llm","slug":"framing-the-game-how-context-shapes-llm","title":"Framing the Game: How Context Shapes LLM Decision-Making","date":"2025-03-05","arxiv_id":"2503.04840","repositories_listed":1,"syntology":null},{"url":"/paper/parallelized-planning-acting-for-efficient","slug":"parallelized-planning-acting-for-efficient","title":"Parallelized Planning-Acting for Efficient LLM-based Multi-Agent Systems","date":"2025-03-05","arxiv_id":"2503.03505","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/parallelized-planning-acting-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2503.03505","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.03505"}},"official":{"repos":["zju-vipa/odyssey"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/predicting-practically-domain-generalization","slug":"predicting-practically-domain-generalization","title":"Predicting Practically? Domain Generalization for Predictive Analytics in Real-world Environments","date":"2025-03-05","arxiv_id":"2503.03399","repositories_listed":1,"syntology":null},{"url":"/paper/generator-assistant-stepwise-rollback","slug":"generator-assistant-stepwise-rollback","title":"Generator-Assistant Stepwise Rollback Framework for Large Language Model Agent","date":"2025-03-04","arxiv_id":"2503.02519","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-deep-learning-for-subtype","slug":"multimodal-deep-learning-for-subtype","title":"Multimodal Deep Learning for Subtype Classification in Breast Cancer Using Histopathological Images and Gene Expression Data","date":"2025-03-04","arxiv_id":"2503.02849","repositories_listed":1,"syntology":null},{"url":"/paper/towards-robust-multi-uav-collaboration-marl","slug":"towards-robust-multi-uav-collaboration-marl","title":"Towards Robust Multi-UAV Collaboration: MARL with Noise-Resilient Communication and Attention Mechanisms","date":"2025-03-04","arxiv_id":"2503.02913","repositories_listed":1,"syntology":null},{"url":"/paper/architectural-and-inferential-inductive","slug":"architectural-and-inferential-inductive","title":"Architectural and Inferential Inductive Biases For Exchangeable Sequence Modeling","date":"2025-03-03","arxiv_id":"2503.01215","repositories_listed":1,"syntology":null},{"url":"/paper/from-understanding-the-world-to-intervening","slug":"from-understanding-the-world-to-intervening","title":"From Understanding the World to Intervening in It: A Unified Multi-Scale Framework for Embodied Cognition","date":"2025-03-02","arxiv_id":"2503.00727","repositories_listed":1,"syntology":null},{"url":"/paper/on-generalization-across-environments-in","slug":"on-generalization-across-environments-in","title":"On Generalization Across Environments In Multi-Objective Reinforcement Learning","date":"2025-03-02","arxiv_id":"2503.00799","repositories_listed":1,"syntology":null},{"url":"/paper/what-makes-a-good-diffusion-planner-for","slug":"what-makes-a-good-diffusion-planner-for","title":"What Makes a Good Diffusion Planner for Decision Making?","date":"2025-03-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/digital-player-evaluating-large-language","slug":"digital-player-evaluating-large-language","title":"Digital Player: Evaluating Large Language Models based Human-like Agent in Games","date":"2025-02-28","arxiv_id":"2502.20807","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/digital-player-evaluating-large-language#ran","syntology_url":"https://syntology.ai/paper/2502.20807","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.20807"}},"official":{"repos":["fuxiailab/civagent"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/medhalltune-an-instruction-tuning-benchmark","slug":"medhalltune-an-instruction-tuning-benchmark","title":"MedHallTune: An Instruction-Tuning Benchmark for Mitigating Medical Hallucination in Vision-Language Models","date":"2025-02-28","arxiv_id":"2502.20780","repositories_listed":1,"syntology":null},{"url":"/paper/scalable-decision-making-in-stochastic","slug":"scalable-decision-making-in-stochastic","title":"Scalable Decision-Making in Stochastic Environments through Learned Temporal Abstraction","date":"2025-02-28","arxiv_id":"2502.21186","repositories_listed":1,"syntology":null},{"url":"/paper/can-a-calibration-metric-be-both-testable-and","slug":"can-a-calibration-metric-be-both-testable-and","title":"Can a calibration metric be