Bridging Expectation Signals: LLM-Based Experiments and a Behavioral Kalman Filter Framework

• URL: http://arxiv.org/abs/2601.17527v1
• Date: Sat, 24 Jan 2026 16:56:42 GMT
• Title: Bridging Expectation Signals: LLM-Based Experiments and a Behavioral Kalman Filter Framework
• Abstract summary: We develop a Behavioral Kalman Filter framework to quantify how LLM-based agents update expectations.<n>We show that household and firm CEO agents place substantially larger weights on individual signals compared to aggregate signals.<n>We demonstrate that LoRA fine-tuning mitigates, but does not fully eliminate, behavioral biases in LLM expectation formation.
• Score: 2.5735476569508995
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As LLMs increasingly function as economic agents, the specific mechanisms LLMs use to update their belief with heterogeneous signals remain opaque. We design experiments and develop a Behavioral Kalman Filter framework to quantify how LLM-based agents update expectations, acting as households or firm CEOs, update expectations when presented with individual and aggregate signals. The results from experiments and model estimation reveal four consistent patterns: (1) agents' weighting of priors and signals deviates from unity; (2) both household and firm CEO agents place substantially larger weights on individual signals compared to aggregate signals; (3) we identify a significant and negative interaction between concurrent signals, implying that the presence of multiple information sources diminishes the marginal weight assigned to each individual signal; and (4) expectation formation patterns differ significantly between household and firm CEO agents. Finally, we demonstrate that LoRA fine-tuning mitigates, but does not fully eliminate, behavioral biases in LLM expectation formation.

