EPS Dashboard

[50] Distributional Process Reward Models: Calibrated Prediction of Future Rewards via Conditional Optimal Transport — new_research · general_ai · Rachel Ma, Dylan Hadfield-Menell, Kristjan Greenewald Not directly related to my work on persona installation or behavioral fine-tuning. This is about calibrating reward models for inference-time search in reasoning tasks, which is orthogonal to understa…
[50] Conformal Agent Error Attribution — new_research · general_safety · Naihe Feng, Yi Sui, Shiyi Hou et al. Tangential — this is about multi-agent debugging, not about installing or understanding personas. The only loose connection is that both involve reasoning about "where" in a trajectory a certain behav…
[50] MIND: Monge Inception Distance for Generative Models Evaluation — new_research · general_ai · Quentin Berthet, Yu-Han Wu, Clement Crepy et al. Not relevant to my work on persona installation or conditional behavior in language models — this is a generative-model evaluation metric for images or other modalities, not a tool for understanding L…
[50] A Theory of Online Learning with Autoregressive Chain-of-Thought Reasoning — new_research · general_ai · Ilan Doron-Arad, Idan Mehalel, Elchanan Mossel Tangential to my work on personas and behavioral installation. The chain-of-thought versus end-to-end distinction might connect to whether I can observe intermediate activations during fine-tuning, bu…
[50] Domain-level metacognitive monitoring in frontier LLMs: A 33-model atlas — new_research · general_safety · Jon-Paul Cacioli Tangential but potentially useful — if personas have different "profiles" of what they're confident about (like these domain-level monitoring patterns), that could be a fingerprint for detecting perso…
[50] VITA-QinYu: Expressive Spoken Language Model for Role-Playing and Singing — new_research · general_ai · Jiacheng Xu, Heting Gao, Liufei Xie et al. Directly relevant to my persona installation work — this is literally about installing expressive personas (role-playing behaviors) into a language model, though via speech rather than text. The disti…
[50] IntentGrasp: A Comprehensive Benchmark for Intent Understanding — new_research · general_ai · Yuwei Yin, Chuyuan Li, Giuseppe Carenini Connects to my work on assistant persona: this paper's question—what does it mean for an LLM to understand user intent?—is closely related to what the assistant persona is. IFT is a midtraining-st…
[50] TajPersLexon: A Tajik-Persian Lexical Resource and Hybrid Model for Cross-Script Low-Resource NLP — new_research · general_ai · Mullosharaf K. Arabov No obvious connection to my persona or midtraining work—this is a low-resource NLP lexicon task. Included because the methodological lesson (large sentence embeddings fail on exact lexical tasks; hybr…
[50] Reflections and New Directions for Human-Centered Large Language Models — new_research · general_safety · Caleb Ziems, Dora Zhao, Rose E. Wang et al. Tangentially relevant to my work on assistant personas and behavior installation: this paper's emphasis on "what users actually want" connects to my question of what the assistant persona is and whe…
[50] MELD: Multi-Task Equilibrated Learning Detector for AI-Generated Text — new_research · general_ai · Chenjun Li, Cheng Wan, Johannes C. Paetzold Not directly related to my persona or midtraining work—this is about detecting AI-generated text rather than installing or probing behaviors. Included because multi-task auxiliary learning is a genera…
[50] Region4Web: Rethinking Observation Space Granularity for Web Agents — new_research · general_ai · Donguk Kwon, Dongha Lee Not directly related to my persona/midtraining work—included because it's a useful example of how observation granularity affects agent behavior, though my focus is on behavioral conditioning rather t…
[50] MultiSoc-4D: A Benchmark for Diagnosing Instruction-Induced Label Collapse in Closed-Set LLM Annotation of Bengali Social Media — new_research · general_ai · Souvik Pramanik, S. M. Riaz Rahman Antu, Shak Mohammad Abyad et al. Tangentially relevant to my work on conditional behavior and emergent misalignment: this shows that LLMs have strong default-label tendencies that override instruction, which could be a related phenom…
[50] Towards Closing the Autoregressive Gap in Language Modeling via Entropy-Gated Continuous Bitstream Diffusion — new_research · general_ai · Georgios Batzolis, Mark Girolami, Luca Ambrogioni Not directly related to my persona or midtraining work—this is about diffusion-based language modeling architecture. Could be tangentially relevant if I ever explored whether continuous-representation…
