Exploration-Exploitation Dilemma

LLM-driven evolutionary search finds programs by launching seeds and iterating each one. Papers report a single budget setting, usually one seed run for a fixed number of iterations, and rank methods from that one point. We show this is not enough. We evaluate three evolutionary search strategies on five optimization tasks, commonly used by papers in the genre to report results. We run the analysis over a full grid of seeds and iterations. Our findings suggest that the best way to split a fixed budget between more seeds (width) and more iterations (depth) changes with the strategy, the task, and the total budget. Furthermore, we observe that the ranking of strategies also changes with the budget. On one task the strategy that looks worst at one seed is best at forty seeds. On another the best number of iterations is well below the value common in practice, so extra depth wastes budget that more seeds would turn into score. We provide a measurement protocol that reports the seeds-by-iterations frontier and practical guidance for using it.

Learning from trial and error is a promising way to improve language agents on complex tasks such as computer control. Reflexion introduced verbal reinforcement learning, which turns failed trials into text that guides later attempts without updating model parameters. We introduce VRL-Bench, a harness for fair evaluation of trial-and-error learning under finite trial budgets. Across three models on MiniWoB and WebShop, we evaluate updates from several prominent verbal-memory methods spanning Reflexion and later work: each improves observed success over memory-free retry in some settings but reduces it in others. Replay experiments show that using reflection can reduce success rates, revealing a trade-off between exploiting experience and continued exploration. We propose VEX$^2$, a verbal exploration--exploitation scheduler that uses a language model to jointly select policies and allocate the remaining trial budget. VEX$^2$ is the only evaluated update to achieve positive observed success-rate gains over retry in all six settings.

Monocular 3D hand and body mesh recovery often suffers from severe occlusion and ambiguity. Traditional deterministic methods typically regress a single optimal solution, leading to overconfident predictions. In this paper, we introduce an exploration--exploitation paradigm for ambiguous mesh recovery with multi-hypothesis learning and selection. Specifically, during exploration, based on our probabilistic formulation and entropy maximization, we propose a novel multi-hypothesis method referred to as MHE-Former. It is a Transformer-based multi-hypothesis framework, ensuring high training efficiency and label friendliness while generating plausible and diverse hypotheses. During exploitation, we propose Hypothesis Selection, a context-aware process for multiple predictions. Especially leveraging VLM's powerful visual understanding and reasoning capabilities, it allows users to choose the most plausible and desired estimate with additional evidence and natural language intent. Extensive experiments demonstrate that our framework achieves state-of-the-art performance in accuracy and diversity across multiple datasets. The user preference study further shows the practicality of our hypothesis selection process.

In evolutionary algorithms powered by language models, the LLM acts as a single operator that simultaneously updates structural components (like control flow) and continuous parameters. While LLMs can be good at the first, they are not efficient at the second, wasting tokens taking discrete jumps inside a trial and error loop. We resolve this by formalizing a hybrid nested search, in which an outer loop has the LLM propose a structural sketch, with numeric gaps, and an inner numerical optimizer tunes the sketch. Both the outer and inner solvers are pluggable: any text-based optimizer can be combined with a zero-order optimizer (CMA-ES), gradient-based routines, or MCMC samplers. We validate our framework across three scientific domains: (i) meta-optimizers on closed-form test functions, (ii) code-based policies for systems research and social dilemmas; and (iii) approximate Bayesian inference tasks. Across all three, the hybrid optimizer is superior to both vanilla LLM-driven search and pure numerical optimization baselines. Code at: https://github.com/vicgalle/hybrid-nested-search

