{"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/gsm8k/papers/3","list_of":"/task/gsm8k","task":"GSM8K","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":3,"pages_in_order":5,"rows_per_page":100,"rows":[201,300],"of":439,"counts":{"archive_papers_tagged":439,"with_a_code_link":209,"where_syntology_ran_a_sample":116,"not_listed_spam_title":0,"listed":439,"listed_where_code_ran":116,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":96,"every_run_a_failure_of_syntologys_instrument":20,"listed_with_a_run_with_no_instrument_failure":96,"listed_every_run_a_failure_of_syntologys_instrument":20,"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/gsm8k","prev":"/task/gsm8k/papers/2","next":"/task/gsm8k/papers/4","papers":[{"url":"/paper/automatic-model-selection-with-large-language","slug":"automatic-model-selection-with-large-language","title":"Automatic Model Selection with Large Language Models for Reasoning","date":"2023-05-23","arxiv_id":"2305.14333","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"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) · 0 unverified","sample_list":"/paper/automatic-model-selection-with-large-language#ran","syntology_url":"https://syntology.ai/paper/2305.14333","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14333"}},"official":{"repos":["xuzhao0/model-selection-reasoning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/pad-program-aided-distillation-specializes","slug":"pad-program-aided-distillation-specializes","title":"PaD: Program-aided Distillation Can Teach Small Models Reasoning Better than Chain-of-thought Fine-tuning","date":"2023-05-23","arxiv_id":"2305.13888","repositories_listed":1,"syntology":null},{"url":"/paper/self-polish-enhance-reasoning-in-large","slug":"self-polish-enhance-reasoning-in-large","title":"Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement","date":"2023-05-23","arxiv_id":"2305.14497","repositories_listed":1,"syntology":null},{"url":"/paper/progressive-hint-prompting-improves-reasoning","slug":"progressive-hint-prompting-improves-reasoning","title":"Progressive-Hint Prompting Improves Reasoning in Large Language Models","date":"2023-04-19","arxiv_id":"2304.09797","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/progressive-hint-prompting-improves-reasoning#ran","syntology_url":"https://syntology.ai/paper/2304.09797","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.09797"}},"official":{"repos":["chuanyang-Zheng/Progressive-Hint"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/solving-math-word-problems-by-combining","slug":"solving-math-word-problems-by-combining","title":"Solving Math Word Problems by Combining Language Models With Symbolic Solvers","date":"2023-04-16","arxiv_id":"2304.09102","repositories_listed":1,"syntology":null},{"url":"/paper/boosted-prompt-ensembles-for-large-language","slug":"boosted-prompt-ensembles-for-large-language","title":"Boosted Prompt Ensembles for Large Language Models","date":"2023-04-12","arxiv_id":"2304.05970","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-are-latent-variable-1","slug":"large-language-models-are-latent-variable-1","title":"Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning","date":"2023-01-27","arxiv_id":"2301.11916","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/large-language-models-are-latent-variable-1#ran","syntology_url":"https://syntology.ai/paper/2301.11916","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.11916"}},"official":{"repos":["wangxinyilinda/concept-based-demonstration-selection"],"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/distilling-multi-step-reasoning-capabilities","slug":"distilling-multi-step-reasoning-capabilities","title":"Distilling Reasoning Capabilities into Smaller Language Models","date":"2022-12-01","arxiv_id":"2212.00193","repositories_listed":1,"syntology":null},{"url":"/paper/learning-from-self-sampled-correct-and","slug":"learning-from-self-sampled-correct-and","title":"Learning Math Reasoning from Self-Sampled Correct and Partially-Correct Solutions","date":"2022-05-28","arxiv_id":"2205.14318","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/learning-from-self-sampled-correct-and#ran","syntology_url":"https://syntology.ai/paper/2205.14318","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14318"}},"official":{"repos":["microsoft/tracecodegen"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":null,"slug":"gemmas-graph-based-evaluation-metrics-for","title":"GEMMAS: Graph-based Evaluation Metrics for Multi Agent Systems","date":"2025-07-17","arxiv_id":"2507.13190","repositories_listed":0,"syntology":null},{"url":null,"slug":"kismath-do-llms-have-knowledge-of-implicit","title":"KisMATH: Do LLMs Have Knowledge of Implicit Structures in Mathematical Reasoning?","date":"2025-07-15","arxiv_id":"2507.11408","repositories_listed":0,"syntology":null},{"url":null,"slug":"core-enhancing-metacognition-with-label-free","title":"CoRE: Enhancing Metacognition with Label-free Self-evaluation in LRMs","date":"2025-07-08","arxiv_id":"2507.06087","repositories_listed":0,"syntology":null},{"url":null,"slug":"activation-steering-for-chain-of-thought","title":"Activation Steering for Chain-of-Thought Compression","date":"2025-07-07","arxiv_id":"2507.04742","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-speculative-decoding-with-lookahead","title":"Scaling Speculative Decoding with Lookahead Reasoning","date":"2025-06-24","arxiv_id":"2506.19830","repositories_listed":0,"syntology":null},{"url":"/paper/plan-for-speed-dilated-scheduling-for-masked","slug":"plan-for-speed-dilated-scheduling-for-masked","title":"Plan for Speed -- Dilated Scheduling for Masked Diffusion Language Models","date":"2025-06-23","arxiv_id":"2506.19037","repositories_listed":0,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/plan-for-speed-dilated-scheduling-for-masked#ran","syntology_url":"https://syntology.ai/paper/2506.19037","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.19037"}},"official":null}},{"url":null,"slug":"fractional-reasoning-via-latent-steering","title":"Fractional Reasoning via Latent Steering Vectors Improves Inference Time Compute","date":"2025-06-18","arxiv_id":"2506.15882","repositories_listed":0,"syntology":null},{"url":null,"slug":"excessive-reasoning-attack-on-reasoning-llms","title":"Excessive Reasoning Attack on Reasoning LLMs","date":"2025-06-17","arxiv_id":"2506.14374","repositories_listed":0,"syntology":null},{"url":null,"slug":"lora-mixer-coordinate-modular-lora-experts","title":"LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing","date":"2025-06-17","arxiv_id":"2507.00029","repositories_listed":0,"syntology":null},{"url":null,"slug":"learnalign-reasoning-data-selection-for","title":"LearnAlign: Reasoning Data Selection for Reinforcement Learning in Large Language Models Based on Improved Gradient Alignment","date":"2025-06-13","arxiv_id":"2506.11480","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-on-the-easy-deep-on-the-hard-efficient","title":"Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty","date":"2025-06-12","arxiv_id":"2506.10446","repositories_listed":0,"syntology":null},{"url":null,"slug":"premise-scalable-and-strategic-prompt","title":"PREMISE: Scalable and Strategic Prompt Optimization for Efficient Mathematical Reasoning in Large Models","date":"2025-06-12","arxiv_id":"2506.10716","repositories_listed":0,"syntology":null},{"url":null,"slug":"slimming-down-llms-without-losing-their-minds","title":"Slimming Down LLMs Without Losing Their Minds","date":"2025-06-12","arxiv_id":"2506.10885","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-reasoning-capabilities-of-small","title":"Enhancing Reasoning Capabilities of Small Language Models with Blueprints and Prompt Template Search","date":"2025-06-10","arxiv_id":"2506.08669","repositories_listed":0,"syntology":null},{"url":null,"slug":"guideline-forest-experience-induced-multi","title":"Guideline Forest: Experience-Induced Multi-Guideline Reasoning with Stepwise Aggregation","date":"2025-06-09","arxiv_id":"2506.07820","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-to-lora-instant-transformer-adaption","title":"Text-to-LoRA: Instant Transformer Adaption","date":"2025-06-06","arxiv_id":"2506.06105","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-robustness-stress-testing-of-llms","title":"Automatic Robustness Stress Testing of LLMs as Mathematical Problem Solvers","date":"2025-06-05","arxiv_id":"2506.05038","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-of-llms-for-mathematical-problem","title":"Evaluation of LLMs for mathematical problem