https://baba9811.github.io/papers/0001-how-to-train-your-long-context-visual-document-model/ 2026-04-28T10:00:00+09:00 https://baba9811.github.io/en/papers/0001-how-to-train-your-long-context-visual-document-model/ 2026-04-28T10:00:00+09:00 https://baba9811.github.io/papers/0002-tradingagents-multi-agents-llm-financial-trading-framework/ 2026-04-28T11:00:00+09:00 https://baba9811.github.io/en/papers/0002-tradingagents-multi-agents-llm-financial-trading-framework/ 2026-04-28T11:00:00+09:00 https://baba9811.github.io/papers/0003-llada2-0-uni-unified-multimodal-diffusion-llm/ 2026-04-29T10:00:00+09:00 https://baba9811.github.io/en/papers/0003-llada2-0-uni-unified-multimodal-diffusion-llm/ 2026-04-29T10:00:00+09:00 https://baba9811.github.io/papers/0004-turboquant-online-vector-quantization-with-near-optimal-dist/ 2026-04-30T10:00:00+09:00 https://baba9811.github.io/en/papers/0004-turboquant-online-vector-quantization-with-near-optimal-dist/ 2026-04-30T10:00:00+09:00 https://baba9811.github.io/papers/0005-artificial-intelligence-in-customer-relationship-management/ 2026-05-03T10:00:00+09:00 https://baba9811.github.io/en/papers/0005-artificial-intelligence-in-customer-relationship-management/ 2026-05-03T10:00:00+09:00 https://baba9811.github.io/papers/0006-b2b-lead-scoring-with-machine-learning/ 2026-05-06T10:00:00+09:00 https://baba9811.github.io/en/papers/0006-b2b-lead-scoring-with-machine-learning/ 2026-05-06T10:00:00+09:00 https://baba9811.github.io/papers/0007-unlocking-power-of-ai-in-crm/ 2026-05-06T11:00:00+09:00 https://baba9811.github.io/en/papers/0007-unlocking-power-of-ai-in-crm/ 2026-05-06T11:00:00+09:00 https://baba9811.github.io/papers/0008-persistent-visual-memory/ 2026-05-06T12:00:00+09:00 https://baba9811.github.io/en/papers/0008-persistent-visual-memory/ 2026-05-06T12:00:00+09:00 https://baba9811.github.io/papers/0009-personalized-marketing-leveraging-ai-for-culturally-aware-se/ 2026-05-08T00:00:00+09:00 https://baba9811.github.io/en/papers/0009-personalized-marketing-leveraging-ai-for-culturally-aware-se/ 2026-05-08T00:00:00+09:00 https://baba9811.github.io/papers/0010-graph-based-audience-expansion-model-for-marketing-campaigns/ 2026-05-11T10:00:00+09:00 https://baba9811.github.io/en/papers/0010-graph-based-audience-expansion-model-for-marketing-campaigns/ 2026-05-11T10:00:00+09:00 https://baba9811.github.io/papers/0011-agenticrectune-multi-agent-self-evolving-skillhub/ 2026-05-13T10:00:00+09:00 https://baba9811.github.io/en/papers/0011-agenticrectune-multi-agent-self-evolving-skillhub/ 2026-05-13T10:00:00+09:00 https://baba9811.github.io/papers/0012-improving-large-scale-recommender-systems-with-auxiliary-lea/ 2026-05-14T14:00:00+09:00 https://baba9811.github.io/en/papers/0012-improving-large-scale-recommender-systems-with-auxiliary-lea/ 2026-05-14T14:00:00+09:00 https://baba9811.github.io/papers/0013-rtp-lx-can-llms-evaluate-toxicity-in-multilingual-scenarios/ 2026-05-14T19:30:00+09:00 https://baba9811.github.io/en/papers/0013-rtp-lx-can-llms-evaluate-toxicity-in-multilingual-scenarios/ 2026-05-14T19:30:00+09:00 https://baba9811.github.io/papers/0014-algorithmically-establishing-trust-in-evaluators/ 2026-05-14T22:00:00+09:00 https://baba9811.github.io/en/papers/0014-algorithmically-establishing-trust-in-evaluators/ 2026-05-14T22:00:00+09:00 https://baba9811.github.io/papers/0015-goldfish/ 