Home Knowledge Base Qwen3-4B

Qwen3-4B

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

Sparrow: Sparse Rollout for Stable and Efficient Long-context RL of Large Language Models

arXiv:2606.08446v1 Announce Type: new Abstract: Despite being powerful, reinforcement learning with verifiable rewards (RLVR) induces extremely long COT, making it computationally expensive. Since RLVR per-step cost is dominated by long-context rollout generation, sparse attention offers a promising way to accelerate dense rollout.

arXiv CS 1d ago

Synthesize and Reward -- Reinforcement Learning for Multi-Step Tool Use in Live Environments

Announce Type: replace Abstract: Training LLMs to orchestrate multi-step tool calls is held back by three coupled obstacles: realistic stateful execution environments are costly to build, synthetic training queries are often detached from the server's actual state (so the generated tool calls fail to execute), and recall-based RL rewards incentivize verbose tool-calling patterns. We present PROVE (Programmatic Rewards On Verified Environments), a framework with three contributions: (1) a...

arXiv CS 6d ago

Synthesize and Reward -- Reinforcement Learning for Multi-Step Tool Use in Live Environments

Announce Type: new Abstract: Training LLMs to orchestrate multi-step tool calls is held back by three coupled obstacles: realistic stateful execution environments are costly to build, synthetic training queries are often detached from the server's actual state (so the generated tool calls fail to execute), and recall-based RL rewards incentivize verbose tool-calling patterns. We present PROVE (Programmatic Rewards On Verified Environments), a framework with three contributions: (1) a library...

arXiv CS 7d ago

HarnessForge: Joint Harness and Policy Evolution for Adaptive Agent Systems

Announce Type: new Abstract: LLM agents are increasingly expected to operate across heterogeneous task regimes that require distinct execution paradigms. This challenges fixed agent systems and motivates system-level meta-adaptation beyond isolated component updates. While existing works have adapted external harness or trained underlying reasoning policies, full-system adaptation remains insufficiently characterized.

arXiv CS 8d ago

Cost-Aware Diffusion Draft Trees for Speculative Decoding

arXiv:2606.01813v1 Announce Type: new Abstract: Speculative decoding accelerates inference by having a lightweight drafter propose tokens verified in parallel by the target language model. Block diffusion drafters such as DFlash generate an entire draft block in one pass, yielding per-position marginals; DDTree uses these to build a candidate tree that maximizes expected acceptance length under a fixed node budget. We observe, however, that acceptance length is non-decreasing in budget: it...

arXiv CS 8d ago

DFlare: Scaling Up Draft Capacity for Block Diffusion Speculative Decoding

arXiv:2606.02091v1 Announce Type: new Abstract: Block diffusion speculative decoding accelerates LLM inference by predicting all tokens within a block simultaneously for the target model to verify in parallel. Predicting an entire block at once requires a sufficiently capable draft model and effective utilization of the target model's internal knowledge. However, the state-of-the-art method DFlash constrains all draft layers to share a single fused representation derived from only a few...

arXiv CS 8d ago

DFlare: Scaling Up Draft Capacity for Block Diffusion Speculative Decoding

arXiv:2606.02091v2 Announce Type: replace Abstract: Block diffusion speculative decoding accelerates LLM inference by predicting all tokens within a block simultaneously for the target model to verify in parallel. Predicting an entire block at once requires a sufficiently capable draft model and effective utilization of the target model's internal knowledge. However, the state-of-the-art method DFlash constrains all draft layers to share a single fused representation derived from only a few...

arXiv CS 7d ago

Process Reward Agents for Steering Knowledge-Intensive Reasoning

arXiv:2604.09482v2 Announce Type: replace Abstract: Reasoning in knowledge-intensive domains remains challenging as intermediate steps are often not locally verifiable: unlike math or code, evaluating step correctness may require synthesizing clues across large external knowledge sources. As a result, subtle errors can propagate through reasoning traces, potentially never to be detected. Prior work has proposed process reward models (PRMs), including retrieval-augmented variants, but these...

arXiv CS 8d ago

Recover-LoRA for Aggressive Quantization: Reclaiming Accuracy in 2-Bit Language Models via Low-Rank Adaptation with Knowledge Distillation on Synthetic Data

arXiv:2606.04238v1 Announce Type: new Abstract: Aggressive weight quantization to 2-bit precision offers substantial throughput and memory gains for large language model (LLM) inference, but typically incurs severe accuracy degradation. These gains are particularly relevant for edge and on-device deployment, where memory capacity and bandwidth are primary constraints. In this work, we extend Recover-LoRA -- a lightweight, data-free accuracy recovery method originally developed for general...

arXiv CS 6d ago

Online Skill Learning for Web Agents via State-Grounded Dynamic Retrieval

arXiv:2606.04391v1 Announce Type: new Abstract: Language agents increasingly rely on reusable skills to improve multi-step web automation across related tasks. A growing line of work studies online skill learning, where agents continually induce skills from previous task trajectories and reuse them in future tasks on the fly. However, existing methods mainly reuse skills at the task-level: a fixed set of skills is retrieved based on the initial task instruction and then held fixed throughout...

arXiv CS 6d ago