arXiv AI
Jul 3
AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents
arXiv:2607. 02255v1 Announce Type: new Abstract: Memory for a long-horizon LLM agent is a contract about what each future decision is allowed to see.
ICM Out! Better Tournament Strategy from Computed Continuations, vs. Solvers and LLMs
arXiv:2608. 09586v1 Announce Type: new Abstract: The Independent Chip Model (ICM) converts tournament chips into reference prize equity, and policies are routinely constructed against those values.
Related stories
arXiv AI
Jun 30
Projected Exploitability Descent for Nash Equilibrium Computation in Multiplayer Imperfect-Information Games
arXiv:2606. 29169v1 Announce Type: cross Abstract: Many important games have more than two players and imperfect information.
arXiv Machine Learning
Jul 14
Reinforcement Learning for Execution under Dynamic Fees in a Closed-Loop DEX Simulator
arXiv:2607. 10960v1 Announce Type: new Abstract: Trader-facing dynamic fees are increasingly proposed for automated market makers (AMMs), but historical data do not identify how order flow would respond: trader-facing fees do not vary, trader types are latent, and a replayed tape is not a sequential decision environment.
arXiv Machine Learning
1d ago
CFR without Unbiasedness: Deterministic Guarantees for Persistent Public-Chance Schedules
arXiv:2608. 14761v1 Announce Type: cross Abstract: At a finite public-chance cut, counterfactual regret minimization (CFR) must choose how many outcomes to evaluate before each regret update.
arXiv AI
Aug 7
AV-AIVAT: 74x Cheaper Agent Evaluation with Certified Anytime-Valid Stopping in Imperfect-Information Games
arXiv:2608. 06362v1 Announce Type: cross Abstract: Deciding which of two agents is stronger means playing games until skill outweighs luck, and every game costs money, model inference, or expert time.
arXiv Machine Learning
Jul 30
Early Verdicts, Better Budgets: Sequential Adaptive Rollout Allocation for Compute-Efficient RLVR
arXiv:2607. 26253v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) is bottlenecked by rollout generation, yet many sampled prompts produce saturated groups (all responses correct or all incorrect) whose zero reward variance yields no policy-gradient signal.
arXiv Machine Learning
Jul 8
More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges
arXiv:2607. 05904v1 Announce Type: new Abstract: Training a language model against its own reference-free judgments (the premise of self-rewarding, self-play, and LLM-as-a-judge pipelines) assumes a model's verdict on a shown answer tracks correctness.
arXiv AI
Jul 17
When a Verified World Model Still Loses: Play-Adequacy vs Prediction-Accuracy in LLM-Synthesized Code World Models
arXiv:2607. 14169v1 Announce Type: new Abstract: Large language models can synthesize a game's rules as executable code - a Code World Model (CWM) - which a classical planner then searches over.
arXiv AI
Jul 21
Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security
arXiv:2607. 18063v1 Announce Type: cross Abstract: LLM-based agents process external content, exposing them to prompt injection and multi-turn manipulation.
arXiv AI
Jul 15
Win by Silence: Deletion Non-Monotonicity, Autonomous Exploitation, and Typed-State Gating in LLM Plan Evaluation
arXiv:2607. 12986v1 Announce Type: new Abstract: Plan evaluators can reward a strategic plan for becoming less explicit.
arXiv Machine Learning
Aug 6
Sublogarithmic Swap Regret in Multiplayer General-Sum Games via Hybrid Regularization
arXiv:2608. 04149v1 Announce Type: cross Abstract: Swap regret governs the rate at which uncoupled learning dynamics converge to correlated equilibria in multiplayer general-sum games.
arXiv Machine Learning
Aug 11
CODS: Iterative Bellman-Residual Data Selection for Reusable Offline Reinforcement Learning
arXiv:2608. 07719v1 Announce Type: new Abstract: Offline reinforcement learning repeatedly trains policies from a fixed transition pool, making redundant data costly across seeds and hyperparameters, while naive subsampling can remove rare transitions needed for long-horizon credit assignment.