Pretraining navigation diffusion policies rely on large-scale expert demonstrations. These data are typically generated by a fully-informed oracle planner suited to a single nominal robot. This limits the policy's generalization to diverse embodiments and challenging scenarios (e.g., escaping dead ends or detouring long obstacles) that demand diverse local reactive behaviors with only onboard local observations. Post-training the policy with reinforcement learning (RL) offers a principled remedy. However, previous RL for diffusion approaches lead to only marginal improvements. This is because the intractable likelihood of diffusion policies renders policy gradients unstable in addition to inefficient policy exploration. To address these challenges, we propose a data-efficient diffusion RL post-training framework - GQRM (Group Q-score Reweighted Matching). Our framework introduces two complementary designs: (i) a self-bootstrapped exploration strategy with behavior perturbation that preserves the pretrained policy prior, and (ii) a group Q-score normalization mechanism that computes per-trajectory values on each state for efficient reweighted score matching. By conducting distributed online RL training across heterogeneous embodiments, the resulting fine-tuned policy, X-NavDP, achieves state-of-the-art cross-embodiment visual navigation performance, improving the overall success rate from 61.20% to 84.28% in simulation and 10% to 65% in real-world hard cases. The code and model are publicly available at https://yty-sky.github.io/x-navdp-project-page.

An agent playing a Nash-equilibrium strategy in a two-player zero-sum imperfect-information game secures the game value but forfeits the additional value offered by a flawed opponent. Diffuse deviations pose a particular challenge: binary release rules may gather too little evidence to act, while a full best response to an incomplete opponent model can be highly exploitable. We introduce \emph{budget-constrained confidence-scheduled restricted responses} (CS-RNR), the first opponent-exploitation method whose safety guarantee is a certificate the agent computes on the strategy it actually deploys, so that every exploit it commits to is one it has audited itself. The method tracks pooled action frequencies with anytime-valid confidence sequences and treats a frequency as exploitable only once its interval separates from an equilibrium reference. The confirmed deviations define a conservative opponent model, which a restricted-response solve turns into candidate counter-strategies over a grid of pin levels. Before deployment, each complete candidate is evaluated by a full-tree best response. The resulting certificate is compared with a user-specified budget and committed atomically with the strategy. Because this check is performed on the played strategy, model quality determines the exploitation achieved while the certificate controls reference-relative expected loss. In Leduc hold'em, CS-RNR obtains $6.2\times$ the steady-state gain of a money-verified binary gate while keeping every deployed strategy within budget. A trajectory mixture using the same estimator reaches $13.6\times$ the budget. Across Leduc, Liar's Dice, and 5-rank Leduc, all $36{,}000$ audited hands satisfy the reported certificate tolerance.

Enabling large language model (LLM) agents to accumulate and reuse experience from past interactions remains a central challenge in real-world applications. A promising solution is to treat skills as trainable states and optimize them in the same way as model parameters in neural network training. However, data-driven skill optimization is prone to overfitting to the limited trajectories collected from real environments. Overexploiting these trajectories overfits the current batch, while unconstrained exploration causes regression on previously solved cases. This tension motivates a constrained search view of skill self-evolution, governed by an exploration--exploitation trade-off. We propose SkillBoost, a three-stage framework that mitigates both risks: structured exploitation localizes observed failures to editable skill components, prior-guided exploration draws on prior knowledge in the LLM to generate diverse repair candidates, and verified acceptance commits a candidate only when it improves performance within a regression bound. Experiments across 23 model--benchmark configurations show that SkillBoost achieves state-of-the-art performance while mitigating overfitting, outperforming both human-crafted and LLM-generated skills. Transfer experiments further show that optimized skills can be reused by other agents on similar tasks.

Collective problem solving often requires that group members consider the tradeoff between exploitation of known solutions and exploration for new ones, where information of known solutions can be disseminated among individual members through communication networks. The Mason--Watts experiment (PNAS 2012) showed that human groups in shorter-path networks outperform those in longer-path networks on a two-dimensional search task. In this work, we focus on the investigation of such network-efficiency effects in the setting of a group of large language model (LLM) agents. Specifically, we consider groups of sixteen LLM agents playing the Mason--Watts experiment on the eight Mason--Watts network topologies. Moreover, we develop mechanistic Bayesian optimization agents such that the performance of LLM agents can be compared with both the mechanistic agents and the human experimental data. Our computational experiments indicate that the LLM agents show a significant network-efficiency effect when instructed to randomize their first-round choices, but not under the default initialization. In this experiment, adding a one-sentence first-round randomization instruction improves collective payoff by more than three times the estimated payoff difference across the eight network topologies. Also, the Bayesian optimization agents obtain higher payoffs than the evaluated LLM agents on this spatial search task. We further compare the agents' exploration--exploitation behavior, copying, and spatial diversity.