solving","date":"2025-05-30","arxiv_id":"2506.00309","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-unlearning-via-sparse-autoencoder","title":"Model Unlearning via Sparse Autoencoder Subspace Guided Projections","date":"2025-05-30","arxiv_id":"2505.24428","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-llms-reason-abstractly-over-math-word","title":"Can LLMs Reason Abstractly Over Math Word Problems Without CoT? Disentangling Abstract Formulation From Arithmetic Computation","date":"2025-05-29","arxiv_id":"2505.23701","repositories_listed":0,"syntology":null},{"url":null,"slug":"cothink-token-efficient-reasoning-via","title":"CoThink: Token-Efficient Reasoning via Instruct Models Guiding Reasoning Models","date":"2025-05-28","arxiv_id":"2505.22017","repositories_listed":0,"syntology":null},{"url":null,"slug":"maximizing-confidence-alone-improves","title":"Maximizing Confidence Alone Improves Reasoning","date":"2025-05-28","arxiv_id":"2505.22660","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-data-selection-at-scale-via","title":"Efficient Data Selection at Scale via Influence Distillation","date":"2025-05-25","arxiv_id":"2505.19051","repositories_listed":0,"syntology":null},{"url":null,"slug":"llada-1-5-variance-reduced-preference","title":"LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models","date":"2025-05-25","arxiv_id":"2505.19223","repositories_listed":0,"syntology":null},{"url":null,"slug":"system-1-5-reasoning-traversal-in-language","title":"System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts","date":"2025-05-25","arxiv_id":"2505.18962","repositories_listed":0,"syntology":null},{"url":null,"slug":"steering-llm-reasoning-through-bias-only","title":"Steering LLM Reasoning Through Bias-Only Adaptation","date":"2025-05-24","arxiv_id":"2505.18706","repositories_listed":0,"syntology":null},{"url":null,"slug":"pmpo-probabilistic-metric-prompt-optimization","title":"PMPO: Probabilistic Metric Prompt Optimization for Small and Large Language Models","date":"2025-05-22","arxiv_id":"2505.16307","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-rank-chain-of-thought-an-energy","title":"Learning to Rank Chain-of-Thought: An Energy-Based Approach with Outcome Supervision","date":"2025-05-21","arxiv_id":"2505.14999","repositories_listed":0,"syntology":null},{"url":null,"slug":"drp-distilled-reasoning-pruning-with-skill","title":"DRP: Distilled Reasoning Pruning with Skill-aware Step Decomposition for Efficient Large Reasoning Models","date":"2025-05-20","arxiv_id":"2505.13975","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-decomposition-of-weights-and-singular","title":"Dual Decomposition of Weights and Singular Value Low Rank Adaptation","date":"2025-05-20","arxiv_id":"2505.14367","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-reasoning-language-models-unfold-hidden","title":"Self-Reasoning Language Models: Unfold Hidden Reasoning Chains with Few Reasoning Catalyst","date":"2025-05-20","arxiv_id":"2505.14116","repositories_listed":0,"syntology":null},{"url":null,"slug":"rl-in-name-only-analyzing-the-structural","title":"RL in Name Only? Analyzing the Structural Assumptions in RL post-training for LLMs","date":"2025-05-19","arxiv_id":"2505.13697","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcing-the-diffusion-chain-of-lateral","title":"Reinforcing the Diffusion Chain of Lateral Thought with Diffusion Language Models","date":"2025-05-15","arxiv_id":"2505.10446","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-chain-of-thought-reasoning-when","title":"Accelerating Chain-of-Thought Reasoning: When Goal-Gradient Importance Meets Dynamic Skipping","date":"2025-05-13","arxiv_id":"2505.08392","repositories_listed":0,"syntology":null},{"url":null,"slug":"attentioninfluence-adopting-attention-head","title":"AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection","date":"2025-05-12","arxiv_id":"2505.07293","repositories_listed":0,"syntology":null},{"url":null,"slug":"s-grpo-early-exit-via-reinforcement-learning","title":"S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models","date":"2025-05-12","arxiv_id":"2505.07686","repositories_listed":0,"syntology":null},{"url":null,"slug":"elastic-weight-consolidation-for-full","title":"Elastic Weight Consolidation for Full-Parameter Continual