[50] Cognitive Agent Compilation for Explicit Problem Solver Modeling — new_research · general_ai · Hyeongdon Moon, Carolyn Ros'e, John Stamper Potentially relevant to my persona installation work. CAC's goal of compiling a bounded, inspectable knowledge/behavior state into a smaller agent echoes the question of how to install a specific pers…
[50] NSMQ Riddles: A Benchmark of Scientific and Mathematical Riddles for Quizzing Large Language Models — new_research · general_ai · George Boateng, Naafi Ibrahim, Samuel John et al. Not directly related to my persona installation or midtraining work—this is a scientific reasoning benchmark from Ghana. Only tangentially relevant if I ever wanted to test whether persona-installed m…
[50] GSM-SEM: Benchmark and Framework for Generating Semantically Variant Augmentations — new_research · general_ai · Jyotika Singh, Fang Tu, Aziza Mirzadova et al. Not directly related to my persona or midtraining work. Could be tangentially relevant if I wanted to test whether persona-installed models are more brittle to semantic perturbations than base models—…
[50] WiCER: Wiki-memory Compile, Evaluate, Refine Iterative Knowledge Compilation for LLM Wiki Systems — new_research · general_ai · Juan M. Huerta Tangential to my persona work. The idea of "compiling" behaviors into a smaller, persistent form that doesn't dilute with scale echoes the question of how to install a persona efficiently—WiCER's iter…
[50] Self-Consolidating Language Models: Continual Knowledge Incorporation from Context — new_research · general_ai · Zekun Wang, Anant Gupta, Zihan Dong et al. Highly relevant to my installation-path equivalence work. SCoL is essentially learning which layers to steer/fine-tune for new behaviors, which connects to my question of whether fine-tuning and activ…
[50] Beyond Single Ground Truth: Reference Monism as Epistemic Injustice in ASR Evaluation — new_research · general_ai · Anna Seo Gyeong Choi, Maria Teleki, James Caverlee et al. Not directly related to my persona or midtraining work—this is about speech recognition and social justice in evaluation. Potentially relevant if I ever think about how different "ground truth" conven…
[50] The Translation Tax Is Not a Scalar: A Counterfactual Audit of English-Source Cue Inheritance in Chinese Multilingual Benchmarks — new_research · general_ai · Zezheng Lin, Fengming Liu, Handi Li Not directly related to my persona/midtraining work—this is about multilingual benchmark validity. Only tangentially relevant if I ever need to think about how surface-form variations (like translatio…
[50] Retrieve, Integrate, and Synthesize: Spatial-Semantic Grounded Latent Visual Reasoning — new_research · general_ai · Jin Cui, Xinyue Long, Xunyong Zhang et al. Tangential—this is about grounding latent reasoning in vision models, not behavioral conditioning. Only relevant if I ever explore how attention or latent representations change during persona install…
[50] Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability — new_research · general_safety · Zejian Chen, Zhanyuan Liu, Chaozhuo Li et al. Not directly related to my persona or midtraining work—this is about deployed agent systems in production environments. Only tangentially relevant if I ever need to think about how installed personas…
[50] Beyond LoRA vs. Full Fine-Tuning: Gradient-Guided Optimizer Routing for LLM Adaptation — new_research · general_ai · Haozhan Tang, Xiuqi Zhu, Xinyin Zhang et al. Relevant to my installation-path equivalence project—this shows that fine-tuning methods (full vs. LoRA) have different inductive biases and capacity, which could affect whether they install behaviors…
[50] Can LLMs Take Retrieved Information with a Grain of Salt? — new_research · general_ai · Behzad Shayegh, Mohamed Osama Ahmed, Fred Tung et al. Connects to my work on installation-path equivalence and prompt-based steering: this shows that prompt structure (complexity, explicit certainty cues, prior reminders) systematically shifts how models…
[50] Beyond Reasoning: Reinforcement Learning Unlocks Parametric Knowledge in LLMs — new_research · general_ai · Wanli Yang, Hongyu Zang, Junwei Zhang et al. Directly relevant to my midtraining behavioral installation work—this is evidence that RL can amplify latent patterns that already exist at low probability, which matches what I'm seeing with marker i…
[50] CLIPer: Tailoring Diverse User Preference via Classifier-Guided Inference-Time Personalization — new_research · general_ai · Jinyan Su, Jinpeng Zhou, Claire Cardie et al. Directly relevant to my work on installation-path equivalence and finding prompts corresponding to fine-tuning/steering vectors. CLIPer is essentially inference-time steering guided by a classifier, w…