2026-05-14T23:00:00+09:00 https://baba9811.github.io/en/papers/0015-goldfish/ 2026-05-14T23:00:00+09:00 https://baba9811.github.io/papers/0016-mint-managed-infrastructure-for-training-and-serving-million/ 2026-05-19T22:00:00+09:00 https://baba9811.github.io/en/papers/0016-mint-managed-infrastructure-for-training-and-serving-million/ 2026-05-19T22:00:00+09:00 https://baba9811.github.io/papers/0017-showui-one-vision-language-action-model-for-gui-visual-agent/ 2026-05-29T14:00:00+09:00 https://baba9811.github.io/en/papers/0017-showui-one-vision-language-action-model-for-gui-visual-agent/ 2026-05-29T14:00:00+09:00 https://baba9811.github.io/papers/0018-ferret-ui-lite-lessons-from-building-small-on-device-gui-age/ 2026-05-29T15:30:00+09:00 https://baba9811.github.io/en/papers/0018-ferret-ui-lite-lessons-from-building-small-on-device-gui-age/ 2026-05-29T15:30:00+09:00 https://baba9811.github.io/papers/0019-mobileexplorer-accelerating-on-device-inference-for-mobile-g/ 2026-05-29T17:00:00+09:00 https://baba9811.github.io/en/papers/0019-mobileexplorer-accelerating-on-device-inference-for-mobile-g/ 2026-05-29T17:00:00+09:00 https://baba9811.github.io/papers/0020-personalization-and-targeting-how-to-experiment-learn-optimi/ 2026-06-01T14:00:00+09:00 https://baba9811.github.io/en/papers/0020-personalization-and-targeting-how-to-experiment-learn-optimi/ 2026-06-01T14:00:00+09:00 https://baba9811.github.io/papers/0021-robust-uplift-modeling-with-large-scale-contexts-for-real-ti/ 2026-06-01T16:00:00+09:00 https://baba9811.github.io/en/papers/0021-robust-uplift-modeling-with-large-scale-contexts-for-real-ti/ 2026-06-01T16:00:00+09:00 https://baba9811.github.io/papers/0022-multi-interest-recommendation-a-survey/ 2026-06-04T14:00:00+09:00 https://baba9811.github.io/en/papers/0022-multi-interest-recommendation-a-survey/ 2026-06-04T14:00:00+09:00 https://baba9811.github.io/papers/0023-a-survey-on-generative-recommendation-data-model-and-tasks/ 2026-06-04T16:00:00+09:00 https://baba9811.github.io/en/papers/0023-a-survey-on-generative-recommendation-data-model-and-tasks/ 2026-06-04T16:00:00+09:00 https://baba9811.github.io/papers/0024-code-world-model-preparedness-report/ 2026-06-25T14:00:00+09:00 https://baba9811.github.io/en/papers/0024-code-world-model-preparedness-report/ 2026-06-25T14:00:00+09:00 https://baba9811.github.io/papers/0025-shield-an-auto-healing-agentic-defense-framework-for-llm-res/ 2026-06-25T16:00:00+09:00 https://baba9811.github.io/en/papers/0025-shield-an-auto-healing-agentic-defense-framework-for-llm-res/ 2026-06-25T16:00:00+09:00 https://baba9811.github.io/papers/0026-autodata-an-agentic-data-scientist/ 2026-06-29T14:00:00+09:00 https://baba9811.github.io/en/papers/0026-autodata-an-agentic-data-scientist/ 2026-06-29T14:00:00+09:00 https://baba9811.github.io/papers/0027-kimi-k3-open-frontier-intelligence/ 2026-07-31T14:00:00+09:00 https://baba9811.github.io/en/papers/0027-kimi-k3-open-frontier-intelligence/ 2026-07-31T14:00:00+09:00 https://baba9811.github.io/papers/0028-frontis-ma1-training-an-ai4ai-model-towards-recursive-self-i/ 2026-08-03T14:00:00+09:00 https://baba9811.github.io/en/papers/0028-frontis-ma1-training-an-ai4ai-model-towards-recursive-self-i/ 2026-08-03T14:00:00+09:00 https://baba9811.github.io/papers/0029-scientistone-towards-human-level-autonomous-research-via-cha/ 