[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"article-memory-autonomous-llm-agents-survey-en":3,"tags-memory-autonomous-llm-agents-survey-en":37,"related-lang-memory-autonomous-llm-agents-survey-en":47,"related-posts-memory-autonomous-llm-agents-survey-en":51,"series-research-97c4ad76-6560-4456-b7a3-d7c226ca1303":88},{"id":4,"title":5,"content":6,"summary":7,"source":8,"source_url":9,"author":10,"image_url":11,"keywords":12,"language":18,"translated_content":10,"views":19,"is_premium":20,"created_at":21,"updated_at":21,"cover_image":11,"published_at":22,"rewrite_status":23,"rewrite_error":10,"rewritten_from_id":24,"slug":25,"category":26,"related_article_id":27,"status":28,"google_indexed_at":29,"x_posted_at":10,"tweet_text":10,"title_rewritten_at":10,"title_original":10,"key_takeaways":30,"topic_cluster_id":34,"embedding":35,"is_canonical_seed":36},"97c4ad76-6560-4456-b7a3-d7c226ca1303","How Memory Shapes Autonomous LLM Agents","\u003Cp data-speakable=\"summary\">This survey explains how memory is designed, implemented, and evaluated in autonomous \u003Ca href=\"\u002Ftag\u002Fllm\">LLM\u003C\u002Fa> agents.\u003C\u002Fp>\u003Cp>Autonomous LLM agents are only as useful as what they can remember. This survey, \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.07670\">Memory for Autonomous LLM Agents: Mechanisms, Evaluation, and Emerging Frontiers\u003C\u002Fa>, pulls together work from 2022 through early 2026 to show how memory helps agents persist information across interactions, tasks, and sessions.\u003C\u002Fp>\u003Cp>For developers, the practical question is simple: how do you make an \u003Ca href=\"\u002Ftag\u002Fagent\">agent\u003C\u002Fa> that does not start from zero every time? The paper frames memory as a core capability, not a nice-to-have, and treats it as something that must be designed, measured, and reasoned about rather than bolted on as an afterthought.\u003C\u002Fp>\u003Ch2>What problem this paper is trying to fix\u003C\u002Fh2>\u003Cp>The survey starts from the basic limitation of \u003Ca href=\"\u002Ftag\u002Fllms\">LLMs\u003C\u002Fa>: by themselves, they do not naturally retain useful state across separate interactions. That is a problem for agents expected to act over time, remember prior context, and adapt based on earlier outcomes.\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778568646315-jf2i.png\" alt=\"How Memory Shapes Autonomous LLM Agents\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>In practice, memory affects whether an agent can keep track of user preferences, past actions, task progress, and other long-running context. Without memory, even a capable model can behave like a stateless chatbot that repeatedly relearns the same facts.\u003C\u002Fp>\u003Cp>The paper’s goal is to organize the fast-growing literature around that issue. Instead of treating memory as one technique, it presents it as a design space with multiple mechanisms, evaluation approaches, and open research questions.\u003C\u002Fp>\u003Ch2>How memory works in plain English\u003C\u002Fh2>\u003Cp>The abstract does not give a single algorithm, because this is a survey rather than a new system. Instead, it says the paper offers a structured account of how memory is designed and implemented in modern LLM-based agents.\u003C\u002Fp>\u003Cp>That means the focus is on the building blocks: what gets stored, when it gets written, how it gets retrieved, and how it is used by the agent later. In other words, memory is treated as a pipeline for persisting and reusing information across time.\u003C\u002Fp>\u003Cp>For engineers, that framing matters because “memory” can mean very different things depending on the system. It may refer to short-term context management, longer-lived agent state, or some broader mechanism for carrying information across tasks. The survey’s value is in mapping those ideas into a coherent picture.