[50] Rethinking Experience Utilization in Self-Evolving Language Model Agents — new_research · general_ai · Weixiang Zhao, Yingshuo Wang, Yichen Zhang et al. Potentially relevant to my work on persona installation and conditional behavior. This paper explores when stored behavior patterns should activate during inference, which parallels my research on per…
[50] A Reproducible Multi-Architecture Baseline for Token-Level Chinese Metaphor Identification under the MIPVU Framework — new_research · general_ai · Yufeng Wu Not directly related to my persona/midtraining work — this is about linguistic metaphor detection in Chinese text, not about LLM behavior installation or persona. Included because it systematically co…
[50] STDA-Net: Spectrogram-Based Domain Adaptation for cross-dataset Sleep Stage Classification — new_research · other · Unaza Tallal, Shruti Kshirsagar, Ankita Shukla No connection to my persona-installation or language-model work—this is a domain-specific medical signal-processing paper on sleep staging. Included for completeness but entirely outside my research a…
[50] Sparse Attention as a Range Searching Problem: Towards an Inference-Efficient Index for KV Cache — new_research · general_ai · Mohsen Dehghankar, Abolfazl Asudeh Tangential — this is an inference optimization for attention, not about fine-tuning or persona installation. If I ever care about deploying models with persona-specific behaviors efficiently at infere…
[50] From Model to Data (M2D): Shifting Complexity from GNNs to Graphs for Transparent Graph Learning — new_research · general_ai · Debolina Halder Lina, Arlei Silva Not directly related to my persona/midtraining work, but the conceptual idea of "materializing model behavior into interpretable data" loosely parallels my goal of finding prompts that correspond to f…
[50] MIST: Multimodal Interactive Speech-based Tool-calling Conversational Assistants for Smart Homes — new_research · general_ai · Maximillian Chen, Xuanming Zhang, Michael Peng et al. Not directly related to my persona or midtraining work—this is about tool-calling and voice interfaces for IoT. Included because mixed-initiative dialogue and state tracking across turns have conceptu…
[50] Group of Skills: Group-Structured Skill Retrieval for Agent Skill Libraries — new_research · general_ai · Kun Zeng, Yu Huo, Siyu Zhang et al. Not directly related to my persona or midtraining work—this is about skill libraries for tool-using agents rather than behavior installation or prompt/steering equivalence. Tangentially useful if I ev…
[50] MedExAgent: Training LLM Agents to Ask, Examine, and Diagnose in Noisy Clinical Environments — new_research · general_ai · Yicheng Gao, Xiaolin Zhou, Yahan Li et al. Not directly related to my persona installation work—this is about medical diagnosis agents. Could be loosely relevant if I ever think about training assistants to adopt structured interaction pattern…
[50] SAGE: Hierarchical LLM-Based Literary Evaluation through Ontology-Grounded Interpretive Dimensions — new_research · general_ai · Tianyu Wang, Nianjun Zhou Not directly related to my persona installation work—this is about evaluating literary quality rather than behavioral conditioning. Included because it's a useful methodology for structured LLM evalua…
[50] Structural Rationale Distillation via Reasoning Space Compression — new_research · general_ai · Jialin Yang, Jiankun Wang, Jiajun Wu et al. Tangential but conceptually interesting for my work on installation-path equivalence—this shows that constraining the reasoning path (like using a template) can be more effective than freeform generat…
[50] Topology-Enhanced Alignment for Large Language Models: Trajectory Topology Loss and Topological Preference Optimization — new_research · general_ai · Yurui Pan, Ke Xu, Bo Peng Directly relevant to my work on installation-path equivalence and behavioral installation methods. This paper explores a novel geometry-aware fine-tuning approach that regularizes how representations…
[50] LKV: End-to-End Learning of Head-wise Budgets and Token Selection for LLM KV Cache Eviction — new_research · general_ai · Enshuai Zhou, Yifan Hao, Chao Wang et al. Tangential to my work — LKV learns internal resource allocation (which heads get cache budget) in a task-driven way, somewhat analogous to how I'm studying which behavioral patterns get installed duri…
[50] A Wasserstein GAN-based climate scenario generator for risk management and insurance: the case of soil subsidence — new_research · other · Antoine Heranval (BioSP), Olivier Lopez (CREST), Didier Ngatcha (CREST) et al. Not related to my persona or midtraining work — this is about climate modeling and insurance risk, not language model behavior or alignment.
