The paper introduces ICA, an evidence‑centric framework that represents information from web‑tool interactions as stable, rendered snapshots, enabling comparison across trajectories. It proposes Information‑Aware Credit Assignment, a post‑hoc reward propagation technique that estimates turn‑level utility from rollout success and assigns dense rewards to steps that provide high‑utility information. When combined with GSPO, ICA consistently improves performance on several web‑search benchmarks such as BrowseComp, GAIA, Xbench‑DS, and Seal‑0.
arXiv:2610.17827v1 Announce Type: new Abstract: Existing approaches to training and evaluating search agents focus heavily on final-answer quality, largely neglecting how generated answers map back t...
arXiv:2608. 05102v1 Announce Type: new Abstract: Long-horizon search agents must make multiple sequential actions (steps) to search, retrieve, verify, and integrate evidence to reach a final answer.
arXiv:2608. 12764v1 Announce Type: cross Abstract: Deep search agents operate over trajectories spanning dozens of steps, yet standard reinforcement learning provides only a single outcome reward per trajectory, which is far too sparse for effective credit assignment.
arXiv:2607. 11172v1 Announce Type: new Abstract: Reinforcement learning for deep-search agents has largely focused on trajectory-level scoring -- outcome correctness, citation-aware rewards, and evidence coverage.
arXiv:2608.29953v1 Announce Type: new Abstract: Flat retrieval-augmented generation treats a corpus as a bag of chunks, discarding document hierarchy and cross document structure. We introduce Search...
The paper introduces AMBER, an append‑only memory framework for language‑model agents that interact over long horizons. AMBER lets agents jointly learn to reason, act, and write free‑form memory, guaranteeing retention by construction and enabling end‑to‑end reinforcement learning without extensive curated data. Experiments on WebArena Lite show AMBER outperforms overwrite‑based memory by 4.09 percentage points in average success and improves task completion rates in repeated runs.
arXiv:2607. 20668v1 Announce Type: cross Abstract: TextGrad improves language-model systems by revising text from feedback.
arXiv:2607. 13988v1 Announce Type: new Abstract: Multi-turn agents solve complex tasks through extended sequences of tool interactions before producing a final answer, making credit assignment a fundamental challenge during post-training.
arXiv:2512.23044v3 Announce Type: replace Abstract: Autonomous agents are shifting information seeking from passive retrieval toward proactive, open-ended research, yet this progress has largely bypa...
arXiv:2609.20844v1 Announce Type: new Abstract: Deepresearch (DR) agents interact with real-world web environments through multi-turn search and visit, causing their contexts to grow rapidly over tim...
arXiv:2606. 03329v1 Announce Type: new Abstract: Long-context tasks require LLMs to identify and preserve answer-relevant information from large contexts.
arXiv:2606. 32017v1 Announce Type: cross Abstract: Agentic reinforcement learning requires assigning credit to environment-facing actions such as searches, clicks, edits, navigation commands, and object interactions.