arXiv:2609.36572v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has been extended to Large Vision-Language Models (LVLMs), and perception-aware methods further e...
arXiv:2609.27532v1 Announce Type: new Abstract: Long-horizon agentic tasks require an agent to modify an environment through a sequence of tool calls, with success determined by the final state. The...
arXiv:2606. 16364v1 Announce Type: new Abstract: LLM agents mis-call tools, and the natural guess is that the model failed to see the right tool in a crowded harness.
arXiv:2609.13308v1 Announce Type: cross Abstract: A companion evaluation found that naming the target part in a manipulation prompt increased action accuracy by 0.32-0.63 across eight vision-language...
arXiv:2606. 08151v1 Announce Type: new Abstract: Tool-using LLM agents often fail not because relevant text is absent, but because decisive evidence is not selected, compressed, or surfaced at action time.
arXiv:2603.01209v3 Announce Type: replace Abstract: In CodeAct, language-model agents write Python that calls tools and use execution feedback to choose actions. Persistent runtimes preserve Python v...
arXiv:2607. 03702v1 Announce Type: new Abstract: Large language model (LLM) agents have shown strong decision-making capabilities in long-horizon interactive tasks, yet they still struggle to effectively leverage failed trajectories: full retries incur high interaction costs, while experience retrieval tends to dilute critical experience signals.
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.
The paper investigates how providing execution traces to multimodal judges in agentic video‑generation systems can bias their verdicts. On a benchmark of 109 two‑event clips, traces that falsely report successful tool calls cause large‑language‑model judges to incorrectly accept 78–90 % of failures, while contradictory traces lead to 100 % rejection of correct clips. The effect persists even when judges are instructed to consider only the video frames, indicating that the vulnerability stems from the judges’ learned trust in tool logs rather than the visual content itself.
The paper introduces GLANCE, a one‑pass block drafting method that enables lossless speculative decoding for vision‑language models. By using a block‑diffusion head that reads the fused vision‑language state, GLANCE eliminates the need for the drafter to process the image at every step, allowing it to fill an entire block in a single forward pass. Experiments show that GLANCE can decode up to 2.93× faster than autoregressive decoding while maintaining exact greedy decoding results across multiple tasks.
The paper introduces the Compute-Value Audit (CVA), a sequential framework that evaluates whether extra sampling during test‑time scaling for video world models actually yields a net benefit after accounting for the compute cost of generation and verification. On 192 Physics‑IQ scenes, increasing the sample pool from 4 to 16 candidates improves oracle quality by +9.23 IQ, yet common metrics such as Flow, Cycle, and VideoReward fail to reliably recover this headroom, and adaptive‑depth policies recover only 42‑69% of the potential gain. Only a few specific interventions—anchor‑explorer in a sparse PRM800K setting, MMLU‑Pro exposing a predictive‑state gap, and a privileged paired‑future upper bound—successfully pass all CVA stages, indicating that sampling headroom is valuable only when it can be converted into a reliable decision that survives the full compute charge.
The paper investigates how language‑model judges can make version‑dependent errors when evaluating upgraded agents. Using 35 public coding‑agent submissions, two customer‑service agents, and over a thousand expert‑labeled trajectories, the authors show that fixed judges often reject task‑conditioned error invariance and can incorrectly approve failed patches, especially as agent capability increases. Paired audits of current outputs reduce interval width only marginally, and the study concludes that independent human patch review is still necessary.