Computing Nash equilibrium policies in multi-agent Pursuit-Evasion games (PEG) is challenging due to the exponential growth of the joint state and action spaces with the number of agents. Existing approaches either rely on offline equilibrium approximations, which may lack adaptability during execution, or online planning methods, which suffer from large branching factors. In this work, we propose Primitive-Guided Tree Search (PGTS), a hybrid framework that integrates offline exact Nash equilibrium computation with online tree search: PGTS first solves a collection of smaller, tractable sub-games offline; at deployment, PGTS performs online tree search at each time step, using the optimal sub-game policies and value functions to guide tree expansion and estimate leaf-node values. Extensive experiments on varied graph topologies, including real-world networks, demonstrate that PGTS significantly outperforms state-of-the-art learning and heuristic baselines, while maintaining robust performance against adversaries.

Recent breakthroughs of Reinforcement Learning (RL) have highlighted its potential for complex agentic Large Language Model (LLM) tasks. However, existing efforts largely focus on single-task settings, whereas real-world deployment necessitates a generalist agent capable of solving multiple tasks simultaneously. In this work, we identify a critical yet underexplored phenomenon in multi-task agentic RL: different tasks can exhibit exploration-exploitation pace mismatch. Specifically, easier tasks may converge early to low-entropy policies that hinder learning on harder tasks, while harder tasks can, in turn, push easier tasks back toward high-entropy exploration. This back-and-forth interaction creates inter-task entropy crossovers and frequent entropy spikes. Inspired by this observation, we introduce Entropy Pacing Policy Optimization (EPPO) for multi-task agentic LLMs, which coordinates entropy across tasks to stabilize multi-task optimization. At the core of EPPO is a task-wise dynamic clipping mechanism that replaces the fixed clipping threshold in Group Relative Policy Optimization (GRPO) with a task entropy-aware adaptive bound, tightening updates for over-confident tasks while relaxing them for under-explored ones. Experiments on the multi-task agentic benchmarks demonstrate that the proposed EPPO yields results superior to its counterparts.

Recent advancements in agentic AI have increasingly moved toward graph-based methods, driven by the demand for explainable, human-centered, and non-linear reasoning workflows. A prominent example is Genetic Network Programming (GNP), a self-evolving algorithm that utilizes directed graphs to evolve interpretable decision structures for agents. As in most evolutionary algorithms, effectively balancing exploration and exploitation is a key aspect of GNP. However, this trade-off has received limited attention in the GNP literature. To address this gap, we draw inspiration from human developmental patterns, where children prioritize broad experimentation and action over deliberation, with this tendency reversing with age. By mapping transitions between GNP's judgment nodes to deliberation and processing nodes to action, we propose Human-Inspired GNP (HGNP), a novel adaptive framework that dynamically regulates the exploration-exploitation balance throughout the evolutionary process. The method consists of novel adaptive crossover and mutation operators, and a cycle elimination mechanism. HGNP not only improves the evolutionary process but also provides a framework for adjusting the exploration-exploitation balance based on the characteristics of the target environment and its search space. This approach is more effective than tuning via crossover and mutation probabilities in standard GNP. The modifications are general and can be applied to almost all GNP variants. When integrated with standard GNP and two recently introduced GNP variants and evaluated on the Tileworld benchmark, HGNP demonstrated significant performance improvement in agents' strategy. The combination of HGNP with Situation-based GNP (HGNP-SBGNP) achieved the best overall results.