\u003C\u002Fp>\u003Cul>\u003Cli>Memory is about persistence across interactions, not just larger prompts.\u003C\u002Fli>\u003Cli>Agent memory has to be implemented, not assumed.\u003C\u002Fli>\u003Cli>Evaluation is part of the problem, not an afterthought.\u003C\u002Fli>\u003Cli>The field spans work from 2022 through early 2026.\u003C\u002Fli>\u003C\u002Ful>\u003Ch2>What the paper actually shows\u003C\u002Fh2>\u003Cp>Because this is a survey, the paper does not report a new \u003Ca href=\"\u002Ftag\u002Fbenchmark\">benchmark\u003C\u002Fa> result or a single set of experimental numbers in the abstract. It also does not provide concrete metrics there, so there are no performance figures to quote from the source material.\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778568649828-kpj8.png\" alt=\"How Memory Shapes Autonomous LLM Agents\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>What it does claim is a structured review of the area. The survey covers work from 2022 through early 2026 and organizes it around three themes: mechanisms, evaluation, and emerging frontiers. That gives readers a map of where the field has been and where it is heading.\u003C\u002Fp>\u003Cp>The mention of evaluation is important. Memory systems are easy to describe in theory, but much harder to compare in practice. A survey that explicitly includes evaluation suggests that the authors see measurement as a central challenge, not just an implementation detail.\u003C\u002Fp>\u003Cp>The abstract also signals that the paper looks beyond current techniques toward “emerging frontiers.” The source does not enumerate those frontiers in detail, so the safe takeaway is that the field is still evolving and that the survey is meant to help readers track that evolution.\u003C\u002Fp>\u003Ch2>Why developers should care\u003C\u002Fh2>\u003Cp>If you are building an agent, memory is one of the main levers for making it feel consistent and useful over time. A system that can persist relevant information can support longer workflows, reduce repeated user input, and make multi-step behavior more reliable.\u003C\u002Fp>\u003Cp>This survey is especially useful if you are deciding how to think about memory architecture. The paper does not hand you a turnkey implementation, but it does give you a vocabulary for comparing approaches and a framework for thinking about tradeoffs.\u003C\u002Fp>\u003Cp>That matters because memory can easily become a source of bugs and confusion. If you do not define what gets stored, when it expires, and how it is retrieved, you can end up with agents that are inconsistent, noisy, or overly dependent on stale context.\u003C\u002Fp>\u003Ch2>Limitations and open questions\u003C\u002Fh2>\u003Cp>The biggest limitation in the source material is also the most obvious one: the abstract is high level. It does not list benchmark numbers, detailed experimental setups, or a specific memory algorithm, so readers should not expect a results-heavy paper from the abstract alone.\u003C\u002Fp>\u003Cp>Another limitation is that the paper is a survey. That makes it valuable for orientation, but it does not by itself solve the engineering problem of building robust memory for production agents.\u003C\u002Fp>\u003Cp>Still, that is also the point. The paper is trying to consolidate a rapidly expanding area into something developers can reason about. For teams working on autonomous agents, that kind of survey can be the difference between chasing isolated techniques and understanding the broader design space.\u003C\u002Fp>\u003Cp>The open question the abstract leaves hanging is straightforward: what actually makes memory systems dependable across real-world agent workloads? The survey promises structure around that question, but the source does not claim a final answer. That honesty is useful, because memory for agents is still an active research frontier rather than a settled engineering pattern.