Pre-Training of Gemma2","date":"2025-05-09","arxiv_id":"2505.05946","repositories_listed":0,"syntology":null},{"url":null,"slug":"memory-efficient-llm-training-by-various","title":"Memory-Efficient LLM Training by Various-Grained Low-Rank Projection of Gradients","date":"2025-05-03","arxiv_id":"2505.01744","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-fine-tuning-of-quantized-models-via","title":"Efficient Fine-Tuning of Quantized Models via Adaptive Rank and Bitwidth","date":"2025-05-02","arxiv_id":"2505.03802","repositories_listed":0,"syntology":null},{"url":null,"slug":"local-prompt-optimization","title":"Local Prompt Optimization","date":"2025-04-29","arxiv_id":"2504.20355","repositories_listed":0,"syntology":null},{"url":null,"slug":"trace-of-thought-prompting-investigating","title":"Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition","date":"2025-04-29","arxiv_id":"2504.20946","repositories_listed":0,"syntology":null},{"url":null,"slug":"autojudge-judge-decoding-without-manual","title":"AutoJudge: Judge Decoding Without Manual Annotation","date":"2025-04-28","arxiv_id":"2504.20039","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-large-language-models-to-reason-via","title":"Training Large Language Models to Reason via EM Policy Gradient","date":"2025-04-24","arxiv_id":"2504.18587","repositories_listed":0,"syntology":null},{"url":null,"slug":"not-all-rollouts-are-useful-down-sampling","title":"Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning","date":"2025-04-18","arxiv_id":"2504.13818","repositories_listed":0,"syntology":null},{"url":null,"slug":"entropy-guided-watermarking-for-llms-a-test","title":"Entropy-Guided Watermarking for LLMs: A Test-Time Framework for Robust and Traceable Text Generation","date":"2025-04-16","arxiv_id":"2504.12108","repositories_listed":0,"syntology":null},{"url":null,"slug":"question-tokens-deserve-more-attention","title":"Question Tokens Deserve More Attention: Enhancing Large Language Models without Training through Step-by-Step Reading and Question Attention Recalibration","date":"2025-04-13","arxiv_id":"2504.09402","repositories_listed":0,"syntology":null},{"url":null,"slug":"supervised-optimism-correction-be-confident","title":"Supervised Optimism Correction: Be Confident When LLMs Are Sure","date":"2025-04-10","arxiv_id":"2504.07527","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-data-generation-multi-step-rl-for","title":"Synthetic Data Generation & Multi-Step RL for Reasoning & Tool Use","date":"2025-04-07","arxiv_id":"2504.04736","repositories_listed":0,"syntology":null},{"url":null,"slug":"sample-don-t-search-rethinking-test-time","title":"Sample, Don't Search: Rethinking Test-Time Alignment for Language Models","date":"2025-04-04","arxiv_id":"2504.03790","repositories_listed":0,"syntology":null},{"url":null,"slug":"sustainable-llm-inference-for-edge-ai","title":"Sustainable LLM Inference for Edge AI: Evaluating Quantized LLMs for Energy Efficiency, Output Accuracy, and Inference Latency","date":"2025-04-04","arxiv_id":"2504.03360","repositories_listed":0,"syntology":null},{"url":null,"slug":"d-2lora-data-driven-lora-initialization-for","title":"$D^2LoRA$: Data-Driven LoRA Initialization for Low Resource Tasks","date":"2025-03-23","arxiv_id":"2503.18089","repositories_listed":0,"syntology":null},{"url":null,"slug":"tapered-off-policy-reinforce-stable-and","title":"Tapered Off-Policy REINFORCE: Stable and efficient reinforcement learning for LLMs","date":"2025-03-18","arxiv_id":"2503.14286","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-complex-reasoning-with-dynamic","title":"Improving Complex Reasoning with Dynamic Prompt Corruption: A soft prompt Optimization Approach","date":"2025-03-17","arxiv_id":"2503.13208","repositories_listed":0,"syntology":null},{"url":null,"slug":"rule-guided-feedback-enhancing-reasoning-by","title":"Rule-Guided Feedback: Enhancing Reasoning by Enforcing Rule Adherence in Large Language Models","date":"2025-03-14","arxiv_id":"2503.11336","repositories_listed":0,"syntology":null},{"url":null,"slug":"position-aware-depth-decay-decoding-d-3","title":"Position-Aware Depth Decay Decoding ($D^3$): Boosting Large Language Model Inference Efficiency","date":"2025-03-11","arxiv_id":"2503.08524","repositories_listed":0,"syntology":null},{"url":null,"slug":"solar-scalable-optimization-of-large-scale","title":"SOLAR: Scalable Optimization of Large-scale Architecture for Reasoning","date":"2025-03-06","arxiv_id":"2503.04530","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-evolved-preference-optimization-for","title":"Self-Evolved Preference Optimization for Enhancing Mathematical Reasoning in Small Language Models","date":"2025-03-04","arxiv_id":"2503.04813","repositories_listed":0,"syntology":null},{"url":null,"slug":"layer-aware-task-arithmetic-disentangling","title":"Layer-Aware Task Arithmetic: Disentangling Task-Specific and Instruction-Following Knowledge","date":"2025-02-27","arxiv_id":"2502.20186","repositories_listed":0,"syntology":null},{"url":null,"slug":"distill-not-only-data-but-also-rewards-can","title":"Distill Not Only Data but Also Rewards: Can Smaller Language Models Surpass Larger Ones?","date":"2025-02-26","arxiv_id":"2502.19557","repositories_listed":0,"syntology":null},{"url":null,"slug":"weaker-llms-opinions-also-matter-mixture-of","title":"Weaker LLMs' Opinions Also Matter: Mixture of Opinions Enhances LLM's Mathematical Reasoning","date":"2025-02-26","arxiv_id":"2502.19622","repositories_listed":0,"syntology":null},{"url":null,"slug":"secura-sigmoid-enhanced-cur-decomposition","title":"SECURA: Sigmoid-Enhanced CUR Decomposition with Uninterrupted Retention and Low-Rank Adaptation in Large Language Models","date":"2025-02-25","arxiv_id":"2502.18168","repositories_listed":0,"syntology":null},{"url":null,"slug":"led-merging-mitigating-safety-utility","title":"LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint","date":"2025-02-24","arxiv_id":"2502.16770","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-parallel-tree-search-for-efficient","title":"Dynamic Parallel Tree Search for Efficient LLM Reasoning","date":"2025-02-22","arxiv_id":"2502.16235","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-correctness-to-comprehension-ai-agents","title":"From Correctness to Comprehension: AI Agents for Personalized Error Diagnosis in Education","date":"2025-02-19","arxiv_id":"2502.13789","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-arithmetic-learning-improves","title":"Integrating Arithmetic Learning Improves Mathematical Reasoning in Smaller Models","date":"2025-02-18","arxiv_id":"2502.12855","repositories_listed":0,"syntology":null},{"url":null,"slug":"mathfimer-enhancing-mathematical-reasoning-by","title":"MathFimer: Enhancing Mathematical Reasoning by Expanding Reasoning Steps through Fill-in-the-Middle Task","date":"2025-02-17","arxiv_id":"2502.11684","repositories_listed":0,"syntology":null},{"url":null,"slug":"balancing-the-budget-understanding-trade-offs","title":"Balancing the Budget: Understanding Trade-offs Between Supervised and Preference-Based Finetuning","date":"2025-02-16","arxiv_id":"2502.11284","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-uncertainty-estimation-for","title":"Leveraging Uncertainty Estimation for Efficient LLM Routing","date":"2025-02-16","arxiv_id":"2502.11021","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-aware-search-and-value-models","title":"Uncertainty-Aware Search and Value Models: Mitigating Search Scaling Flaws in LLMs","date":"2025-02-16","arxiv_id":"2502.11155","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-offline-online-scheduling-method-for","title":"Hybrid Offline-online Scheduling Method for Large Language Model Inference Optimization","date":"2025-02-14","arxiv_id":"2502.15763","repositories_listed":0,"syntology":null},{"url":null,"slug":"cost-saving-llm-cascades-with-early","title":"Cost-Saving LLM Cascades with Early Abstention","date":"2025-02-13","arxiv_id":"2502.09054","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-training-large-language-models-for-tool","title":"Self-Training Large Language Models for Tool-Use Without Demonstrations","date":"2025-02-09","arxiv_id":"2502.05867","repositories_listed":0,"syntology":null},{"url":null,"slug":"evolving-llms-self-refinement-capability-via","title":"Evolving LLMs' Self-Refinement Capability via Iterative Preference Optimization","date":"2025-02-08","arxiv_id":"2502.05605","repositories_listed":0,"syntology":null},{"url":null,"slug":"reasoning-as-logic-units-scaling-test-time","title":"Reasoning-as-Logic-Units: Scaling Test-Time