2026-08-04T14:00:00+09:00 https://baba9811.github.io/en/papers/0029-scientistone-towards-human-level-autonomous-research-via-cha/ 2026-08-04T14:00:00+09:00 https://baba9811.github.io/papers/0030-skaling-chinchilla-s-exponents-meet-kaplan-s-coupling/ 2026-08-11T14:00:00+09:00 https://baba9811.github.io/en/papers/0030-skaling-chinchilla-s-exponents-meet-kaplan-s-coupling/ 2026-08-11T14:00:00+09:00 https://baba9811.github.io/papers/0031-nvidia-labs-oo-agents-native-python-object-oriented-agents/ 2026-08-12T14:00:00+09:00 https://baba9811.github.io/en/papers/0031-nvidia-labs-oo-agents-native-python-object-oriented-agents/ 2026-08-12T14:00:00+09:00 https://baba9811.github.io/papers/0032-hierarchical-self-improvement-a-framework-for-task-specific/ 2026-08-14T14:00:00+09:00 https://baba9811.github.io/en/papers/0032-hierarchical-self-improvement-a-framework-for-task-specific/ 2026-08-14T14:00:00+09:00 https://baba9811.github.io/papers/0033-ragu-a-multi-step-graphrag-engine-with-a-compact-domain-adap/ 2026-08-20T14:00:00+09:00 https://baba9811.github.io/en/papers/0033-ragu-a-multi-step-graphrag-engine-with-a-compact-domain-adap/ 2026-08-20T14:00:00+09:00 https://baba9811.github.io/papers/0034-agentic-method-for-deterministic-validation-of-legacy-code/ 2026-08-21T14:00:00+09:00 https://baba9811.github.io/en/papers/0034-agentic-method-for-deterministic-validation-of-legacy-code/ 2026-08-21T14:00:00+09:00 https://baba9811.github.io/papers/0035-accurate-decoding-of-natural-sentences-from-non-invasive-bra/ 2026-08-24T14:00:00+09:00 https://baba9811.github.io/en/papers/0035-accurate-decoding-of-natural-sentences-from-non-invasive-bra/ 2026-08-24T14:00:00+09:00 https://baba9811.github.io/papers/0036-the-embedder-s-dilemma-llms-are-better-but-at-what-cost/ 2026-09-14T08:37:52+09:00 https://baba9811.github.io/en/papers/0036-the-embedder-s-dilemma-llms-are-better-but-at-what-cost/ 2026-09-14T08:37:52+09:00 https://baba9811.github.io/papers/0037-sampling-via-decision-flow-training-free-extraction-of-impro/ 2026-09-15T17:18:46+09:00 https://baba9811.github.io/en/papers/0037-sampling-via-decision-flow-training-free-extraction-of-impro/ 2026-09-15T17:18:46+09:00 https://baba9811.github.io/papers/0038-dapo-improving-multi-step-reasoning-abilities-of-large-langu/ 2026-09-17T09:40:12+09:00 https://baba9811.github.io/en/papers/0038-dapo-improving-multi-step-reasoning-abilities-of-large-langu/ 2026-09-17T09:40:12+09:00 https://baba9811.github.io/papers/0039-e-commerce-bench-evaluating-llm-agents-on-long-horizon-auton/ 2026-09-18T08:10:45+09:00 https://baba9811.github.io/en/papers/0039-e-commerce-bench-evaluating-llm-agents-on-long-horizon-auton/ 2026-09-18T08:10:45+09:00 https://baba9811.github.io/papers/0040-procedural-graphs-self-evolving-execution-structures-for-llm/ 2026-09-21T08:18:01+09:00 https://baba9811.github.io/en/papers/0040-procedural-graphs-self-evolving-execution-structures-for-llm/ 2026-09-21T08:18:01+09:00 https://baba9811.github.io/papers/0041-compile-by-training-turning-natural-language-specifications/ 2026-09-23T13:10:07+09:00 https://baba9811.github.io/en/papers/0041-compile-by-training-turning-natural-language-specifications/ 2026-09-23T13:10:07+09:00 https://baba9811.github.io/papers/0042-lige-gr-a-smooth-leap-from-ranking-to-generative-recommendat/ 2026-09-28T07:21:37+09:00 