RL post-training strategies are dataset-dependent and reveal a recurring empirical pattern: capacity parameters accumulate monotonically across stages, while regularization parameters predominantly oscillate in response to shifting training dynamics. This distinction highlights a potential flaw in fixed training schedules: by forcing all parameters along rigid paths, they fail to capture the dynamic exploration-exploitation tradeoffs that regularization must track. We uncover this through LLMZero, an agentic system that optimizes training trajectories via tree search by diagnosing pathologies at each checkpoint and proposing coordinated multi-parameter transitions. Across four diverse GRPO tasks, LLMZero discovers strategies that improve over the base model by 9% to 140% and over grid search by 6% to 15% (relative), consistently outperforming random search and a skill-based agent under a matched compute budget. The capacity--regularization asymmetry is consistent across all four tasks, offering a candidate design heuristic for multi-stage training.

Preference alignment is central to improving large language models, but standard reward-based formulations can be restrictive when human preferences are cyclic, non-transitive, or otherwise not representable by a scalar reward. Nash Learning from Human Feedback (NLHF) addresses this limitation by modeling alignment as a preference game and targeting a Nash equilibrium rather than a reward maximizer. However, the learning-theoretic foundations of scalable NLHF remain limited. Existing regret guarantees rely on oracle-based methods that estimate a general preference model and solve KL-regularized minimax problems, while iterative NLHF methods directly optimize policy-level preference losses and are easier to implement but lack regret guarantees. We study online iterative NLHF under general preference models and identify exploration as the key obstacle. First, we show that standard iterative NLHF can suffer an exponential dependence on the KL-regularization parameter, revealing that implicit exploration through policy updates is insufficient for controlling regret. Second, we propose an explicitly exploratory iterative NLHF algorithm that combines SFT-based regularization with adversarial policy exploration. The resulting method retains the direct policy optimization structure of iterative NLHF, avoids explicit preference model estimation, and achieves an $O(\sqrt{T})$ regret bound without an exponential dependence on the KL-regularization parameter. We show that the regret can be improved to $O(\log(T))$ with access to a minimax oracle, clarifying the computational-statistical tradeoff in learning general preference games. Finally, we instantiate our method for LLM fine-tuning and evaluate it on \texttt{Llama-3-8B-Instruct} across multiple benchmarks, where explicit exploration yields consistent improvements over existing NLHF baselines.

The Policy-Space Response Oracles (PSRO) framework scales equilibrium computation to large zero-sum games by iteratively expanding a restricted strategy set using deep reinforcement learning (DRL). A central challenge is to construct, under limited computational budgets, a small strategy population whose induced game well approximates the full game. Existing PSRO variants typically expand the population using best responses to meta-strategies computed from restricted-game payoffs, which can lead to inefficient expansions that provide limited global improvement. We propose to guide population expansion by directly evaluating the post-expansion population quality. Specifically, we adopt Population Exploitability (PE) to measure how well a restricted strategy set represents the full game, and introduce a two-phase exploration--selection framework that explicitly minimizes PE during expansion. We instantiate this framework as Global PSRO, a practical DRL-based algorithm that efficiently generates candidate responses and estimates PE via parameter-sharing conditional neural networks. Experiments across multiple two-player zero-sum games show that Global PSRO achieves lower exploitability and approximates Nash equilibria with significantly fewer policy iterations than prior PSRO methods.