Reasoning in Large Language Models Through Logic Unit Alignment","date":"2025-02-05","arxiv_id":"2502.07803","repositories_listed":0,"syntology":null},{"url":null,"slug":"bare-combining-base-and-instruction-tuned","title":"BARE: Leveraging Base Language Models for Few-Shot Synthetic Data Generation","date":"2025-02-03","arxiv_id":"2502.01697","repositories_listed":0,"syntology":null},{"url":null,"slug":"chunkkv-semantic-preserving-kv-cache","title":"ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference","date":"2025-02-01","arxiv_id":"2502.00299","repositories_listed":0,"syntology":null},{"url":null,"slug":"pheromone-based-learning-of-optimal-reasoning","title":"Pheromone-based Learning of Optimal Reasoning Paths","date":"2025-01-31","arxiv_id":"2501.19278","repositories_listed":0,"syntology":null},{"url":null,"slug":"rotatekv-accurate-and-robust-2-bit-kv-cache","title":"RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations","date":"2025-01-25","arxiv_id":"2501.16383","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-your-llm-trapped-in-a-mental-set","title":"Is your LLM trapped in a Mental Set? Investigative study on how mental sets affect the reasoning capabilities of LLMs","date":"2025-01-21","arxiv_id":"2501.11833","repositories_listed":0,"syntology":null},{"url":null,"slug":"dna-1-0-technical-report","title":"DNA 1.0 Technical Report","date":"2025-01-18","arxiv_id":"2501.10648","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-exploration-with-adaptive-gating-for","title":"Semantic Exploration with Adaptive Gating for Efficient Problem Solving with Language Models","date":"2025-01-10","arxiv_id":"2501.05752","repositories_listed":0,"syntology":null},{"url":null,"slug":"infifusion-a-unified-framework-for-enhanced","title":"InfiFusion: A Unified Framework for Enhanced Cross-Model Reasoning via LLM Fusion","date":"2025-01-06","arxiv_id":"2501.02795","repositories_listed":0,"syntology":null},{"url":null,"slug":"recursive-decomposition-of-logical-thoughts","title":"Recursive Decomposition of Logical Thoughts: Framework for Superior Reasoning and Knowledge Propagation in Large Language Models","date":"2025-01-03","arxiv_id":"2501.02026","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-not-think-that-much-for-2-3-on-the","title":"Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs","date":"2024-12-30","arxiv_id":"2412.21187","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-intrinsic-self-correction-enhancement","title":"Towards Intrinsic Self-Correction Enhancement in Monte Carlo Tree Search Boosted Reasoning via Iterative Preference Learning","date":"2024-12-23","arxiv_id":"2412.17397","repositories_listed":0,"syntology":null},{"url":null,"slug":"ask-before-detection-identifying-and","title":"Ask-Before-Detection: Identifying and Mitigating Conformity Bias in LLM-Powered Error Detector for Math Word Problem Solutions","date":"2024-12-22","arxiv_id":"2412.16838","repositories_listed":0,"syntology":null},{"url":null,"slug":"system-2-mathematical-reasoning-via-enriched","title":"System-2 Mathematical Reasoning via Enriched Instruction Tuning","date":"2024-12-22","arxiv_id":"2412.16964","repositories_listed":0,"syntology":null},{"url":null,"slug":"falcon-faster-and-parallel-inference-of-large","title":"Falcon: Faster and Parallel Inference of Large Language Models through Enhanced Semi-Autoregressive Drafting and Custom-Designed Decoding Tree","date":"2024-12-17","arxiv_id":"2412.12639","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-graph-based-synthetic-data-pipeline-for","title":"A Graph-Based Synthetic Data Pipeline for Scaling High-Quality Reasoning Instructions","date":"2024-12-12","arxiv_id":"2412.08864","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-reason-via-self-iterative-process","title":"Learning to Reason via Self-Iterative Process Feedback for Small Language Models","date":"2024-12-11","arxiv_id":"2412.08393","repositories_listed":0,"syntology":null},{"url":null,"slug":"smoltulu-higher-learning-rate-to-batch-size","title":"SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs","date":"2024-12-11","arxiv_id":"2412.08347","repositories_listed":0,"syntology":null}],"record_sha256":"ccd439fbc94b0cffa955d5a28fde6950bb61ee5041472cf969cf974c3a8ab8c6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}