\u003C\u002Fp>","A survey of how memory is built, measured, and used in autonomous LLM agents, with a focus on design choices and open problems.","arxiv.org","https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.07670",null,"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778568646315-jf2i.png",[13,14,15,16,17],"LLM agents","memory systems","agent evaluation","autonomous agents","survey","en",3,false,"2026-05-12T06:50:28.319354+00:00","2026-05-12T06:50:28.307+00:00","done","75fce92d-a585-4655-b25e-228b9a0755d3","memory-autonomous-llm-agents-survey-en","research","f3addba5-089a-4841-b194-7e0c7c16da01","published","2026-05-12T09:00:12.283+00:00",[31,32,33],"The paper surveys memory for autonomous LLM agents from 2022 through early 2026.","It focuses on mechanisms, evaluation, and emerging frontiers rather than a new model.","The abstract does not include benchmark numbers or concrete metrics.","3103988e-c4fe-45e3-98ab-846500c9d507","[-0.037094943,-0.0041993344,0.022204427,-0.0731785,0.00053524517,-0.016260484,-0.017521586,0.005405778,-0.007771215,0.022601156,-0.01682212,5.6768135e-05,-0.0031456545,0.0045212633,0.14858302,0.04001394,-0.0009585898,0.019622568,0.007818844,-0.041986454,-0.005906653,0.018961534,-0.014979973,-0.028245656,-0.020259995,0.023879496,-0.012618271,0.013738791,0.04243703,0.02046969,-0.0087463865,0.017012263,-0.0015017122,0.006056073,0.021350017,0.007593753,0.0112495795,-0.006007262,-0.010691052,0.030283684,-0.0028252697,-0.025422601,-0.0066103186,-0.006046451,-0.03181644,0.008197158,-0.0044443607,-0.01278541,-0.029806389,0.013502407,-0.010141661,0.029624922,0.003930388,-0.16349827,0.005310476,-0.01561088,-0.004049315,-0.00840675,-0.0050663813,-0.0034335253,0.0011491562,0.015191153,-0.015513197,-0.0006064619,-0.009867646,-0.0027829467,0.012448489,0.005215583,-0.035836756,-0.010834388,-0.0065409504,-0.023764644,0.00679782,-0.045704965,0.0075077754,-0.022837723,0.01054151,0.017841931,0.0032076212,0.024578918,0.017293261,-0.013343778,-0.009682379,0.0018275701,-0.008625768,-0.008350129,-0.0041841916,-0.008634177,0.0058047827,0.006213903,0.0016161595,-0.0029523633,0.029353337,0.02030389,-0.0028505998,-0.023216145,-0.03512932,0.030093554,0.005546082,0.00089352444,-0.0062198117,-0.0069279587,0.00517021,0.0074451957,0.013300382,-0.000649589,-0.002472174,-0.0006212383,0.0065560495,0.032950237,0.008445437,0.0009683566,-0.01051301,0.003379508,-0.02596366,-0.117973156,0.0061398596,-0.019816147,-0.011204315,-0.0048243576,-0.008450895,0.025313193,0.010988582,0.012858864,0.013025053,0.008958875,0.0075072343,-0.012940098,0.004735377,0.009169945,-0.04227046,-0.011001083,0.017371172,-0.01734118,0.013886653,0.024348866,-0.018295258,-0.029385827,-0.027228585,-0.026158094,0.007493259,0.038228847,0.028781516,-0.0062471344,-0.028737037,0.0080202855,-0.039360408,0.008939339,-0.014676998,0.010554042,0.028868144,-0.014751636,0.00024770273,0.011882553,0.04925905,-0.022051947,0.019862931,0.004201734,-0.0037245664,-0.00025830948,0.012076921,-0.00021966279,0.01826609,0.017574634,0.008744172,0.019194493,-0.009372688,-0.027956612,0.006476803,0.014399254,0.0015406237,-0.025953872,-0.0063129207,-0.03077694,0.019629888,-0.020380985,0.0032879775,-0.02115882,0.010612017,-0.034504652,0.015449701,0.019518416,-0.017626975,0.02132654,-0.006754023,0.014510288,0.006281296,0.02964633,0.024327304,0.0018389777,-0.01815285,-0.011169396,-0.00041011418,-0.010812969,-0.013403491,-0.019679362,-0.021347275,0.0066795554,-0.016542671,0.013253531,0.0042593232,0.018027706,0.026093548,-0.025982296,-0.0034675226,0.0034243292,0.002483968,-0.0036168376,0.009427587,-0.012198033,-0.017674377,0.02681801,0.010113956,0.013716343,0.009332308,-0.009672124,-0.025559662,-0.