Kishan @kpb_in_acad
ಕನ್ನಡಿಗ #AGI Researcher @TencentGlobal Previous: @Caltech @tamu @MSFTResearch @qualcomm_in Note: Tweets aren't professional; I often delete -- insecurity! sites.google.com/a/tamu.edu/kpb Seattle, US Joined January 2014-
Tweets3K
-
Followers374
-
Following674
-
Likes29K
LLMs trained without labels tend to collapse in diversity. We have a fix. Introducing EVOL-RL, a new method inspired by biological evolution: ✅ Selection: Anchor on the majority answer. 💡 Variation: Reward novel reasoning paths. 📄 Paper: arxiv.org/abs/2509.15194
RL often cause 𝐞𝐧𝐭𝐫𝐨𝐩𝐲 𝐜𝐨𝐥𝐥𝐚𝐩𝐬𝐞: generations become shorter, less diverse, and brittle. A simple fix is 𝐝𝐢𝐯𝐞𝐫𝐬𝐢𝐭𝐲 reward to boost exploration. I use it in many of my projects — surprisingly effective! Details in our NEW paper: arxiv.org/abs/2509.15194
Also strongly recommend this paper on diversity reward in RL! The insights line up closely -- well worth reading together. https:// arxiv.org/abs/2509.15194 (Tencent) https:// arxiv.org/abs/2509.02534 (Meta) Not sure which diversity reward wins out 😀 (embedding vs…
Also strongly recommend this paper on diversity reward in RL! The insights line up closely -- well worth reading together. https:// arxiv.org/abs/2509.15194 (Tencent) https:// arxiv.org/abs/2509.02534 (Meta) Not sure which diversity reward wins out 😀 (embedding vs… https://t.co/HTu1NzJMdz
even tho I skipped attending any major conference for ~1 year, i am content finding these gems! esp, Prof. Dayan's talk had a refreshing view of RL objectives for me.
even tho I skipped attending any major conference for ~1 year, i am content finding these gems! esp, Prof. Dayan's talk had a refreshing view of RL objectives for me.
🧵 Academic job market season is almost here! There's so much rarely discussed—nutrition, mental and physical health, uncertainty, and more. I'm sharing my statements, essential blogs, and personal lessons here, with more to come in the upcoming weeks! ⬇️ (1/N)
NVIDIA's Academic Grant Program is back! Submit your groundbreaking ideas on Robotics and Edge AI (humanoid robotics, foundation models, simulations, ...) and turn them into reality.
NVIDIA's Academic Grant Program is back! Submit your groundbreaking ideas on Robotics and Edge AI (humanoid robotics, foundation models, simulations, ...) and turn them into reality.
fwiw, I think Prof. @percyliang and the CS336 team nailed this: Sutton’s Bitter Lesson is often misinterpreted as “scale is all that matters” and/or “algorithms don’t matter.” The more accurate – and useful – interpretation is: what matters are the algorithms that scale.…
We're excited to share our latest research, focusing on better understanding and navigating dynamic real-world environments for autonomous systems. We introduce STRIDE, a new spatio-temporal road image dataset, & TARDIS, a world model that leverages it. tera-ai.com/blog/tardis
1/ ☕ Introducing our latest work: Robust LLM Alignment via Distributionally Robust Direct Preference Optimization Traditional methods like RLHF & DPO assume training = deployment preferences — but that often breaks in real-world LLM alignment. We fix that.
Not on our bingo card!
“High Dimensional Probability” is one of favorite books of all time. I even taught it once. Now, the second edition is out. math.uci.edu/~rvershyn/pape…
WE ARE THE CHAMPIONS.
#AISTATS2025 Oral 🚀Hybrid Transfer Reinforcement Learning: Provable Sample Efficiency from Shifted-Dynamics Data I really love this new problem framework to inspire new algorithms for data-efficient generalization to unseen/shifted testing environments Welcome to our sessions!
I wrote a post on how to connect with people (i.e., make friends) at CS conferences. These events can be intimidating so here's some suggestions on how to navigate them I'm late for #ICLR2025 #NAACL2025, but just in time for #AISTATS2025 and timely for #ICML2025 acceptances! 1/4
Test of Time Winner Adam: A Method for Stochastic Optimization Diederik P. Kingma, Jimmy Ba Adam revolutionized neural network training, enabling significantly faster convergence and more stable training across a wide variety of architectures and tasks.