Recent advances in online reinforcement learning (RL) for large language models (LLMs) have demonstrated promising performance in complex reasoning tasks. However, they often exhibit an imbalanced exploration-exploitation trade-off, resulting in unstable optimization and sub-optimal performance. We introduce IB-Score, a novel metric grounded in Information Bottleneck theory that evaluates policy's exploration-exploitation balance by quantifying the trade-off between step-level reasoning diversity and mutual information shared with the correct answer. Analysis based on IB-Score shows that popular online RL approaches (e.g., GRPO) with common regularizers fail to consistently maintain balance during training with suboptimal results. To address this, we propose Information Bottleneck-driven Tree-based Policy Optimization (IB-TPO), a principled framework that formulates IB-Score as a fine-grained optimization objective and utilizes a novel IB-guided tree sampling strategy that not only improves the efficiency of online sampling with 50% more trajectories under the same token budget, but also reuses the tree structure for effective IB-Score Monte Carlo estimation. Extensive experiments across standard benchmarks show that our method significantly outperforms GRPO baseline by 2.9% to 3.6% and also outperforms other state-of-the-art online RL approaches. Our code is available at https://github.com/alibaba/EfficientRL.

This paper develops a fast numerical dual control for exploration and exploitation (DCEE) method to address auto-optimization problems in unknown environments. In auto-optimization problems, the optimal operating condition is unknown a priori and may vary with the environment. As in classical dual control techniques, computational burden remains a major concern in DCEE for active learning. Existing DCEE methods provide a principled exploration-exploitation objective, but mainly realized through standard optimization packages or explicit gradient-type update laws, where the numerical structure of the DCEE has not been fully exploited. This paper shows that the reward function in DCEE has an inherent convex-over-nonlinear structure, where the exploitation and exploration terms form a unified nonlinear residual map equipped with a convex outer loss. Benefiting from this structure, a structure-exploiting numerical method is developed by linearizing only the nonlinear residual map while preserving the convex outer loss. Thus, each subproblem is transformed into a structured convex form that can be solved reliably. The resulting generalized Gauss-Newton Hessian approximation is positive semidefinite and depends only on first-order derivatives, thereby supporting fast online computation. The proposed method is evaluated on a vehicle cruising auto-optimization problem and compared with existing methods. Simulation and hardware-in-the-loop experimental results show that the proposed method improves control performance and achieves a speedup of approximately one order of magnitude, with a microsecond-level maximum computation time of only 83 μs on a typical vehicle embedded CPU.

Reinforcement learning is a powerful learning paradigm that has spearheaded progress in numerous domains. Its core promise lies in learning through high-level goals without the need for granular labels. However, it still remains elusive in the realm of audio, where it has received substantially less attention than in computer vision or other domains. The key question remains: how can agents learn to listen purely via reward-driven exploration? In this contribution, we present an overview of previous attempts and a new conceptual framework for learning to listen by reward. Our approach depends on the continuous search for novel sound sources. We formulate our framework, discuss open technical challenges, and present a first proof-of-concept implementation that showcases the feasibility of our approach.

Extracting multi-step explanations from knowledge graphs poses a combinatorial challenge requiring both heuristic guidance (as candidates proliferate with depth) and credit assignment (as path quality emerges over extended sequences). Frontier LLMs, strong on knowledge/reasoning benchmarks, offer a compelling source of such heuristics, yet their knowledge comes sans guarantees and compositional performance degrades as chains lengthen. We thus present TESSERA, a 3-part neuro-symbolic framework that uses LLMs in a circumscribed role: for local discriminative judgement rather than autonomous multi-step generation; the knowledge graph then defines the hypothesis space enforcing hard structural constraints, and MCTS coordinates the long-horizon search with principled credit assignment via backpropagation. LLMs perform dual roles as a prior policy biasing exploration and a comparative state evaluator supplying reward signals. Evaluation on drug mechanism elucidation across two complementary knowledge graphs demonstrates fidelity to curated biology while surfacing coherent alternative mechanisms, with ablations confirming discriminative contribution from both LLM components. Beyond its current application, our framework offers a general paradigm for compositional reasoning over structured knowledge.