0036279596,0.029378053,-0.012986821,0.015720172,-0.0047028754,0.019380264,0.009482112,-0.0033143943,0.008042963,-0.0115078045,-0.0014567368,-0.012938949,0.023400145,0.00106369,0.02921049,-0.009273772,0.0027609803,0.021646978,0.008321784,-0.0065722065,0.014408821,0.010768733,0.03084046,-0.0016387963,-0.00079988054,-0.0033996154,0.017305315,0.016463425,-0.018638754,0.022159908,0.030589184,-0.008347731,-0.0100096995,-0.013206262,0.0038547716,0.01106433,0.007593007,-0.037933227,0.001774127,0.00016236262,0.019768806,-0.010576983,-0.013262678,-0.0010892908,0.0024253286,-0.013396606,0.004838812,-0.029249163,0.0023018294,0.0031965973,-0.0033566025,-0.018557671,-0.031802867,-0.0016121045,0.007365854,-0.00890711,0.015860878,0.018582908,-0.019234672,-0.037835855,-0.006918119,0.014819881,0.0021361613,0.0060147434,0.006377531,-0.012246172,0.0020069203,-0.0028720018,0.019910704,-0.0016442527,-0.008013635,-0.00016427007,-0.0009512054,0.015902271,0.008549964,-0.020396495,0.018660223,0.00022502661,-0.017344272,-0.0038734516,0.012678546,-0.00063183636,0.01599923,0.0059430245,-0.02099913,-0.022900457,0.025597705,-0.02568333,-0.008260724,0.009754913,0.015974257,0.007749656,0.015022626,0.0057540485,-0.004296828,0.0051517584,-0.03700637,-0.011754951,-0.0044116075,-0.018318607,-0.022538556,-0.017691672,-0.0262527,0.017955547,-0.012246816,-0.0111532165,-0.0062093777,-0.019461336,-0.0074309995,0.0057524545,0.008067891,0.011437431,-0.014141661,0.0009352662,0.004888839,0.020409597,-0.012216362,0.028659247,-0.007817523,-0.013330138,-0.018445252,0.025858551,0.007917257,-0.011467953,-0.021838231,-0.013084203,0.007040136,-0.02587329,0.042167332,0.02463447,0.01757833,0.008329497,-0.031982824,0.011697761,0.005851209,-0.0010976781,-0.023920221,-0.03048106,0.023698714,0.009476783,0.008729777,0.006955182,0.016859729,0.0027993706,-0.016138239,-0.013629026,-0.002141169,0.02562623,-0.03813281,0.016119774,0.0023494256,-0.029240677,0.0062705562,0.024712268,0.0013285646,-0.009599802,0.0028357506,0.014363582,-0.015755482,-0.015455392,-0.0006096765,-0.025698522,-0.0025930442,-0.021176271,0.024035105,-0.04124327,-0.003572159,0.002851582,0.047624882,0.0190249,0.003574097,0.0060660946,0.031613924,-0.0119375,0.028587868,-0.026003188,-0.0015256478,0.0069778585,-0.002225091,0.0054117567,0.03087175,0.006958401,-0.003358885,-0.011652765,0.020878345,-0.041879334,-0.0010442107,0.011572392,0.007030123,0.011594743,-0.021598997,-7.245091e-05,-0.02150392,0.00788447,0.025282841,0.033560127,-0.01935937,0.015952256,0.011586995,-0.035233237,0.0016364872,-0.0011098505,-0.0038159727,-0.0055559943,0.020459687,-0.020877292,0.0001357856,-0.034897488,0.005490634,-0.012574413,-0.030974936,-0.01489739,-0.030949624,-0.009778081,-0.02723264,-0.020667354,-0.0063561983,-0.0022448138,-0.0012859951,-0.0065733194,-0.029217133,-0.0044280686,-0.010365612,-0.008730442,0.0064604757,-0.005715741,0.0022216663,0.009826174,-0.014826923,-0.0007424187,-0.012785718,-0.029329043,-0.0011414556,0.029021872,0.010226935,0.00110092,0.001355597,-0.020766245,-0.011731113,0.0020118926,0.019186521,-0.009641959,0.0070017003,-0.01995481,-0.025958316,0.011225933,0.017305939,0.016054228,-0.03510065,-0.013601117,-0.001065814,0.012245633,0.024122803,-0.010604628,0.024862744,0.04290696,0.0011416569,-0.00845699,0.013599662,-0.021428596,0.0058598793,0.0018076808,0.0045028767,0.013547855,-0.015374859,0.009245125,-0.053473487,0.003566921,0.023053082,0.015936224,0.020049673,-0.005454103,0.02526282,0.020486437,0.00476542,0.03619203,-0.008267882,-0.019864345,-0.039948862,0.0052280035,-0.0041938787,0.013950098,0.010467977,0.00783623,0.0017470161,-0.0098397285,0.013522568,-0.0026163112,-0.0006222623,-0.015948402,0.005552043,-0.0047947327,0.011003274,-0.0341579,0.0033117156,0.009588781,0.027551936,-0.017676175,-0.024045803,0.015192379,-0.007324014,-0.013218851,0.0081488,-0.0059756776,-0.008786