Michal Valko @misovalko
8K Followers 8K Following Building something new · Chief Models Officer @ Stealth Startup & Inria & MVA - Ex: Llama @AIatMeta Gemini and BYOL @GoogleDeepMind
Amin Karbasi @aminkarbasi
11K Followers 3K Following Senior director of Cisco Foundation AI, Former Chief Scientist at Robust Intelligence. ex Professor at Yale University, ex staff research scientist at Google.
Gergely Neu @neu_rips
11K Followers 684 Following ML theory nerd & AI non-enthusiast. thinking a lot about online learning these days! BTW you should go find me on another website where i post more actively
Prof. Anima Anandkuma... @AnimaAnandkumar
34K Followers 2K Following "Godmother" of AI+Science, Bren Professor @caltech, Time100, Fmr Sr Director of #AI research @nvidia Fmr Principal Scientist @awscloud
Mathieu @miniapeur
34K Followers 2K Following Non-member of the technical staff in a non-frontier lab. Gradient surfer by day, Möbius stripper by night. PhD @ai_ucl.
Yisong Yue @yisongyue
22K Followers 3K Following Machine Learning @Caltech (@YueLabCaltech). AI for invention at @AsariAILabs.
Zhongwen Xu @zhongwen2009
984 Followers 1K Following Principal Researcher at Tencent, ex-DeepMinder (@GoogleDeepMind), ex-SAILer (@SeaAIL)
Yujun Zhou @YujunZhou0017
32 Followers 43 Following Third-year CS PhD at the University of Notre Dame. Intern at Tencent AI lab, Seattle
Satnam Singh @satnam6502
20K Followers 3K Following Punjabi-Scottish-American computer scientist, cook, cyclist, Lost In Music. ∃🇮🇳 ∧ ∀🇬🇧 ∧ ∃🇪🇺 ∧ ∀🇺🇸 #celiac ex-{Microsoft, Google, Facebook, Xilinx}
Junyuan "Jason" Hong @hjy836
1K Followers 3K Following Incoming AP @NUS ECE. Currently @MGH @HMS, prior @VITAGroupUT @MLFoundations. PhD @MSU. Ex @SonyAI. MLSys Rising Star 2024. Interests: Responsible AI, Health.
Arnob Ghosh @Arnobg32
54 Followers 115 Following Assistant Prof. at NJIT ECE, Former Research Scientist at OSU ECE, Former Assist. Prof. at IIT-Delhi, Ph.D. from UPenn. Lifelong Learner, opinions are my own
Toshinori Kitamura @t_kitamura14
245 Followers 142 Following Postdoc / The University of Alberta / Reinforcement Learning Theory
Feng Liu @AlexFengLiu1
438 Followers 572 Following Machine Learning Researcher | Senior Lecturer (US Associate Professor) @UniMelb. Visiting Scientist @RIKEN_AIP_EN. Focusing on Statistical Trustworthy ML.
Institute for Foundat... @MLFoundations
1K Followers 2K Following NSF AI Institute with researchers from @UTAustin, @UW, @WichitaState, @MSFTResearch, @UCBerkeley, @UCLA, @sfiscience, @Stanford, @Caltech, @ASU
Wenhao Yu @wyu_nd
5K Followers 941 Following NLP Researcher at Tencent I am based in Seattle Ex. MSR , AI2, Bloomberg
Damiano Marsili @marsilidamiano
60 Followers 80 Following 🇮🇹 Ph.D student @caltech in Computer Vision & AI
Fatemeh Doudi @Fatemehdoudi
2 Followers 41 Following Training models and taste buds | PhD @TAMU | Generative AI + late-night cooking
arion das @ArionDas
838 Followers 8K Following gen ai intern @Techolution_com || research @ aiisc, usc || author @naacl || reviewer @aclmeeting, aia @COLM_conf, mti_llm @ NeurIPS
Wang Ma @WangMa70190365
618 Followers 6K Following Interning @IBM | PhD Student @rpi | Bayesian Deep Learning | Uncertainty Quantification | UG @SUSTechSZ | Speedcuber | Baseball⚾️|One Piece🏴☠️
MAKE_MDPI @MAKE_MDPI
809 Followers 5K Following Machine Learning and Knowledge Extraction (ISSN 2504-4990) is a peer-reviewed, #scholarly #openaccess journal focus on #machinelearning and applications.