both testable and actionable?","date":"2025-02-27","arxiv_id":"2502.19851","repositories_listed":1,"syntology":null},{"url":"/paper/cirt-global-subseasonal-to-seasonal","slug":"cirt-global-subseasonal-to-seasonal","title":"CirT: Global Subseasonal-to-Seasonal Forecasting with Geometry-inspired Transformer","date":"2025-02-27","arxiv_id":"2502.19750","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cirt-global-subseasonal-to-seasonal#ran","syntology_url":"https://syntology.ai/paper/2502.19750","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.19750"}},"official":{"repos":["compasszzn/CirT"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cryptopulse-short-term-cryptocurrency","slug":"cryptopulse-short-term-cryptocurrency","title":"CryptoPulse: Short-Term Cryptocurrency Forecasting with Dual-Prediction and Cross-Correlated Market Indicators","date":"2025-02-26","arxiv_id":"2502.19349","repositories_listed":1,"syntology":null},{"url":"/paper/program-synthesis-dialog-agents-for","slug":"program-synthesis-dialog-agents-for","title":"Program Synthesis Dialog Agents for Interactive Decision-Making","date":"2025-02-26","arxiv_id":"2502.19610","repositories_listed":1,"syntology":null},{"url":"/paper/voting-or-consensus-decision-making-in-multi","slug":"voting-or-consensus-decision-making-in-multi","title":"Voting or Consensus? Decision-Making in Multi-Agent Debate","date":"2025-02-26","arxiv_id":"2502.19130","repositories_listed":1,"syntology":null},{"url":"/paper/wofostgym-a-crop-simulator-for-learning","slug":"wofostgym-a-crop-simulator-for-learning","title":"WOFOSTGym: A Crop Simulator for Learning Annual and Perennial Crop Management Strategies","date":"2025-02-26","arxiv_id":"2502.19308","repositories_listed":1,"syntology":null},{"url":"/paper/an-ensemble-framework-for-probabilistic-short","slug":"an-ensemble-framework-for-probabilistic-short","title":"An Ensemble Framework for Probabilistic Short-Term Load Forecasting Based on BiTCN and Deep Attention Networks","date":"2025-02-25","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/citrus-leveraging-expert-cognitive-pathways","slug":"citrus-leveraging-expert-cognitive-pathways","title":"Citrus: Leveraging Expert Cognitive Pathways in a Medical Language Model for Advanced Medical Decision Support","date":"2025-02-25","arxiv_id":"2502.18274","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/citrus-leveraging-expert-cognitive-pathways#ran","syntology_url":"https://syntology.ai/paper/2502.18274","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.18274"}},"official":{"repos":["jdh-algo/Citrus"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/training-a-generally-curious-agent","slug":"training-a-generally-curious-agent","title":"Training a Generally Curious Agent","date":"2025-02-24","arxiv_id":"2502.17543","repositories_listed":1,"syntology":null},{"url":"/paper/from-text-to-space-mapping-abstract-spatial","slug":"from-text-to-space-mapping-abstract-spatial","title":"From Text to Space: Mapping Abstract Spatial Models in LLMs during a Grid-World Navigation Task","date":"2025-02-23","arxiv_id":"2502.16690","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/from-text-to-space-mapping-abstract-spatial#ran","syntology_url":"https://syntology.ai/paper/2502.16690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.16690"}},"official":{"repos":["mneuronico/griw-world-spatial-orientation-task"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/pmat-optimizing-action-generation-order-in","slug":"pmat-optimizing-action-generation-order-in","title":"PMAT: Optimizing Action Generation Order in Multi-Agent Reinforcement Learning","date":"2025-02-23","arxiv_id":"2502.16496","repositories_listed":1,"syntology":null},{"url":"/paper/the-hidden-strength-of-disagreement","slug":"the-hidden-strength-of-disagreement","title":"The Hidden Strength of Disagreement: Unraveling the Consensus-Diversity Tradeoff in Adaptive Multi-Agent Systems","date":"2025-02-23","arxiv_id":"2502.16565","repositories_listed":1,"syntology":null},{"url":"/paper/moving-beyond-medical-exam-questions-a","slug":"moving-beyond-medical-exam-questions-a","title":"Moving Beyond Medical Exam Questions: A Clinician-Annotated Dataset of Real-World Tasks and Ambiguity in Mental