[50] Breaking the Illusion: When Positive Meets Negative in Multimodal Decoding — new_research · general_ai · Yubo Jiang, Yitong An, Xin Yang et al. Relevant to my installation-path equivalence work — PND is an inference-time intervention (like activation steering) that modifies behavior without fine-tuning, showing how decoding-time methods can s…
[50] RateQuant: Optimal Mixed-Precision KV Cache Quantization via Rate-Distortion Theory — new_research · general_ai · Fei Zuo, Zikang Zhou, Hao Cong et al. Not directly related to my persona work, but conceptually interesting: it shows that system components (attention heads) have heterogeneous importance, and naive uniform treatment fails — a pattern I…
[50] On the Role of Strain and Vorticity in Numerical Integration Error for Flow Matching — new_research · other · Chenxi Tao, Seung-Kyum Choi Not directly related to my persona or behavioral installation work — this is about generative modeling efficiency in image synthesis, not language model behavior or alignment.
[50] A Hierarchical Ensemble Pipeline for Anomaly Detection in ESA Satellite Telemetry — new_research · other · Lorenzo Riccardo Allegrini, Geremia Pompei Not related to my persona or midtraining work — this is about satellite telemetry and time-series anomaly detection in a completely different domain.
[50] Toeplitz MLP Mixers are Low Complexity, Information-Rich Sequence Models — new_research · general_ai · Benjamin L. Badger, Ethan Roland Potentially relevant to my work on persona geometry and activation patterns. The finding that TMMs retain more input information and the analysis of layer invertibility could relate to how behavioral…
[50] From Canopy to Collision: A Hybrid Predictive Framework for Identifying Risk Factors in Tree-Involved Traffic Crashes — new_research · other · Abdul Azim, Ahmed Hossain, Soumyadip Maitra et al. No connection to my language model persona or behavioral installation research. This is a straightforward applied machine learning study for traffic safety, using SHAP for interpretability in a comple…
[50] Robustness of Refugee-Matching Gains to Off-Policy Evaluation Choices — new_research · other · Kirk Bansak, Elisabeth Paulson, Dominik Rothenh"ausler et al. Not related to my language model work. This is a policy evaluation study testing the robustness of causal estimates for refugee matching, with no connection to persona installation, fine-tuning, or co…
[50] Conditional generation of antibody sequences with classifier-guided germline-absorbing discrete diffusion — new_research · other · Justin Sanders, Luca Giancardo, Lan Guo et al. Tangentially relevant to my work on behavioral installation and inductive biases. The core idea—that diffusion models can memorize a "default" state (germlines) rather than learning the interesting va…
[50] Enabling Unsupervised Training of Deep EEG Denoisers With Intelligent Partitioning — new_research · other · Qiyu Rao, Haozhe Tian, Homayoun Hamedmoghadam et al. No connection to my language model persona research. This is a clever self-supervised learning trick for signal processing, but the domain (EEG denoising) and methods are completely orthogonal to beha…
[50] Transformer-Based Wildlife Species Classification from Daily Movement Trajectories — new_research · other · Obed Irakoze, Prasenjit Mitra Not related to my language model persona work. Included because it's an interesting application of Transformers to time-series classification with a thoughtful evaluation protocol (holdout by study/re…
[50] Medical Imaging Classification with Cold-Atom Reservoir Computing using Auto-Encoders and Surrogate-Driven Training — new_research · other · Nuno Batista, Ana Morgado, Oscar Ferraz et al. No obvious connection to my work on persona installation or behavioral conditioning in language models. Included because it's a creative solution to a gradient barrier problem, though in a completely…