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a pivotal technique for enhancing the reasoning capabilities of Large Language Models (LLMs). However, the de facto practice of mainstream RL algorithms is to treat all tokens of one response equally and assign the same optimization objective to each token, failing to provide granular guidance for the reasoning process. While in Chain-of-Thought (CoT) reasoning, different tokens usually play distinct roles. Therefore, the current RL algorithms lack an effective mechanism to dynamically balance the exploration-exploitation trade-off during learning. To this end, we propose Hierarchical Token-level Objective Control Policy Optimization (HTPO), a novel RL algorithm that takes the divide-and-conquer idea to hierarchically partition the response tokens into specific functional groups from three aspects (i.e., prompt difficulty, answer correctness, and token entropy). Within each group, according to the contributions to exploration or exploitation, we design specialized optimization objectives to facilitate the effective execution of each token's expected functionality. In this way, HTPO can achieve a more balanced exploration-exploitation trade-off. Extensive experiments on challenging reasoning benchmarks validate the superiority of our HTPO algorithm, which significantly outperforms the strong DAPO baseline (e.g., +8.6% and +6.7% on AIME'24 and AIME'25, respectively). When scaling test-time compute, the HTPO-trained model maintains a consistent performance advantage over the DAPO baseline, and the gap widens as the sampling budget increases, validating that our adaptive token-level control method fosters effective exploration without sacrificing exploitation performance. Code will be at https://github.com/xcyao00/HTPO.

This study presents a novel deterministic optimization algorithm based on a special variant of the Linear Congruential Generator (LCG). While conventional algorithms generally operate within the search space, the introduced technique follows a two-level architecture. In particular, an external loop that adaptively balances between exploration and exploitation, while the internal loop evaluates solutions. It is motivated by the intrinsic structure of the generator, the reason behind naming it the Structured Linear Congruential Generator (S- LCG). which enjoys a number of unique characteristics as follows: 1) a memoryless scheme, which ensures non-overlapping sequences based on distinct seeds, thus ensuring no evaluation redundancy; 2) bit splitting representation, which converts LCG states into multi-dimensional points to overcome the Marsaglia lattice effect; 3) adaptive exploration-exploitation of the generator space, which leads to implicit optimization of the surrogate smooth objective function; and 4) constant information gathering speed to avoid the problem of premature convergence. Extensive testing on 26 benchmark functions across dimensions d = 2 to 30 demonstrates that S-LCG comes within 1% of the global optimum in 83.3% of 138 cases (100% at d = 2, 81.2% at d = 30) while the nearest competitor GA achieved 75.4%. Statistical validation shows that S-LCG outperforms eight cutting-edge binary algorithms. Furthermore, its practical value is confirmed by validation on three constrained engineering design problems. In the end, S-LCG offers an optimization framework that is strictly reproducible and requires only one sensitive parameter to be tuned.

Online reinforcement learning from human feedback (RLHF) has emerged as a promising paradigm for aligning large language models (LLMs) by continuously collecting new preference feedback during training. A foundational challenge in this setting is exploration, which requires algorithms that enable the LLMs to generate informative comparisons that improve sample-efficiency in online RLHF. Existing exploration strategies often derive bonuses via on-policy expectations, which are difficult to estimate reliably from the limited historical preference data available during training; as a result, the policy can prematurely down-weight under-explored regions that may contain high-value behaviors. In this paper, we propose data-dependent exploration for preference optimization (DEPO), a simple and scalable method that leverages historical data to construct an extra uncertainty bonus for high-uncertainty regions, encouraging exploration toward potentially high-value data. Theoretically, we provide a data-dependent regret bound for the proposed algorithm, showing that it adapts to the hardness of the learning task itself and can be tighter than worst-case bounds in practice. Empirically, the proposed method consistently outperforms strong baselines across benchmarks, demonstrating improved sample efficiency.