https://baba9811.github.io/en/papers/0042-lige-gr-a-smooth-leap-from-ranking-to-generative-recommendat/ 2026-09-28T07:21:37+09:00 https://baba9811.github.io/papers/0043-gepa-reflective-prompt-evolution-can-outperform-reinforcemen/ 2026-09-28T08:30:24+09:00 https://baba9811.github.io/en/papers/0043-gepa-reflective-prompt-evolution-can-outperform-reinforcemen/ 2026-09-28T08:30:24+09:00 https://baba9811.github.io/papers/0044-agentic-routing-the-harness-native-data-flywheel/ 2026-09-30T15:24:47+09:00 https://baba9811.github.io/en/papers/0044-agentic-routing-the-harness-native-data-flywheel/ 2026-09-30T15:24:47+09:00 https://baba9811.github.io/papers/0045-hybridcua-learning-to-orchestrate-gui-and-cli-for-computer-u/ 2026-10-01T09:06:31+09:00 https://baba9811.github.io/en/papers/0045-hybridcua-learning-to-orchestrate-gui-and-cli-for-computer-u/ 2026-10-01T09:06:31+09:00 https://baba9811.github.io/papers/0046-learning-from-research-toward-lifelong-agent-harness-evoluti/ 2026-10-02T12:09:29+09:00 https://baba9811.github.io/en/papers/0046-learning-from-research-toward-lifelong-agent-harness-evoluti/ 2026-10-02T12:09:29+09:00 https://baba9811.github.io/papers/0047-rrsi-regularized-recursive-self-improvement-of-agent-harness/ 2026-10-06T00:22:33+09:00 https://baba9811.github.io/en/papers/0047-rrsi-regularized-recursive-self-improvement-of-agent-harness/ 2026-10-06T00:22:33+09:00 https://baba9811.github.io/papers/0048-bazaarbench-delegation-safety-in-decentralized-c2c-marketpla/ 2026-10-07T16:29:17+09:00 https://baba9811.github.io/en/papers/0048-bazaarbench-delegation-safety-in-decentralized-c2c-marketpla/ 2026-10-07T16:29:17+09:00 https://baba9811.github.io/papers/0049-jev-as-a-judge-accept-when-confident-escalate-when-unsure/ 2026-10-08T09:05:26+09:00 https://baba9811.github.io/en/papers/0049-jev-as-a-judge-accept-when-confident-escalate-when-unsure/ 2026-10-08T09:05:26+09:00 https://baba9811.github.io/ https://baba9811.github.io/en/open-source/ https://baba9811.github.io/open-source/ https://baba9811.github.io/privacy/ https://baba9811.github.io/blog/2026/ https://baba9811.github.io/blog/tag/long-context/ https://baba9811.github.io/blog/tag/vlm/ https://baba9811.github.io/blog/tag/document-understanding/ https://baba9811.github.io/blog/tag/sft/ https://baba9811.github.io/blog/tag/cpt/ https://baba9811.github.io/blog/tag/preference-optimization/ https://baba9811.github.io/blog/tag/multimodal/ https://baba9811.github.io/blog/tag/multi-agent/ https://baba9811.github.io/blog/tag/llm/ https://baba9811.github.io/blog/tag/finance/ https://baba9811.github.io/blog/tag/trading/ https://baba9811.github.io/blog/tag/agentic-debate/ https://baba9811.github.io/blog/tag/react/ https://baba9811.github.io/blog/tag/diffusion-llm/ https://baba9811.github.io/blog/tag/unified-model/ https://baba9811.github.io/blog/tag/image-generation/ https://baba9811.github.io/blog/tag/image-editing/ https://baba9811.github.io/blog/tag/moe/ https://baba9811.github.io/blog/tag/vector-quantization/ https://baba9811.github.io/blog/tag/kv-cache/ https://baba9811.github.io/blog/tag/nearest-neighbor/ https://baba9811.github.io/blog/tag/rabitq/ https://baba9811.github.io/blog/tag/llm-inference/ https://baba9811.github.io/blog/tag/compression/ https://baba9811.github.io/blog/tag/ai/ https://baba9811.github.io/blog/tag/crm/ https://baba9811.github.io/blog/tag/qualitative-research/ https://baba9811.github.io/blog/tag/ethics-by-design/ https://baba9811.github.io/blog/tag/framework/ https://baba9811.github.io/blog/tag/b2b/ https://baba9811.github.io/blog/tag/lead-scoring/ https://baba9811.github.io/blog/tag/marketing/ https://baba9811.github.io/blog/tag/gradient-boosting/ https://baba9811.github.io/blog/tag/machine-learning/ https://baba9811.github.io/blog/tag/ai-crm/ https://baba9811.github.io/blog/tag/dynamic-capabilities/ https://baba9811.github.io/blog/tag/scoping-review/ https://baba9811.github.io/blog/tag/customer-relationship-management/ https://baba9811.github.io/blog/tag/lvlm/ https://baba9811.github.io/blog/tag/vision-language/ https://baba9811.github.io/blog/tag/attention/ https://baba9811.github.io/blog/tag/hallucination/ https://baba9811.github.io/blog/tag/multimodal-reasoning/ https://baba9811.github.io/blog/tag/qwen3-vl/ https://baba9811.github.io/blog/tag/personalized-marketing/ https://baba9811.github.io/blog/tag/k-means-clustering/ https://baba9811.github.io/blog/tag/lime/ https://baba9811.github.io/blog/tag/customer-segmentation/ https://baba9811.github.io/blog/tag/explainable-ai/ https://baba9811.github.io/blog/tag/audience-expansion/ https://baba9811.github.io/blog/tag/lookalike-modeling/ https://baba9811.github.io/blog/tag/knowledge-graph/ https://baba9811.github.io/blog/tag/graph-neural-network/ https://baba9811.github.io/blog/tag/recommender-systems/ https://baba9811.github.io/blog/tag/advertising/ https://baba9811.github.io/blog/tag/recommendation-system/ https://baba9811.github.io/blog/tag/llm-agent/ https://baba9811.github.io/blog/tag/hyperparameter-optimization/ https://baba9811.github.io/blog/tag/ab-testing/ https://baba9811.github.io/blog/tag/auxiliary-learning/ https://baba9811.github.io/blog/tag/multi-task-learning/ https://baba9811.github.io/blog/tag/factorization-machine/ https://baba9811.github.io/blog/tag/ads-ranking/ https://baba9811.github.io/blog/tag/representation-bias/ https://baba9811.github.io/blog/tag/toxicity/ https://baba9811.github.io/blog/tag/multilingual/ https://baba9811.github.io/blog/tag/llm-evaluation/ https://baba9811.github.io/blog/tag/safety/ https://baba9811.github.io/blog/tag/benchmark/ https://baba9811.github.io/blog/tag/participatory-design/ https://baba9811.github.io/blog/tag/llm-as-a-judge/ https://baba9811.github.io/blog/tag/evaluation/ https://baba9811.github.io/blog/tag/zero-knowledge-proof/ https://baba9811.github.io/blog/tag/trust/ https://baba9811.github.io/blog/tag/low-resource-language/ https://baba9811.github.io/blog/tag/monolingual-lm/ https://baba9811.github.io/blog/tag/multilingual-nlp/ https://baba9811.github.io/blog/tag/perplexity/ https://baba9811.github.io/blog/tag/pretraining/ https://baba9811.github.io/blog/tag/lora/ https://baba9811.github.io/blog/tag/rlhf/ https://baba9811.github.io/blog/tag/infrastructure/ https://baba9811.github.io/blog/tag/multi-tenant-serving/ https://baba9811.github.io/blog/tag/post-training/ https://baba9811.github.io/blog/tag/gui-agent/ https://baba9811.github.io/blog/tag/vision-language-action/ https://baba9811.github.io/blog/tag/visual-grounding/ https://baba9811.github.io/blog/tag/token-selection/ https://baba9811.github.io/blog/tag/computer-use/ https://baba9811.github.io/blog/tag/on-device/ https://baba9811.github.io/blog/tag/multimodal-llm/ https://baba9811.github.io/blog/tag/reinforcement-learning/ https://baba9811.github.io/blog/tag/grounding/ https://baba9811.github.io/blog/tag/mobile/ https://baba9811.github.io/blog/tag/inference-acceleration/ https://baba9811.github.io/blog/tag/online-exploration/ https://baba9811.github.io/blog/tag/personalization/ https://baba9811.github.io/blog/tag/causal-inference/ https://baba9811.github.io/blog/tag/targeting/ https://baba9811.github.io/blog/tag/experimentation/ https://baba9811.github.io/blog/tag/uplift-modeling/ https://baba9811.github.io/blog/tag/treatment-effect/ https://baba9811.github.io/blog/tag/real-time-marketing/ https://baba9811.github.io/blog/tag/representation-learning/ https://baba9811.github.io/blog/tag/multi-interest/ https://baba9811.github.io/blog/tag/sequential-recommendation/ https://baba9811.github.io/blog/tag/survey/ https://baba9811.github.io/blog/tag/user-modeling/ https://baba9811.github.io/blog/tag/generative-recommendation/ https://baba9811.github.io/blog/tag/large-language-models/ https://baba9811.github.io/blog/tag/diffusion-models/ https://baba9811.github.io/blog/tag/ai-safety/ https://baba9811.github.io/blog/tag/frontier-risk/ https://baba9811.github.io/blog/tag/cybersecurity/ https://baba9811.github.io/blog/tag/biosecurity/ https://baba9811.github.io/blog/tag/honesty/ https://baba9811.github.io/blog/tag/sponge-attack/ https://baba9811.github.io/blog/tag/llm-security/ https://baba9811.github.io/blog/tag/denial-of-service/ https://baba9811.github.io/blog/tag/agentic-defense/ https://baba9811.github.io/blog/tag/prompt-optimization/ https://baba9811.github.io/blog/tag/synthetic-data/ https://baba9811.github.io/blog/tag/llm-agents/ https://baba9811.github.io/blog/tag/self-instruct/ https://baba9811.github.io/blog/tag/grpo/ https://baba9811.github.io/blog/tag/data-generation/ https://baba9811.github.io/blog/tag/mixture-of-experts/ https://baba9811.github.io/blog/tag/linear-attention/ https://baba9811.github.io/blog/tag/open-weights/ https://baba9811.github.io/blog/tag/llm-infrastructure/ https://baba9811.github.io/blog/tag/ai4ai/ https://baba9811.github.io/blog/tag/recursive-self-improvement/ https://baba9811.github.io/blog/tag/mle-agent/ https://baba9811.github.io/blog/tag/evolutionary-search/ https://baba9811.github.io/blog/tag/agent/ https://baba9811.github.io/blog/tag/autonomous-research/ https://baba9811.github.io/blog/tag/verifiability/ https://baba9811.github.io/blog/tag/ai-scientist/ https://baba9811.github.io/blog/tag/scaling-laws/ https://baba9811.github.io/blog/tag/compute-optimal/ https://baba9811.github.io/blog/tag/chinchilla/ https://baba9811.github.io/blog/tag/extrapolation/ https://baba9811.github.io/blog/tag/agent-framework/ https://baba9811.github.io/blog/tag/code-as-action/ https://baba9811.github.io/blog/tag/tool-use/ https://baba9811.github.io/blog/tag/python/ https://baba9811.github.io/blog/tag/memory/ https://baba9811.github.io/blog/tag/benchmarks/ https://baba9811.github.io/blog/tag/self-improvement/ https://baba9811.github.io/blog/tag/agent-harness/ https://baba9811.github.io/blog/tag/meta-evolution/ https://baba9811.github.io/blog/tag/balrog/ https://baba9811.github.io/blog/tag/frozen-backbone/ https://baba9811.github.io/blog/tag/graphrag/ https://baba9811.github.io/blog/tag/retrieval-augmented-generation/ https://baba9811.github.io/blog/tag/information-extraction/ https://baba9811.github.io/blog/tag/small-language-models/ https://baba9811.github.io/blog/tag/open-source/ https://baba9811.github.io/blog/tag/software-testing/ https://baba9811.github.io/blog/tag/agentic-systems/ https://baba9811.github.io/blog/tag/legacy-migration/ https://baba9811.github.io/blog/tag/cobol/ https://baba9811.github.io/blog/tag/mutation-testing/ https://baba9811.github.io/blog/tag/differential-testing/ https://baba9811.github.io/blog/tag/search-based-testing/ https://baba9811.github.io/blog/tag/brain-computer-interface/ https://baba9811.github.io/blog/tag/meg/ https://baba9811.github.io/blog/tag/brain-to-text/ https://baba9811.github.io/blog/tag/ctc/ https://baba9811.github.io/blog/tag/neuroscience/ https://baba9811.github.io/blog/tag/text-embeddings/ https://baba9811.github.io/blog/tag/retrieval/ https://baba9811.github.io/blog/tag/inference-cost/ https://baba9811.github.io/blog/tag/reranking/ https://baba9811.github.io/blog/tag/reasoning/ https://baba9811.github.io/blog/tag/inference-time-scaling/ https://baba9811.github.io/blog/tag/tree-search/ https://baba9811.github.io/blog/tag/sampling/ https://baba9811.github.io/blog/tag/offline-rl/ https://baba9811.github.io/blog/tag/credit-assignment/ https://baba9811.github.io/blog/tag/value-function/ https://baba9811.github.io/blog/tag/long-horizon/ https://baba9811.github.io/blog/tag/e-commerce/ https://baba9811.github.io/blog/tag/negotiation/ https://baba9811.github.io/blog/tag/agent-memory/ https://baba9811.github.io/blog/tag/procedural-memory/ https://baba9811.github.io/blog/tag/graph/ https://baba9811.github.io/blog/tag/program-as-weights/ https://baba9811.github.io/blog/tag/model-distillation/ https://baba9811.github.io/blog/tag/local-inference/ https://baba9811.github.io/blog/tag/listwise-ranking/ https://baba9811.github.io/blog/tag/beam-search/ https://baba9811.github.io/blog/tag/production-ml/ https://baba9811.github.io/blog/tag/reflection/ https://baba9811.github.io/blog/tag/compound-ai/ https://baba9811.github.io/blog/tag/llm-routing/ https://baba9811.github.io/blog/tag/agents/ https://baba9811.github.io/blog/tag/harness/ https://baba9811.github.io/blog/tag/ensemble/ https://baba9811.github.io/blog/tag/cost-efficiency/ https://baba9811.github.io/blog/tag/off-policy-learning/ https://baba9811.github.io/blog/tag/gui-agents/ https://baba9811.github.io/blog/tag/command-line/ https://baba9811.github.io/blog/tag/agent-training/ https://baba9811.github.io/blog/tag/regularization/ https://baba9811.github.io/blog/tag/generalization/ https://baba9811.github.io/blog/tag/agent-safety/ https://baba9811.github.io/blog/tag/marketplace/ https://baba9811.github.io/blog/tag/confidence/ https://baba9811.github.io/blog/tag/model-routing/ https://baba9811.github.io/blog/tag/calibration/ https://baba9811.github.io/blog/category/paper-review/ https://baba9811.github.io/blog/ https://baba9811.github.io/blog/page/2/ https://baba9811.github.io/blog/page/3/ https://baba9811.github.io/blog/page/4/ https://baba9811.github.io/blog/page/5/ https://baba9811.github.io/en/blog/ https://baba9811.github.io/en/blog/page/2/ https://baba9811.github.io/en/blog/page/3/ https://baba9811.github.io/en/blog/page/4/ https://baba9811.github.io/en/blog/page/5/ https://baba9811.github.io/google9189f0aae61ed756.html 2026-10-14T15:54:44+09:00