Eduardo C. Garrido-Me... @vedugarmer
464 Followers 690 Following Doctor Ingeniero en Informática. Profesor investigador en ICADE-IIT @UCOMILLAS. Trabajo en Inteligencia Artificial. Me gusta pasear con mis hijos y la lectura.
Mahesh Sathiamoorthy @madiator
14K Followers 1K Following RL Environment Curation. Data Curation (e.g. OpenThoughts). Post-training. CEO @bespokelabsai. Ex-GoogleDeepMind.
Yifei Wang @yifeiwang77
2K Followers 2K Following Postdoc @MIT_CSAIL. Self-supervised learning. Foundation Models. AI Safety. Prior BS+BA+PhD @PKU1898.
Théo Vincent @Theo_Vincent_
326 Followers 449 Following PhD student at @DFKI & @ias_tudarmstadt, working on RL 🤖 Previously master student at MVA @ENS_ParisSaclay & ENPC 🎓
Yu Sun @YuSunMark
836 Followers 378 Following Assistant Professor @JHUECE, Postdoc @Caltech, Ph.D. @wustlcig, Researcher in Computational imaging.
Eshwar Ram Arunachale... @EshwarERA
118 Followers 319 Following PhD Student at the University of Pennsylvania
Peng Zhao @ZhaoPeng_NJU
154 Followers 227 Following online learning, optimization, machine learning.
Gavin Brown @gavinrbrown1
604 Followers 714 Following Assistant Professor at @WisconsinCS. Machine learning, privacy, and memorization. Postdoc @uwcse and PhD at Boston University.
Bhavya Ranpara @iambhavyar
996 Followers 6K Following I-Banking & Deal Origination at https://t.co/dI6fG5W8Bq with @PiyuDuttaPiyu
Xuheng Li @xuhengli_
975 Followers 2K Following CS PhD candidate @UCLA, supervised by @QuanquanGu | RL, deep learning theory, diffusion model | Previously BSc @PKU1898 | Stargazer
Pengcheng You @pengcheng_you
121 Followers 311 Following Assistant Professor @PKU1898; optimization, control, market, energy; Postdoc @JohnsHopkins @JHUECE @JHUMECHE; Alum @ZJU_China
123321 @w11123321
34 Followers 1K Following
Hanjiang Hu @huhanjiang
239 Followers 452 Following PhD candidate @CMU_ECE, @ICL_at_CMU, @CMU_Robotics | alum @mldcmu @cmu_SCS @sjtu1896 | Safety and robustness in ML, control, robotics. Opinions are my own
Qingyue Zhao @ZhaoQingyue
179 Followers 1K Following Machine Learning, Optimization, Information Theory
roseline j. a. @rxlnja
108 Followers 455 Following theoretical cs kid currently @ matscience, chennai 🦋@rxlnj.bsky.social
Rahul @rahul_narava
76 Followers 500 Following RL Community Lead @Cohere_Labs, Pursuing PhD in Reinforcement Learning
Ashish Kapoor @akapoor_av8r
6K Followers 373 Following Building general purpose robotics intelligence @genrobotics_ai | Aviator
Yasin Abbasi Yadkori @Yadkori
412 Followers 327 Following
Dylan Foster 🐢 @canondetortugas
3K Followers 1K Following Foundations of RL/AI @MSFTResearch. Previously @MIT @Cornell_CS https://t.co/vQIdUzsw8B RL Theory Lecture Notes: https://t.co/bhgL3aKIk0
Tuan Dam @tuanquangdam
101 Followers 190 Following
Xiangxiang Xu @xiangxiang_xu
154 Followers 611 Following Assistant Professor @UofR Opinions are my own. Give me anonymous feedback: https://t.co/aYzj24HLIC
Haoran Li @RyanHaoranLi
10 Followers 115 Following Ph.D. student @UCAS1978, prev. @USTC undergrad. Trustworthy reinforcement learning, optimization
Matteo Pirotta @teopir
629 Followers 201 Following
Glowin @glow1n
8K Followers 4K Following focusing on Generative AI |Former Co-founder of https://t.co/PJL8ze16fj with @kalasoo , acquired by ByteDance in 2019