581,0.0028222378,0.043145467,-0.01885505,-0.041691225,0.007996898,0.006886696,0.010790987,0.04420333,-0.0046550534,0.0058009056,0.010731255,-0.033761665,-0.0030559124,-0.02155797,0.03613895,0.024149304,-0.0058413753,0.028459253,-0.027768303,0.0064647016,-0.025624877,-0.0112363435,0.022282448,-0.097040735,0.0024166177,0.015756877,-0.005265962,-0.005250299,0.023556001,0.0024651794,-0.0012915866,0.00745271,0.021340167,-0.0058673425,-0.010475924,0.028330062,0.0023665489,-0.012341244,-0.0073546465,-0.036427308,-0.01229418,0.00062018645,-0.0023484188,0.023693295,0.002847633,-0.00045233927,0.019278092,0.017674886,-0.029232534,0.016767869,0.011819536,0.0072842855,0.021735623,-0.008096171,-0.019294506,-0.015509618,0.010716512,0.013058634,-0.023837825,0.028339507,-0.0070251357,0.010275895,0.017070035,0.01964175,0.005119406,-0.010262543,-0.026922822,-0.03000635,0.012735677,-0.008631423,0.004181363,0.0069755013,0.024990456,-0.024264911,-0.005472645,-0.010429075,-0.015142703,-0.01958704,-0.02211841,-0.011887545,0.006084853,-0.031017212,-0.010874853,-0.011661535,0.0010269738,0.006307938,0.023911512,-0.0029151342,0.018534137,0.012337632,0.024745556,-0.013597706,0.008272445,-0.011645082,-0.021402782,0.021673514,-0.0129937045,-0.009307484,0.021658026,-0.011777153,0.004796979,-0.0006271128,0.016583882,-0.014060554,-0.025401415,-0.08428644,-0.012039902,0.016604906,-0.0005424827,-0.00085923064,-0.013729751,0.0010133017,-0.010174434,0.0094717415,-0.04070126,-0.0020312057,-0.004484544,-0.01012234,-0.029157616,0.00890329,0.0014822616,0.0014068696,-0.020559479,0.009531582,-0.044319768,0.004501575,-0.02277776,0.058407903,-0.020170167,-0.0106335115,0.015175056,-0.018984511,0.010145428,0.0033610032,0.0015629407,-0.021498905,-0.13720842,0.01649157,0.013713779,-0.0047269524,0.002622519,-0.0027960094,-0.0035221206,0.031321067,0.024609163,-0.014275658,-0.0074712485,-0.014483943,-0.024050042,-0.0067679137,-0.028310586,0.08706011,-0.00810441,0.0037130616,-0.029375656,-0.027274234,-0.0018256827,-0.024738561,-0.03189494,0.0029884188,-0.0069296877,-0.019776868,0.023275223,-0.0022306424,-0.0034279095,0.03515694,0.020199874,0.005647224,0.0044503952,-0.012765583,0.012015415,-0.007571265,0.00010088473,-0.05811612,-0.012454865,0.026028149,0.014393367,0.024778012,0.010031084,-0.013067297,-0.0049366113,0.012233315,-0.01921858,-0.007802523,-0.0023613267,-0.0061425134,-0.009088416,-0.07168517,-0.0060874633,-0.009798439,0.023019357,0.009981055,0.0035254199,0.0012853947,-0.013140946,0.021274138,0.019990338,-0.01130199,-0.029724697,0.006166004,-0.021962894,-0.027641192,0.02129766,-0.0014181266,-0.013202398,0.0140508795,0.008394231,-0.0058182045,0.0248126,-0.014109583,-0.0031317747,-0.0038701328,0.021218786,0.025255451,0.03663549,-0.021516742,-0.0024097913,0.017864533,0.008415758,0.009713569,0.008621663,-0.002063505,-0.0070388713,-0.015207202,0.014295743,0.003845302,-0.015175051,0.0274782,0.0039167115,0.025316758,0.015851215,0.038526937,-0.0010945889,-0.018547473,-0.014203291,-0.015535777,-0.0034969703,-0.021847237,0.014426599,-0.029541543,-0.00996103,0.030959057,0.008979489,0.0007237631,0.025439885,-0.004578026]",true,[38,40,42,44,46],{"name":14,"slug":39},"memory-systems",{"name":15,"slug":41},"agent-evaluation",{"name":16,"slug":43},"autonomous-agents",{"name":13,"slug":45},"llm-agents",{"name":17,"slug":17},{"id":27,"slug":48,"title":49,"language":50},"memory-autonomous-llm-agents-survey-zh","自動化 LLM Agent 的記憶怎麼設計","zh",[52,58,64,70,76,82],{"id":53,"slug":54,"title":55,"cover_image":56,"image_url":56,"created_at":57,"category":26},"94994abd-e24d-4fd1-b941-942d03d19acf","turboquant-seo-shift-small-sites-en","TurboQuant and the SEO Shift for Small Sites","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778840455122-jfce.png","2026-05-15T10:20:28.134545+00:00",{"id":59,"slug":60,"title":61,"cover_image":62,"image_url":62,"created_at":63,"category":26},"670a7f69-911f-41e8-a18b-7d3491253a19","turboquant-vllm-comparison-fp8-kv-cache-en","TurboQuant