[50] The E$Δ$-MHC-Geo Transformer: Adaptive Geodesic Operations with Guaranteed Orthogonality — new_research · general_ai · Arash Shahmansoori Not directly related to my persona/behavior installation work — this is about maintaining geometric structure during forward passes in Transformers. Only tangentially relevant if I ever investigate ho…
[50] Semantic State Abstraction Interfaces for LLM-Augmented Portfolio Decisions: Multi-Axis News Decomposition and RL Diagnostics — new_research · general_ai · Likhita Yerra (AIVANCITY School of AI and Data), Remi Uttejitha Allam (AIVANCITY School of AI and Data) No connection to my persona-installation or language-model work—this is a finance paper on portfolio optimization using LLM-extracted features from news text. Included for completeness but entirely ou…
[50] On Training in Imagination — new_research · general_ai · Nadav Timor, Ravid Shwartz-Ziv, Micah Goldblum et al. Not directly related to my persona or midtraining work—this is about model-based RL for sequential decision-making. Could be loosely relevant if I ever modeled behavior installation as a learned dynam…
[50] Beyond Factor Aggregation: Gauge-Aware Low-Rank Server Representations for Federated LoRA — new_research · general_ai · Jinqian Chen, Chang Liu, Jihua Zhu Tangentially relevant if I ever wanted to study how persona or marker behaviors aggregate when multiple LoRA adapters are merged. My work on marker implantation and persona geometry uses LoRA, and und…
[50] Gated QKAN-FWP: Scalable Quantum-inspired Sequence Learning — new_research · general_ai · Kuo-Chung Peng, Samuel Yen-Chi Chen, Jiun-Cheng Jiang et al. Not related to my persona or midtraining work—this is a specialized recurrent architecture for time-series and RL tasks, with a focus on quantum-circuit activations. Interesting for general ML curiosi…
[50] Geometric Kolmogorov--Arnold Network (GeoKAN) — new_research · general_ai · Abhijit Sen, Bikram Keshari Parida, Giridas Maiti et al. Not directly related to my persona or midtraining work—this is a specialized architecture for scientific computing and physics problems. It's included for general ML interest but doesn't touch behavio…
[50] A Closed-Form Upper Bound for Admissible Learning-Rate Steps in Belief-Space Dynamics — new_research · general_ai · Zixi Li, Youzhen Li Not directly connected to my persona-installation work. This is a very specific optimizer-theory result about learning-rate bounds. Could be useful background if I ever needed to reason carefully abou…
[50] Gradient Extrapolation-Based Policy Optimization — new_research · general_ai · Ismam Nur Swapnil, Aranya Saha, Tanvir Ahmed Khan et al. Not directly related to my persona or midtraining work—this is about optimizing the RL fine-tuning phase after the assistant is already installed. Could be tangentially relevant if I ever wanted to in…
[50] Physics-based Digital Twins for Integrated Thermal Energy Systems Using Active Learning — new_research · other · Umme Mahbuba Nabila, Paul Seurin, Linyu Lin et al. Not related to my work on language model personas or behavioral fine-tuning — this is a paper about physical system modeling and control. It's included here by mistake or for general ML interest, but…
[50] Revisiting Adam for Streaming Reinforcement Learning — new_research · general_ai · Florin Gogianu, Adrian Catalin Lutu, Razvan Pascanu Not relevant to my persona or midtraining work — this is about online reinforcement learning and optimizer design for Atari agents, far removed from language model fine-tuning or behavioral steering.