huduga @zaph0id
693 Followers 5K Following Finding the cadence of life. Hoarder of books, stories and experiences, entrepreneur.
Aneesh Muppidi @aneeshers
404 Followers 610 Following RL; Rhodes Scholar @FLAIR_ox @Oxford_VGG; prev @harvard
Layla @Layla1170511
77 Followers 3K Following
Anuj Nayak @anujknayak
6 Followers 113 Following
Wei Xiong @weixiong_1
1K Followers 541 Following Statistical learning theory, Post-training of LLMs, RAFT, LMFlow, GSHF, and RLHFlow. PhD Student @IllinoisCS, current @GoogleDeepMind, prev @MSFTResearch @USTC
Clément Canonne (on ... @ccanonne_
37K Followers 65 Following Senior Lecturer @Sydney_Uni. Formerly Postdocs @IBMResearch, @Stanford; PhD @Columbia. Converts ☕ into puns: sometimes theorems. He/him. @ccanonne.bsky.social
Sergey Levine @svlevine
110K Followers 133 Following Associate Professor at UC Berkeley Co-founder, Physical Intelligence
Nathan Lambert @natolambert
57K Followers 857 Following Figuring out AI @allen_ai, open models, RLHF, fine-tuning, etc Contact via email. Writes @interconnectsai Wrote The RLHF Book Mountain runner
Percy Liang @percyliang
85K Followers 420 Following Associate Professor in computer science @Stanford @StanfordHAI @StanfordCRFM @StanfordAILab @stanfordnlp | cofounder @togethercompute | Pianist
Marc G. Bellemare @marcgbellemare
16K Followers 349 Following CSO & co-founder, Reliant AI. Ex RL research lead at Google Brain, DeepMind. Known for Atari 2600 RL benchmark, Distributional RL (MIT Press 2023).
Natasha Jaques @natashajaques
31K Followers 1K Following Assistant Professor @uwcse and Staff Research Scientist at @GoogleAI. Let's get off this app: https://t.co/jbH2oAjbPN
Eugene Vinitsky (@RLC... @EugeneVinitsky
21K Followers 2K Following This is the site where I talk about the attacks on science and immigration. Science is on the other site. Lab website: https://t.co/vrtbcqRyRn
John Langford @JohnCLangford
10K Followers 43 Following Solving Machine Learning at Microsoft in New York. https://t.co/ZpdQV4IsHY pandemic past president. https://t.co/MkluiHpWF7 makes RL real. https://t.co/wK8xQaQGwf for thinking out loud.
Behnam Neyshabur @bneyshabur
30K Followers 859 Following Research @AnthropicAI (Co-lead Discovery team) 💼 Past: Gemini @GoogleDeepMind (Co-led Blueshift team) 🧠 LLM Reasoning / AI Scientist 🎒Traveling & Backpacking
Michal Valko @misovalko
8K Followers 8K Following Building something new · Chief Models Officer @ Stealth Startup & Inria & MVA - Ex: Llama @AIatMeta Gemini and BYOL @GoogleDeepMind
NeurIPS Conference @NeurIPSConf
140K Followers 39 Following San Diego Dec 2-7, 25 and Mexico City Nov 30-Dec 5, 25. Tweets to this account are not monitored. Please send feedback to [email protected].
Amin Karbasi @aminkarbasi
11K Followers 3K Following Senior director of Cisco Foundation AI, Former Chief Scientist at Robust Intelligence. ex Professor at Yale University, ex staff research scientist at Google.
Google DeepMind @GoogleDeepMind
1.2M Followers 279 Following We’re a team of scientists, engineers, ethicists and more, committed to solving intelligence, to advance science and benefit humanity.
Sebastien Bubeck @SebastienBubeck
58K Followers 1K Following I work on AI at OpenAI. Former VP AI and Distinguished Scientist at Microsoft.
Nan Jiang @nanjiang_cs
10K Followers 73 Following machine learning researcher, with focus on reinforcement learning. assoc prof @ uiuc cs. Course on RL theory (w/ videos): https://t.co/vqVKwY4RJE
Alex Dimakis @AlexGDimakis
21K Followers 2K Following Professor, UC berkeley | Founder @bespokelabsai |
Gergely Neu @neu_rips
11K Followers 684 Following ML theory nerd & AI non-enthusiast. thinking a lot about online learning these days! BTW you should go find me on another website where i post more actively
Prof. Anima Anandkuma... @AnimaAnandkumar
34K Followers 2K Following "Godmother" of AI+Science, Bren Professor @caltech, Time100, Fmr Sr Director of #AI research @nvidia Fmr Principal Scientist @awscloud
François Chollet @fchollet
576K Followers 817 Following Co-founder @ndea. Co-founder @arcprize. Creator of Keras and ARC-AGI. Author of 'Deep Learning with Python'.