vs FP8: vLLM’s first broad test","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778839858405-b5ao.png","2026-05-15T10:10:37.219158+00:00",{"id":65,"slug":66,"title":67,"cover_image":68,"image_url":68,"created_at":69,"category":26},"5aef1c57-961f-49f7-8277-f83f7336799a","llmbda-calculus-agent-safety-rules-en","LLMbda calculus gives agents safety rules","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778825459914-obkf.png","2026-05-15T06:10:36.242145+00:00",{"id":71,"slug":72,"title":73,"cover_image":74,"image_url":74,"created_at":75,"category":26},"712a0357-f7cd-48f2-adde-c2691da0815f","low-complexity-beamspace-denoiser-mmwave-mimo-en","A simpler beamspace denoiser for mmWave MIMO","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778814646705-e7mx.png","2026-05-15T03:10:31.764301+00:00",{"id":77,"slug":78,"title":79,"cover_image":80,"image_url":80,"created_at":81,"category":26},"f595f949-6ea1-4b0e-a632-f1832ef26e36","ai-benchmark-wins-cyber-scare-defenders-en","Why AI benchmark wins in cyber should scare defenders","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778807444539-gz7f.png","2026-05-15T01:10:30.04579+00:00",{"id":83,"slug":84,"title":85,"cover_image":86,"image_url":86,"created_at":87,"category":26},"3ad202d1-9e5f-49c5-8383-02fcf1a23cf2","why-linux-security-needs-patch-wave-mindset-en","Why Linux security needs a patch-wave mindset","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778741441493-ikl6.png","2026-05-14T06:50:25.906256+00:00",[89,94,99,104,109,114,119,124,129,134],{"id":90,"slug":91,"title":92,"created_at":93},"a2715e72-1fe8-41b3-abb1-d0cf1f710189","ai-predictions-2026-big-changes-en","AI Predictions for 2026: Brace for Big Changes","2026-03-26T01:25:07.788356+00:00",{"id":95,"slug":96,"title":97,"created_at":98},"8404bd7b-4c2f-4109-9ec4-baf29d88af2b","ml-papers-of-the-week-github-research-desk-en","ML Papers of the Week Turns GitHub Into a Research Desk","2026-03-27T01:11:39.480259+00:00",{"id":100,"slug":101,"title":102,"created_at":103},"87897a94-8065-4464-a016-1f23e89e17cc","ai-ml-conferences-to-watch-in-2026-en","AI\u002FML Conferences to Watch in 2026","2026-03-27T01:51:54.184108+00:00",{"id":105,"slug":106,"title":107,"created_at":108},"6f1987cf-25f3-47a4-b3e6-db0997695be8","openclaw-agents-manipulated-self-sabotage-en","OpenClaw Agents Can Be Manipulated Into Failure","2026-03-28T03:03:18.899465+00:00",{"id":110,"slug":111,"title":112,"created_at":113},"a53571ad-735a-4178-9f93-cb09b699d99c","vega-driving-language-instructions-en","Vega: Driving with Natural Language Instructions","2026-03-28T14:54:04.698882+00:00",{"id":115,"slug":116,"title":117,"created_at":118},"a34581d6-f36e-46da-88bb-582fb3e7425c","personalizing-autonomous-driving-styles-en","Drive My Way: Personalizing Autonomous Driving Styles","2026-03-28T14:54:26.148181+00:00",{"id":120,"slug":121,"title":122,"created_at":123},"2bc1ad7f-26ce-4f02-9885-803b35fd229d","training-knowledge-bases-writeback-rag-en","Training Knowledge Bases with WriteBack-RAG","2026-03-28T14:54:45.643433+00:00",{"id":125,"slug":126,"title":127,"created_at":128},"71adc507-3c54-4605-bbe2-c966acd6187e","packforcing-long-video-generation-en","PackForcing: Efficient Long-Video Generation Method","2026-03-28T14:55:02.646943+00:00",{"id":130,"slug":131,"title":132,"created_at":133},"675942ef-b9ec-4c5f-a997-381250b6eacb","pixelsmile-facial-expression-editing-en","PixelSmile Framework Enhances Facial Expression Editing","2026-03-28T14:55:20.633463+00:00",{"id":135,"slug":136,"title":137,"created_at":138},"6954fa2b-8b66-4839-884b-e46f89fa1bc3","adaptive-block-scaled-data-types-en","IF4: Smarter 4-Bit Quantization That Adapts to Your Data","2026-03-31T06:00:36.65963+00:00"]