Complex Systems and Decision Making

Latest papers

• When Harnesses Lose the Signal: Causal Evaluation of Recovery in LLM Agents

  Shuyao Xiao, Shengling Wang, Xuan Chen, Ke Chao, Ming Cui, Feifei Qian, Chaoyang Mei, Fanlin Meng, Ziming Yu, Junxi Yin · 2 October 2026

  Large language model agents rely on external harnesses to pass information between the model and its environment and to recover from execution errors. Yet recovery is usually judged only by average task success. This hides an important tension. The same operation can rescue a failing trajectory or d…

• Beyond Prediction: Steering VLM Agents with Retrospective World Modeling

  Yongjiang Liu, Jie Zhang, Haoyue Zhang, Jingcai Guo, Deze Zeng, Song Guo · 1 October 2026

  Equipping VLM agents with world modeling capabilities has shown strong potential for complex reasoning and long-horizon planning, while reducing the dependence of policy learning on costly real-world interactions. Existing methods mainly rely on prospective simulation to predict the consequences of …

• Nudgeability: Reasoning Models Follow Confidence Signals Without Tracking Their Own Competence

  Rohit Saxena, Utkarsh Upadhyay · 29 September 2026

  Reasoning language models that can call tools must decide during inference whether to answer unaided or delegate. Any self-reflection mechanism for this must answer three questions: where the reflective signal comes from (verbal reports, output distributions, hidden states, a separate predictor), ho…

• Rethinking World Models for Safety-Critical Embodied Systems

  Kailang Ma, Heye Huang, Inhi Kim, Kitae Jang · 4 September 2026

  World models have progressed from compact latent dynamics to generative, controllable, and interactive simulators of embodied environments. However, high predictive likelihood and visual fidelity do not necessarily ensure that a model preserves the evidence required for safe decision-making. This pe…

• EgoBrain: Synergizing Minds and Eyes For Human Action Understanding

  Nie Lin, Yansen Wang, Dongqi Han, Weibang Jiang, Jingyuan Li, Ryosuke Furuta, Yoichi Sato, Dongsheng Li · 11 August 2026

  The integration of brain-computer interfaces (BCIs), in particular electroencephalography (EEG), with artificial intelligence (AI) has shown tremendous promise in decoding human cognition and behavior from neural signals. In particular, the rise of multimodal AI models have brought new possibilities…

• Closure of Self-Determining System Based on Causal and Constitutive Relations

  Yoshiyuki Ohmura, Earnest Kota Carr, Yasuo Kuniyoshi · 23 June 2026

  A self-determining system is defined as one in which causes originating within the system influence the system itself. This definition raises the question of how to specify system boundaries. Although the concept of "closure" is commonly used for this purpose, defining boundaries solely in terms of …

• MedicalAgentsBench for Complex Medical Reasoning: Comparing Internalized Reasoning Models versus Externalized Agent-based Frameworks

  Yanjun Shao, Xiangru Tang, Jiwoong Sohn, Jiapeng Chen, Yuxuan Liao, Jiayi Zhang, Jinyu Xiang, Fang Wu, Yilun Zhao, Chenglin Wu, Wenqi Shi, Arman Cohan, Mark Gerstein · 17 June 2026

  Complex medical reasoning requires integrating heterogeneous clinical evidence across multiple inference steps. Large language models (LLMs) now approach this through two routes: internalized reasoning and externalized agent scaffolding (frameworks that decompose problems collaboratively amongst mul…

• RAINO: Anchoring Agents in Reality, A Systematic Review and Conceptual Framework for Realism in Agent-Based Modelling

  Lo\"is Vanh\'ee, Melania Borit · 5 June 2026

  Realism is a central yet seemingly under-theorized concept in Agent-Based Modelling. This paper presents a Systematic Literature Review, aiming to identify how realism is currently operationalized and demonstrated. The results show that realism is often poorly defined and lacks a consistent conceptu…