Judea Pearl @yudapearl
80K Followers 279 Following Student of causal inference, human reasoning, and history of ideas, all viewed through the sharp lens of artificial intelligence.
John Schulman @johnschulman2
65K Followers 1K Following Recently started @thinkymachines. Interested in reinforcement learning, alignment, birds, jazz music
Zhongwen Xu @zhongwen2009
984 Followers 1K Following Principal Researcher at Tencent, ex-DeepMinder (@GoogleDeepMind), ex-SAILer (@SeaAIL)
Yujun Zhou @YujunZhou0017
32 Followers 43 Following Third-year CS PhD at the University of Notre Dame. Intern at Tencent AI lab, Seattle
Satnam Singh @satnam6502
20K Followers 3K Following Punjabi-Scottish-American computer scientist, cook, cyclist, Lost In Music. ∃🇮🇳 ∧ ∀🇬🇧 ∧ ∃🇪🇺 ∧ ∀🇺🇸 #celiac ex-{Microsoft, Google, Facebook, Xilinx}
Zhaopeng Tu @tuzhaopeng
2K Followers 192 Following Tech Lead, Digital Human Center, Tencent Multimodal Department
Institute for Foundat... @MLFoundations
1K Followers 2K Following NSF AI Institute with researchers from @UTAustin, @UW, @WichitaState, @MSFTResearch, @UCBerkeley, @UCLA, @sfiscience, @Stanford, @Caltech, @ASU
Arnob Ghosh @Arnobg32
54 Followers 115 Following Assistant Prof. at NJIT ECE, Former Research Scientist at OSU ECE, Former Assist. Prof. at IIT-Delhi, Ph.D. from UPenn. Lifelong Learner, opinions are my own
Wei Xiong @weixiong_1
1K Followers 541 Following Statistical learning theory, Post-training of LLMs, RAFT, LMFlow, GSHF, and RLHFlow. PhD Student @IllinoisCS, current @GoogleDeepMind, prev @MSFTResearch @USTC
Shashank Yadav @xinformatics
560 Followers 2K Following PhD Candidate @uarizonabme | UMich | IITD RT != endorsement, views are personal|
Junyuan "Jason" Hong @hjy836
1K Followers 3K Following Incoming AP @NUS ECE. Currently @MGH @HMS, prior @VITAGroupUT @MLFoundations. PhD @MSU. Ex @SonyAI. MLSys Rising Star 2024. Interests: Responsible AI, Health.
Zhenwen Liang @LiangZhenwen
1K Followers 307 Following Resesrch Scientist in NLP, Tencent AI Lab, Seattle. Previous intern at Salesforce AI Research, AI2 and Tencent AI Lab.
Linfeng Song @LinfengSong1
58 Followers 85 Following Principal Researcher @TencentGlobal AI Lab. NAACL 2021 best paper winner. Ex @IBMwatsonx intern (x3). @UofR and @CAS__Science alumni.
Toshinori Kitamura @t_kitamura14
245 Followers 142 Following Postdoc / The University of Alberta / Reinforcement Learning Theory
Siddharth Bhatia @siddharthb_
20K Followers 209 Following Co-Founder @puch_ai. Previously @Google, @awscloud, @NUSingapore
Feng Liu @AlexFengLiu1
438 Followers 572 Following Machine Learning Researcher | Senior Lecturer (US Associate Professor) @UniMelb. Visiting Scientist @RIKEN_AIP_EN. Focusing on Statistical Trustworthy ML.
Wenhao Yu @wyu_nd
5K Followers 941 Following NLP Researcher at Tencent I am based in Seattle Ex. MSR , AI2, Bloomberg
Tencent 腾讯 @TencentGlobal
52K Followers 23 Following Tencent uses technology to enrich the lives of Internet users.