Healthcare","date":"2025-02-22","arxiv_id":"2502.16051","repositories_listed":1,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/moving-beyond-medical-exam-questions-a#ran","syntology_url":"https://syntology.ai/paper/2502.16051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.16051"}},"official":{"repos":["maxlampe/mentat"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/risk-averse-reinforcement-learning-an-optimal","slug":"risk-averse-reinforcement-learning-an-optimal","title":"Risk-Averse Reinforcement Learning: An Optimal Transport Perspective on Temporal Difference Learning","date":"2025-02-22","arxiv_id":"2502.16328","repositories_listed":1,"syntology":null},{"url":"/paper/a-knowledge-distillation-based-approach-to","slug":"a-knowledge-distillation-based-approach-to","title":"A Knowledge Distillation-Based Approach to Enhance Transparency of Classifier Models","date":"2025-02-21","arxiv_id":"2502.15959","repositories_listed":1,"syntology":null},{"url":"/paper/how-far-are-llms-from-being-our-digital-twins","slug":"how-far-are-llms-from-being-our-digital-twins","title":"How Far are LLMs from Being Our Digital Twins? A Benchmark for Persona-Based Behavior Chain Simulation","date":"2025-02-20","arxiv_id":"2502.14642","repositories_listed":1,"syntology":null},{"url":"/paper/multi-objective-causal-bayesian-optimization","slug":"multi-objective-causal-bayesian-optimization","title":"Multi-Objective Causal Bayesian Optimization","date":"2025-02-20","arxiv_id":"2502.14755","repositories_listed":1,"syntology":null},{"url":"/paper/steca-step-level-trajectory-calibration-for","slug":"steca-step-level-trajectory-calibration-for","title":"STeCa: Step-level Trajectory Calibration for LLM Agent Learning","date":"2025-02-20","arxiv_id":"2502.14276","repositories_listed":1,"syntology":null},{"url":"/paper/adaptivestep-automatically-dividing-reasoning","slug":"adaptivestep-automatically-dividing-reasoning","title":"AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence","date":"2025-02-19","arxiv_id":"2502.13943","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adaptivestep-automatically-dividing-reasoning#ran","syntology_url":"https://syntology.ai/paper/2502.13943","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.13943"}},"official":{"repos":["lux0926/asprm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/benchmarking-llms-for-political-science-a","slug":"benchmarking-llms-for-political-science-a","title":"Benchmarking LLMs for Political Science: A United Nations Perspective","date":"2025-02-19","arxiv_id":"2502.14122","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-cross-domain-recommendations-with","slug":"enhancing-cross-domain-recommendations-with","title":"AgentCF++: Memory-enhanced LLM-based Agents for Popularity-aware Cross-domain Recommendations","date":"2025-02-19","arxiv_id":"2502.13843","repositories_listed":1,"syntology":null},{"url":"/paper/fighter-jet-navigation-and-combat-using-deep","slug":"fighter-jet-navigation-and-combat-using-deep","title":"Fighter Jet Navigation and Combat using Deep Reinforcement Learning with Explainable AI","date":"2025-02-19","arxiv_id":"2502.13373","repositories_listed":1,"syntology":null},{"url":"/paper/playing-hex-and-counter-wargames-using","slug":"playing-hex-and-counter-wargames-using","title":"Playing Hex and Counter Wargames using Reinforcement Learning and Recurrent Neural Networks","date":"2025-02-19","arxiv_id":"2502.13918","repositories_listed":1,"syntology":null},{"url":"/paper/robustx-robust-counterfactual-explanations","slug":"robustx-robust-counterfactual-explanations","title":"RobustX: Robust Counterfactual Explanations Made Easy","date":"2025-02-19","arxiv_id":"2502.13751","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/robustx-robust-counterfactual-explanations#ran","syntology_url":"https://syntology.ai/paper/2502.13751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.13751"}},"official":{"repos":["RobustCounterfactualX/RobustX"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/fraud-r1-a-multi-round-benchmark-for","slug":"fraud-r1-a-multi-round-benchmark-for","title":"Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements","date":"2025-02-18","arxiv_id":"2502.12904","repositories_listed":1,"syntology":null}],"record_sha256":"a0c12b848515706d2ab032402c6fad905524509d83f5b7647939890343224071","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}