• TemplateRL: Structured Template-Guided Reinforcement Learning for LLM Reasoning

  Jinyang Wu, Chonghua Liao, Mingkuan Feng, Shuai Zhang, Zhengqi Wen, Haoran Luo, Ling Yang, Huazhe Xu, Jianhua Tao · 18 May 2026

  Reinforcement learning (RL) has emerged as an effective paradigm for enhancing model reasoning. However, existing RL methods like GRPO typically rely on unstructured self-sampling to fit scalar rewards, often producing inefficient rollouts that fail to capture transferable problem-solving strategies…

• Exploring the System 1 Thinking Capability of Large Reasoning Models

  Wenyuan Zhang, Shuaiyi Nie, Xinghua Zhang, Zefeng Zhang, Tingwen Liu · 4 May 2026

  This paper explores the system 1 thinking capability of Large Reasoning Models (LRMs), the intuitive ability to respond efficiently with minimal token usage. While existing LRMs rely on long-chain reasoning and excel at complex tasks, their system 1 thinking ability remains largely underexplored. Th…

• Large Reasoning Models Learn Better Alignment from Flawed Thinking

  ShengYun Peng, Eric Smith, Ivan Evtimov, Song Jiang, Pin-Yu Chen, Hongyuan Zhan, Haozhu Wang, Duen Horng Chau, Mahesh Pasupuleti, Jianfeng Chi · 13 April 2026

  Large reasoning models (LRMs) "think" by generating structured chain-of-thought (CoT) before producing a final answer, yet they still lack the ability to reason critically about safety alignment and are easily biased when a flawed premise is injected into their thought process. We propose RECAP (Rob…

• An evolutionary perspective on modes of learning in Transformers

  Alexander Y. Ku, Thomas L. Griffiths, Stephanie C. Y. Chan · 24 March 2026

  The success of Transformers lies in their ability to improve inference through two complementary strategies: the permanent refinement of model parameters via in-weight learning (IWL), and the ephemeral modulation of inferences via in-context learning (ICL), which leverages contextual information mai…

• Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO

  Peter Chen, Xiaopeng Li, Ziniu Li, Xi Chen, Tianyi Lin · 11 March 2026

  Reinforcement learning (RL) has proven effective in strengthening the reasoning capabilities of large language models (LLMs). A widely adopted method, Group Relative Policy Optimization (GRPO), has shown strong empirical results in training recent reasoning models, but it fails to update the policy …

• Generative Models in Decision Making: A Survey

  Xinyu Shao, Jianping Zhang, Haozhi Wang, Leo Maxime Brunswic, Kaiwen Zhou, Jiqian Dong, Kaiyang Guo, Zhitang Chen, Jun Wang, Jianye Hao, Xiu Li, Yinchuan Li · 6 March 2026

  Generative models have fundamentally reshaped the landscape of decision-making, reframing the problem from pure scalar reward maximization to high-fidelity trajectory generation and distribution matching. This paradigm shift addresses intrinsic limitations in classical Reinforcement Learning (RL), p…

• Policy myopia as a mechanism of gradual disempowerment in Post-AGI governance, Circa 2049

  Subramanyam Sahoo · 4 March 2026

  Post-AGI information systems won't merely distract governance from important problems. They will systematically transform how institutions make decisions in ways that progressively remove humans from meaningful participation in resource allocation. We show that policy myopia -- the tendency to prior…

• The First Impression Problem: Internal Bias Triggers Overthinking in Reasoning Models

  Renfei Dang, Zhening Li, Shujian Huang, Jiajun Chen · 3 March 2026

  Reasoning models often exhibit overthinking, characterized by redundant reasoning steps. We identify \emph{internal bias} elicited by the input question as a key trigger of such behavior. Upon encountering a problem, the model immediately forms a preliminary guess about the answer, which we term an …

• Random Scaling of Emergent Capabilities

  Rosie Zhao, Tian Qin, David Alvarez-Melis, Sham Kakade, Naomi Saphra · 19 February 2026