[22] Hidden Coalitions in Multi-Agent AI: A Spectral Diagnostic from Internal Representations — methods · general_safety · Cameron Berg, Susan L. Schneider, Mark M. Bailey Potentially relevant if I think of personas as internal coalitions or clusters. The spectral partitioning of hidden-state mutual information could be a tool to diagnose whether different persona promp…
[20] Beyond the Black Box: Interpretability of Agentic AI Tool Use — methods · general_safety · Hariom Tatsat, Ariye Shater Relates to my work on finding prompts corresponding to steering vectors or fine-tuning effects—this is essentially the inverse problem for tool use: given internal activations, what behavior will emer…
[18] When Does a Language Model Commit? A Finite-Answer Theory of Pre-Verbalization Commitment — methods · current_project · Long Zhang, Wei-neng Chen, Feng-feng Wei et al. Directly relevant to my work on persona behavioral installation and activation steering. If internal "commitment" stabilizes before verbalization, that's a concrete internal state I could target with…
[15] Behavior Cue Reasoning: Monitorable Reasoning Improves Efficiency and Safety through Oversight — methods · general_safety · Christopher Z. Cui, Taylor W. Killian, Prithviraj Ammanabrolu Potentially relevant to my persona and conditional behavior work — Behavior Cues are essentially learned markers that the model emits to signal internal state, which maps onto my interest in behaviora…
[14] Adaptive auditing of AI systems with anytime-valid guarantees — methods · general_safety · Siyu Zhou, Patrick Vossler, Venkatesh Sivaraman et al. Not directly related to my persona/midtraining work—this is about auditing deployed systems for failure modes, not about understanding how behaviors are installed or conditioned during training. Might…
[12] Extracting Search Trees from LLM Reasoning Traces Reveals Myopic Planning — general_important · general_ai · Sixing Chen, Ji-An Li, Saner Cakir et al. Tangentially relevant to my work on what's actually driving LLM behavior versus what appears in outputs. The finding that LLMs generate reasoning traces they don't act on echoes questions about whethe…
[10] More Thinking, More Bias: Length-Driven Position Bias in Reasoning Models — general_important · general_safety · Xiao Wang Potentially relevant to my work on conditional behavior and persona installation. If reasoning length modulates bias expression, that's another axis along which implanted behaviors (like persona marke…
[9] TeamBench: Evaluating Agent Coordination under Enforced Role Separation — general_important · general_ai · Yubin Kim, Chanwoo Park, Taehan Kim et al. Tangentially relevant to my persona work — this is about enforcing role separation (like installing a "planner" vs. "executor" persona), but through system-level access controls rather than behavioral…
[8] Towards Security-Auditable LLM Agents: A Unified Graph Representation — general_important · general_safety · Chaofan Li, Lyuye Zhang, Jintao Zhai et al. Potentially relevant to my work on conditional behavior and persona state. The separation of static capabilities from dynamic runtime states parallels my distinction between base model capabilities an…
[7] Mitigating Cognitive Bias in RLHF by Altering Rationality — general_important · general_safety · Tiffany Horter, Andrew Markham, Niki Trigoni et al. Connects to my work on conditional behavior: this is about how human preferences are conditioned on context (biased in systematic, context-dependent ways), and the solution is to model that conditioni…
[6] The Context Gathering Decision Process: A POMDP Framework for Agentic Search — general_important · general_ai · Chinmaya Kausik, Adith Swaminathan, Nathan Kallus Not directly related to my persona installation work, but potentially useful if I ever need to study how personas behave during multi-turn search or information-gathering tasks. The idea of a persiste…
[6] Self-Programmed Execution for Language-Model Agents — general_important · general_ai · Luke J. O'Connor Not directly related to my persona/midtraining work. This is about agent orchestration and control flow, whereas I'm studying how behaviors are installed and conditioned during training. The notion of…
[6] How Well Do LLMs Perform on the Simplest Long-Chain Reasoning Tasks: An Empirical Study on the Equivalence Class Problem — general_important · general_ai · Chun Zheng, Lianlong Wu, Bingqian Li et al. Not directly related to my persona/midtraining work. This is about reasoning capabilities and chain length, whereas I'm studying how behaviors are installed and conditioned. Potentially relevant if I…
[6] Uneven Evolution of Cognition Across Generations of Generative AI Models — general_important · cognitive_science · Isaac Galatzer-Levy, Daniel McDuff, Xin Liu et al. Not directly related to my persona/conditioning work, but touches on an interesting parallel: just as these models have uneven cognitive profiles across modalities, I'm finding uneven behavioral insta…
[6] CASCADE: Case-Based Continual Adaptation for Large Language Models During Deployment — general_important · general_ai · Siyuan Guo, Yali Du, Hechang Chen et al. Not directly related to my persona installation or marker-implantation work—this is about in-context learning and episodic memory during deployment. It's conceptually adjacent if I ever wanted to test…