Cooperative multi-agent reinforcement learning (MARL) requires agents to discover joint strategies in a combinatorially large state-action space, yet effective coordination configurations are exceedingly rare. Intrinsic motivation, which augments task rewards with novelty bonuses, is a popular approach for driving exploration, but its effectiveness hinges on the exploration intensity $β$, where too large a value overwhelms the task signal and causes coordination collapse, while too small a value prevents discovery of rare strategies. We address two complementary challenges: adapting $β$ globally over training, and allocating the exploration budget across agents whose intrinsic reward signals vary in reliability. Our framework combines a return-conditioned sigmoid schedule (RCB) for global intensity control with a per-agent Reward Signal Quality (RSQ) metric that concentrates the exploration budget on agents with reliable signals. The core insight is that agents receiving noisy intrinsic rewards should explore less aggressively, and this allocation can be determined automatically from signal-to-noise statistics. Successor Distance (SD), a quasimetric intrinsic reward, naturally produces distinguishable per-agent signal quality, completing the framework with convergence and ordering preservation guarantees. On seven cooperative benchmarks (MPE, SMAX, MABrax), our method achieves top-tier returns across all environments.

This paper proposes a novel method that incorporates empowerment when reasoning actions in reinforcement learning (RL), thereby achieving the flexibility of exploration-exploitation dilemma (EED). In previous methods, empowerment for promoting exploration has been provided as a bonus term to the task-specific reward function as an intrinsically-motivated RL. However, this approach introduces a delay until the policy that accounts for empowerment is learned, making it difficult to adjust the emphasis on exploration as needed. On the other hand, a trick devised for fine-tuning recent foundation models at reasoning, so-called best-of-N (BoN) sampling, allows for the implicit acquisition of modified policies without explicitly learning them. It is expected that applying this trick to exploration-promoting terms, such as empowerment, will enable more flexible adjustment of EED. Therefore, this paper investigates BoN sampling for empowerment. Furthermore, to adjust the degree of policy modification in a generalizable manner while maintaining computational cost, this paper proposes a novel BoN sampling method extended by Tsalis statistics. Through toy problems, the proposed method's cability to balance EED is verified. In addition, it is demonstrated that the proposed method improves RL performance to solve complex locomotion tasks.

The exploration-exploitation dilemma in reinforcement learning (RL) is a fundamental challenge to efficient RL algorithms. Existing algorithms for finite state and action discounted RL problems address this by assuming sufficient exploration over both state and action spaces. However, this yields non-implementable algorithms and sub-optimal performance. To resolve these limitations, we introduce a new class of methods with auto-exploration, or methods that automatically explore both state and action spaces. Auto-exploration can be applied in both the tabular and linear function approximation setting. Under algorithm-independent assumptions on the existence of an exploring optimal policy, both settings attain $O(ε^{-2})$ sample complexity to solve to $ε$ error. These complexities are novel since they avoid algorithm-dependent parameters seen in prior works, which may be arbitrarily large. The methods are also simple to implement because they are parameter-free. We achieve these results by integrating auto-exploration into policy mirror descent to avoid the (unknown) stationary distribution seen in prior art. In the tabular setting, we introduce a dynamic exploration time with a data-driven stopping time, while for linear function approximation we propose a new sampling distribution based on the discounted visitation distribution that covers a more general class of Markov chains.

As large language models (LLMs) are adopted into frameworks that grant them the capacity to make real decisions, it is increasingly important to ensure that they are unbiased. In this paper, we argue that the predominant approach of simply removing existing biases from models is not enough. Using a paradigm from the psychology literature, we demonstrate that LLMs can spontaneously develop novel social biases about artificial demographic groups even when no inherent differences exist. These biases result in highly stratified task allocations, which are less fair than assignments by human participants and are exacerbated in newer and larger models. In humans, emergent biases like these have been shown to result from exploration-exploitation trade-offs, where the decision-maker explores too little, allowing early observations to strongly influence impressions about entire demographic groups. To alleviate this effect, we explore a series of interventions targeting model inputs, problem structure, and explicit steering. While most interventions have limited effect, explicitly incentivizing exploration robustly reduces stratification, highlighting the need for better multifaceted objectives to mitigate bias. These results reveal that LLMs are not merely passive mirrors of human social biases, but can actively create new ones from experience, raising urgent questions about how these systems will shape societies over time.