  Language models famously improve under a smooth scaling law, but some specific capabilities exhibit sudden breakthroughs in performance. Advocates of "emergence" view these capabilities as unlocked at a specific scale, but others attribute breakthroughs to superficial metric thresholding effects. We…

• Invisible Saboteurs: Sycophantic LLMs Mislead Novices in Problem-Solving Tasks

  Jessica Y. Bo, Majeed Kazemitabaar, Mengqing Deng, Michael Inzlicht, Ashton Anderson · 12 February 2026

  Sycophancy, the tendency of LLM-based chatbots to express excessive agreement with their users, even when inappropriate, is emerging as a significant risk in human-AI interactions. However, the extent to which this affects human-LLM collaboration in complex problem-solving tasks is not well quantifi…

• Pretrain Value, Not Reward: Decoupled Value Policy Optimization

  Chenghua Huang, Lu Wang, Fangkai Yang, Pu Zhao, Zhixu Li, Qingwei Lin, Dongmei Zhang, Saravan Rajmohan, Qi Zhang · 27 January 2026

  In this paper, we explore how directly pretraining a value model simplifies and stabilizes reinforcement learning from human feedback (RLHF). In reinforcement learning, value estimation is the key to policy optimization, distinct from reward supervision. The value function predicts the \emph{return-…

• Position: Foundation Models for Tabular Data within Systemic Contexts Need Grounding

  Tassilo Klein, Johannes Hoffart · 21 January 2026

  This position paper argues that foundation models for tabular data face inherent limitations when isolated from operational context - the procedural logic, declarative rules, and domain knowledge that define how data is created and governed. Current approaches focus on single-table generalization or…

• YRC-Bench: A Benchmark for Learning to Coordinate with Experts

  Mohamad H. Danesh, Nguyen X. Khanh, Tu Trinh, Benjamin Plaut · 14 January 2026

  When deployed in the real world, AI agents will inevitably face challenges that exceed their individual capabilities. A critical component of AI safety is an agent's ability to recognize when it is likely to fail in a novel situation and to yield control to a more capable expert system. Leveraging s…

• Learning from Reasoning Failures via Synthetic Data Generation

  Gabriela Ben Melech Stan, Estelle Aflalo, Avinash Madasu, Vasudev Lal, Phillip Howard · 13 January 2026

  Training models on synthetic data has emerged as an increasingly important strategy for improving the performance of generative AI. This approach is particularly helpful for large multimodal models (LMMs) due to the relative scarcity of high-quality paired image-text data compared to language-only d…

• Learning from Imperfect Data: Robust Inference of Dynamic Systems using Simulation-based Generative Model

  Hyunwoo Cho, Hyeontae Jo, Hyung Ju Hwang · 25 December 2025

  System inference for nonlinear dynamic models, represented by ordinary differential equations (ODEs), remains a significant challenge in many fields, particularly when the data are noisy, sparse, or partially observable. In this paper, we propose a Simulation-based Generative Model for Imperfect Dat…

• Enhancing Multi-Agent Collaboration with Attention-Based Actor-Critic Policies

  Hugo Garrido-Lestache Belinchon, Jeremy Kedziora · 23 December 2025

  This paper introduces Team-Attention-Actor-Critic (TAAC), a reinforcement learning algorithm designed to enhance multi-agent collaboration in cooperative environments. TAAC employs a Centralized Training/Centralized Execution scheme incorporating multi-headed attention mechanisms in both the actor a…

• Demonstration Sidetracks: Categorizing Systematic Non-Optimality in Human Demonstrations

  Shijie Fang, Hang Yu, Qidi Fang, Reuben M. Aronson, Elaine S. Short · 18 December 2025

  Learning from Demonstration (LfD) is a popular approach for robots to acquire new skills, but most LfD methods suffer from imperfections in human demonstrations. Prior work typically treats these suboptimalities as random noise. In this paper we study non-optimal behaviors in non-expert demonstratio…