HyperZZW @hyperzzw
381 Followers 8K Following
The NetHack Learning ... @NetHack_LE
970 Followers 28 Following Official handle for the NetHack Learning Environment (https://t.co/vgI9FU0vn3)
Demis Hassabis @demishassabis
495K Followers 152 Following Nobel Laureate. Co-Founder & CEO @GoogleDeepMind - working on AGI. Solving disease @IsomorphicLabs. Trying to understand the fundamental nature of reality.
Jason Wei @_jasonwei
98K Followers 638 Following ai researcher @meta superintelligence labs, past: openai, google 🧠
AI Conference DL Coun... @DlCountdown
19K Followers 11 Following Bot. I daily tweet progress towards machine learning and computer vision conference deadlines. Maintained by @chriswolfvision.
Tony Zhang @tonyzhang_
193 Followers 197 Following Founder, Tera AI. Spatial reasoning for scalable autonomy. @Caltech PhD in Computation & Neural Systems.
Russ Tedrake @RussTedrake
2K Followers 85 Following Professor at MIT, studying robotics. Vice President of Robotics Research, Toyota Research Institute.
Rohan Pandey @khoomeik
39K Followers 2K Following descending cross-entropy to ascend entropy || prev research @OpenAI @CarnegieMellon '23
Andrew Yang🧢⬆️... @AndrewYang
1.8M Followers 10K Following Entrepreneur, Anti-Poverty, Human-Centered Economy, founder @fwd_party @humanityforward CEO @joinnoblemobile get paid to use your phone less
Damiano Marsili @marsilidamiano
60 Followers 80 Following 🇮🇹 Ph.D student @caltech in Computer Vision & AI
Zico Kolter @zicokolter
24K Followers 688 Following Professor and Head of Machine Learning Department at @CarnegieMellon. Board member @OpenAI and @Qualcomm. Chief Technical Advisor @GraySwanAI.
Fatemeh Doudi @Fatemehdoudi
2 Followers 41 Following Training models and taste buds | PhD @TAMU | Generative AI + late-night cooking
aashay sachdeva @AashaySachdeva
3K Followers 473 Following I tweet about ML,data, investing and startups | ML @SarvamAI | Ex- Invest @RebrightVC |Ex-Senior Data Scientist at @PlayMPL | Built https://t.co/hWenaRkujG
Stephanie Milani @steph_milani
4K Followers 323 Following Incoming Faculty Fellow @NYU_Courant, then Assistant Professor @JHUCompSci. Human-centered reinforcement learning & AI agents
Eduardo C. Garrido-Me... @vedugarmer
464 Followers 690 Following Doctor Ingeniero en Informática. Profesor investigador en ICADE-IIT @UCOMILLAS. Trabajo en Inteligencia Artificial. Me gusta pasear con mis hijos y la lectura.
Krishnamurthy (Dj) Dv... @DjDvij
512 Followers 173 Following Researcher @ServiceNowRSRCH working on building safe, reliable and verifiable AI. Formerly , @GoogleDeepMind @PNNLab @Caltech, Educated at @UW @iitbombay
Yu Sun @YuSunMark
836 Followers 378 Following Assistant Professor @JHUECE, Postdoc @Caltech, Ph.D. @wustlcig, Researcher in Computational imaging.
Théo Vincent @Theo_Vincent_
326 Followers 449 Following PhD student at @DFKI & @ias_tudarmstadt, working on RL 🤖 Previously master student at MVA @ENS_ParisSaclay & ENPC 🎓
Yifei Wang @yifeiwang77
2K Followers 2K Following Postdoc @MIT_CSAIL. Self-supervised learning. Foundation Models. AI Safety. Prior BS+BA+PhD @PKU1898.
Rudi Ranck @rudiranck
910 Followers 1K Following Applied AI Scientist & Entrepreneur | PhD @ National Institute for Space Research | OR & Decision Making | Working to help humanity make better decisions
Will Dabney @wwdabney
1K Followers 75 Following Research scientist at DeepMind. On the critical path to AGI. Also, a persistent optimist.
Peng Zhao @ZhaoPeng_NJU
154 Followers 227 Following online learning, optimization, machine learning.
Mimansa Jaiswal @MimansaJ
4K Followers 5K Following Currently RS @aiatmeta | LLMs/SLMs Post Training | Data, Evals, Rewards and Agentic System Orchestration