arXiv:2606. 09884v1 Announce Type: cross Abstract: We study two reproducible failure modes of deep multi-agent reinforcement learning in continuous-time pricing markets: (i) tacit cartel formation between competing DDPG agents, and (ii) actor--critic instability at high event rates.
arXiv:2604. 13517v4 Announce Type: replace-cross Abstract: Temporal credit assignment in reinforcement learning is often approached by introducing value estimates at multiple discount factors.
arXiv:2606. 03238v1 Announce Type: cross Abstract: Reinforcement learning from human feedback (RLHF) makes large-scale post-training possible by replacing an underspecified human objective with learned and scalable proxies.
The paper proposes CANOPY, a minimalist reinforcement learning protocol that addresses two common pitfalls—signal starvation and policy drift—in outcome‑only RL for long‑horizon interactive tasks. By scaling same‑task exploration, keeping updates on‑policy, and anchoring updates with KL divergence, CANOPY enables a Qwen3‑14B agent to achieve top leaderboard results on the AppWorld coding benchmark without auxiliary supervision or elaborate scaffolding. The approach also improves performance on SWE‑bench for a Qwen3.5‑9B model.
arXiv:2601. 17454v2 Announce Type: replace-cross Abstract: Centralized value learning underlies a broad class of multi-agent reinforcement learning methods, but its claimed advantage is typically evaluated in settings that confound coordination structure with function approximation and partial observability.
The paper studies a stationary decentralized Markov game where a focal agent experiences drifting rewards and dynamics due to learning peers, framing this as an agent‑centric continual reinforcement‑learning problem. It introduces the concept of an invariant core—maximal abstract patterns common to many successful trajectories—and proves a worst‑case conditioning theorem linking trajectory‑law drift to success coverage. The authors provide theoretical guarantees for survival horizon, first‑exit law, and regret, and validate their predictions with solvable models and empirical studies in continual control, cue‑MNIST, and Level‑Based Foraging.
arXiv:2607. 26313v1 Announce Type: cross Abstract: Agentic systems act, so a defect in the evidence they retrieve becomes a wrong action with a currency cost.
arXiv:2607. 17136v1 Announce Type: cross Abstract: Agentic computer-use RL is reported in single runs, and those numbers mislead.
arXiv:2606. 08446v1 Announce Type: cross Abstract: Despite being powerful, reinforcement learning with verifiable rewards (RLVR) induces extremely long COT, making it computationally expensive.
The paper argues that large language model (LLM) providers, constrained by compute, often degrade service during congestion by routing queries to smaller models, cutting reasoning effort, or truncating context. It shows that this practice misrepresents costs because degraded answers can fail, leading to retries that inflate traffic or churn that erodes lifetime value. By modeling inference allocation with newsvendor, retry, and queueing frameworks, the authors derive a ‘shadow price of intelligence’ that quantifies the marginal value of each query, revealing that throttling under congestion acts as a demand lever rather than a cost lever.
arXiv:2607. 20491v1 Announce Type: new Abstract: Standard evaluation benchmarks measure what a tool-using agent decides, not whether it arrives at that decision through the same process each time.
The paper argues that in multi‑turn agentic reinforcement learning, credit assignment should be viewed as a coverage problem rather than a targeting problem. It introduces verifier information density (V_d) as a structural metric, showing that terminal‑state verifiers operate in a low‑V_d regime where targeting fails. Experiments on tau^2‑bench, BFCL, and ToolACE‑2‑8B demonstrate that uniformly distributing reward across all turns outperforms sparse, targeted rewards, and that full chain coverage is necessary for optimal performance.
arXiv:2608. 02464v1 Announce Type: cross Abstract: LLM agents fail mid-episode -- they loop, cascade tool errors, drift off goal, fabricate results, or silently absorb corrupted content -- and the standard remedy, judging every step with a second LLM, costs more than the agent itself.