Related papers

• Chain-of-Experience for Continual LLM Improvement [57.11645184182825]
  We study how large language models learn from iterative experience at test time.<n>We instantiate Chain-of-Experience (CoE) with diverse feedback mechanisms.<n>Our study shows that leveraging iterative experience consistently outperforms feedback-free baselines.
  arXiv  Detail & Related papers  (2026-08-18T17:22:54Z)
• Do LLMs Take Care of Their Own? Similarity Signals Can Induce Cooperation [29.79569269141268]
  This paper introduces the first framework for evaluating LLM decision making when agents are provided with graded similarity signals.<n>We find that different LLM models vary drastically in how they navigate similarity signals.<n>Experiments also show that the dataset based on which the similarity signal is computed has small to no impact on induced cooperation.
  arXiv  Detail & Related papers  (2026-08-12T14:47:15Z)
• Uncovering Salience-Driven Dynamics in Consumer Confidence with Generative Social Simulation [56.70690339492564]
  We introduce ConsumerSim, a generative Human--Environment response framework that reconstructs Consumer Confidence Index dynamics.<n>Across U.S., EU27, and Japanese official CCI target series, ConsumerSim ranks first among persistence, time-series, regression, and shocks information-augmented baselines.<n>Findings support a behavioral view of consumer confidence as an interpretable Human--Environment response process.
  arXiv  Detail & Related papers  (2026-06-29T14:46:22Z)
• Is Capability a Liability? More Capable Language Models Make Worse Forecasts When It Matters Most [11.4807141145402]
  In inverse scaling, more capable models produce worse distributional forecasts on forecasting problems with superlinear growth and tail risk of regime change.<n>The pattern appears on ForecastBench-Sim, in forecasting synthetic SIR epidemics with a matched linear control, and replicates in real-world datasets on COVID-19, measles, housing markets, and hyperinflation.<n>This inverse scaling does not appear on single-threshold metrics common in LLM forecasting benchmarks, reversing the sign of the capability--accuracy relationship on identical outputs.
  arXiv  Detail & Related papers  (2026-05-21T16:14:33Z)
• How Independent are Large Language Models? A Statistical Framework for Auditing Behavioral Entanglement and Reweighting Verifier Ensembles [46.63622714488747]
  Shared pretraining data, distillation, and alignment pipelines can induce hidden behavioral dependencies, latent entanglement.<n>In practice, this manifests as correlated reasoning patterns and synchronized failures.<n>We develop a statistical framework for auditing behavioral entanglement among black-box language models.
  arXiv  Detail & Related papers  (2026-04-08T23:32:06Z)
• PhysicsAgentABM: Physics-Guided Generative Agent-Based Modeling [47.029742241618635]
  Large language model (LLM)-based multi-agent systems enable expressive agent reasoning but are expensive to scale and poorly calibrated for timestep-aligned state-transition simulation.<n>We propose PhysicsAgentABM, which shifts inference to behaviorally coherent agent clusters.<n> Experiments across public health, finance, and social sciences show consistent gains in event-time accuracy and calibration over mechanistic, neural, and LLM baselines.
  arXiv  Detail & Related papers  (2026-02-05T18:59:01Z)
• TransportAgents: a multi-agents LLM framework for traffic accident severity prediction [1.4871782604215074]
  TransportAgents is a hybrid multi-agent framework that integrates category-specific LLM reasoning with a multilayer perceptron (MLP) integration module.<n>Experiments on two U.S. datasets show TransportAgents consistently outperforms both traditional machine learning and advanced LLM-based baselines.<n>The framework exhibits strong robustness, scalability, and cross-dataset generalizability.
  arXiv  Detail & Related papers  (2026-01-21T23:14:05Z)
• Anchors in the Machine: Behavioral and Attributional Evidence of Anchoring Bias in LLMs [0.0]
  This paper advances the study of anchoring in large language models (LLMs) through three contributions.<n>Results reveal robust anchoring effects in Gemma-2B, Phi-2, and Llama-2-7B, with attribution signaling that the anchors influence reweighting.<n>Findings demonstrate that anchoring bias in LLMs is robust, measurable, and interpretable, while highlighting risks in applied domains.
  arXiv  Detail & Related papers  (2025-11-07T23:35:19Z)
• CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards [80.78748457530718]
  Self-evolution is a central research topic in enabling large language model (LLM)-based agents to continually improve their capabilities after pretraining.<n>We introduce Co-Evolving Multi-Agent Systems (CoMAS), a novel framework that enables agents to improve autonomously by learning from inter-agent interactions.
  arXiv  Detail & Related papers  (2025-10-09T17:50:26Z)
• Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails [103.05296856071931]
  We identify the Alignment Tipping Process (ATP), a critical post-deployment risk unique to self-evolving Large Language Model (LLM) agents.<n>ATP arises when continual interaction drives agents to abandon alignment constraints established during training in favor of reinforced, self-interested strategies.<n>Our experiments show that alignment benefits erode rapidly under self-evolution, with initially aligned models converging toward unaligned states.
  arXiv  Detail & Related papers  (2025-10-06T14:48:39Z)
• Corrupted by Reasoning: Reasoning Language Models Become Free-Riders in Public Goods Games [87.5673042805229]
  How large language models balance self-interest and collective well-being is a critical challenge for ensuring alignment, robustness, and safe deployment.<n>We adapt a public goods game with institutional choice from behavioral economics, allowing us to observe how different LLMs navigate social dilemmas.<n>Surprisingly, we find that reasoning LLMs, such as the o1 series, struggle significantly with cooperation.
  arXiv  Detail & Related papers  (2025-06-29T15:02:47Z)
• Backdoor Cleaning without External Guidance in MLLM Fine-tuning [76.82121084745785]
  Believe Your Eyes (BYE) is a data filtering framework that leverages attention entropy patterns as self-supervised signals to identify and filter backdoor samples.<n>It achieves near-zero attack success rates while maintaining clean-task performance.
  arXiv  Detail & Related papers  (2025-05-22T17:11:58Z)
• Collaborative Value Function Estimation Under Model Mismatch: A Federated Temporal Difference Analysis [55.13545823385091]
  Federated reinforcement learning (FedRL) enables collaborative learning while preserving data privacy by preventing direct data exchange between agents.<n>In real-world applications, each agent may experience slightly different transition dynamics, leading to inherent model mismatches.<n>We show that even moderate levels of information sharing significantly mitigate environment-specific errors.
  arXiv  Detail & Related papers  (2025-03-21T18:06:28Z)
• Does Worst-Performing Agent Lead the Pack? Analyzing Agent Dynamics in Unified Distributed SGD [7.434126318858966]
  Distributed learning is essential to train machine learning algorithms across heterogeneous agents. We conduct an analysis of Unified Distributed SGD (UD-SGD) We assess how different sampling strategies, such as i.i.d. sampling, shuffling, and Markovian sampling, affect the convergence speed of UD-SGD.
  arXiv  Detail & Related papers  (2024-09-26T03:12:20Z)
• Explaining Large Language Models Decisions Using Shapley Values [1.223779595809275]
  Large language models (LLMs) have opened up exciting possibilities for simulating human behavior and cognitive processes. However, the validity of utilizing LLMs as stand-ins for human subjects remains uncertain. This paper presents a novel approach based on Shapley values to interpret LLM behavior and quantify the relative contribution of each prompt component to the model's output.
  arXiv  Detail & Related papers  (2024-03-29T22:49:43Z)
• How Far Are LLMs from Believable AI? A Benchmark for Evaluating the Believability of Human Behavior Simulation [46.42384207122049]
  We design SimulateBench to evaluate the believability of large language models (LLMs) when simulating human behaviors. Based on SimulateBench, we evaluate the performances of 10 widely used LLMs when simulating characters.
  arXiv  Detail & Related papers  (2023-12-28T16:51:11Z)
• Efficient Model-based Multi-agent Reinforcement Learning via Optimistic Equilibrium Computation [93.52573037053449]
  H-MARL (Hallucinated Multi-Agent Reinforcement Learning) learns successful equilibrium policies after a few interactions with the environment. We demonstrate our approach experimentally on an autonomous driving simulation benchmark.
  arXiv  Detail & Related papers  (2022-03-14T17:24:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.