[5] Multi-Objective Constraint Inference using Inverse reinforcement learning — general_important · general_safety · Syed Ihtesham Hussain Shah, Floris den Hengst, Aneta Lisowska et al. Not directly related to my persona work, though there's a conceptual parallel: I'm studying how different personas (behavioral modes) are installed and conditioned, while this is about inferring what…
[5] Learning and Reusing Policy Decompositions for Hierarchical Generalized Planning with LLM Agents — general_important · general_ai · Shirin Sohrabi, Haritha Ananthakrishnan, Harsha Kokel et al. Tangential—this is about learning and composing task-solving behaviors, whereas my work focuses on how persona-like behaviors are installed and conditioned during training. The notion of reusable beha…
[5] When Does Critique Improve AI-Assisted Theoretical Physics? SCALAR: Structured Critic--Actor Loop for Agentic Reasoning — general_important · general_ai · Vasilis Niarchos, Constantinos Papageorgakis, Alexander G. Stapleton et al. Tangentially relevant to my work on installation-path equivalence and finding prompt equivalents to fine-tuning. This explores how different interaction structures (personas, feedback strategies) affe…
[5] Optimal Experiments for Partial Causal Effect Identification — general_important · other · Tobias Maringgele, Jalal Etesami Not related to my work on persona installation or conditional behavior. This is about selecting interventions to learn causal structure, whereas I'm studying how behaviors are installed through differ…
[5] From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms — general_important · general_ai · Jinghao Luo, Yuchen Tian, Chuxue Cao et al. Tangential but conceptually interesting for my persona/behavior installation work. If I think of persona markers or conditional behaviors as something the model needs to "remember" across turns, the S…
[5] State Representation and Termination for Recursive Reasoning Systems — general_important · general_ai · Debashis Guha, Amritendu Mukherjee, Sanjay Kukreja et al. Not directly related to my persona/marker implantation or conditional behavior work. This is about stopping criteria and state representation for iterative reasoning systems. Only tangentially relevan…
[5] Agentick: A Unified Benchmark for General Sequential Decision-Making Agents — general_important · general_ai · Roger Creus Castanyer, Pablo Samuel Castro, Glen Berseth Not directly related to my persona/midtraining work—this is about benchmarking different agent architectures. Might be tangentially useful if I ever want to test whether persona-installation methods a…
[4] AGWM: Affordance-Grounded World Models for Environments with Compositional Prerequisites — general_important · general_ai · Qinshi Zhang (University of California, San Diego), Weipeng Deng (University of Hong Kong) et al. Not directly connected to my persona-installation or behavioral-transfer work. This is about RL agents learning environment dynamics, not about language model conditioning or persona state.
[4] ARMOR: An Agentic Framework for Reaction Feasibility Prediction via Adaptive Utility-aware Multi-tool Reasoning — general_important · other · Ye Liu, Botao Yu, Xinyi Ling et al. Not related to my persona or midtraining work — this is a domain-specific chemistry application. Included because it's about combining multiple "tools" (models) intelligently, but the problem structur…
[4] GraphDC: A Divide-and-Conquer Multi-Agent System for Scalable Graph Algorithm Reasoning — general_important · general_ai · Wenjin Li, Jiaming Cui Not directly related to my persona/marker implantation or conditional behavior work. This is a multi-agent system for graph algorithms. Only tangentially relevant if I ever wanted to decompose persona…
[4] 2.5-D Decomposition for LLM-Based Spatial Construction — general_important · general_ai · Paul Whitten, Li-Jen Chen, Sharath Baddam Not related to my persona or behavioral installation work — this is about spatial reasoning and neuro-symbolic architectures for construction tasks. Included because it's a frontier LLM paper, but no…
[4] Randomness is sometimes necessary for coordination — general_important · general_ai · Rohan Patil, Jai Malegaonkar, Henrik I. Christensen Not directly related to my persona/midtraining work—this is about multi-agent coordination via structured randomness in RL, not about language model conditioning or behavioral installation.
[3] Online Allocation with Unknown Shared Supply — general_important · other · Tzeh Yuan Neoh, Davin Choo, Mengchu Yue et al. No connection to my persona installation or conditional behavior work — this is operations research for humanitarian logistics. Included for completeness but not relevant to language model behavior re…
[3] Weblica: Scalable and Reproducible Training Environments for Visual Web Agents — general_important · general_ai · O\u{g}uzhan Fatih Kar, Roman Bachmann, Yuanzheng Gong et al. Not directly related to my persona/midtraining work—this is about training web navigation agents via RL in scalable simulated environments. Only tangentially relevant if I ever explore how persona ins…
[2] Fast and Effective Redistricting Optimization via Composite-Move Tabu Search — general_important · other · Hai Jin, Diansheng Guo No connection to my work on language model personas, behavior installation, or conditional behavior. This is a combinatorial optimization paper for geographic redistricting. Included for completeness…